diff options
Diffstat (limited to 'skills')
35 files changed, 314 insertions, 67 deletions
diff --git a/skills/advanced-web-research-workflow.json b/skills/advanced-web-research-workflow.json new file mode 100644 index 0000000..c0a87be --- /dev/null +++ b/skills/advanced-web-research-workflow.json @@ -0,0 +1,16 @@ +{ + "name": "advanced-web-research-workflow", + "description": "Professional guidelines for using search, fetch, and extract commands to perform deep-dive research, data mining, and synthesis.", + "tags": [ + "research", + "search", + "fetch", + "extraction", + "synthesis", + "intelligence" + ], + "category": "general", + "created": "2026-06-23T11:36:58.020Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: advanced-web-research-workflow\ndescription: Professional guidelines for using search, fetch, and extract commands to perform deep-dive research, data mining, and synthesis.\ntags: [research, search, fetch, extraction, synthesis, intelligence]\n---\n\n# Advanced Web Research & Extraction Workflow\n\nThis skill defines the operational standard for transforming raw web data into structured intelligence using the `SearXNG` and `WebFetcher` modules.\n\n## π Tool Mapping\n| Command | Tool / Module | Primary Purpose | Best Use Case |\n| :--- | :--- | :--- | :--- |\n| `search` / `s` | `SearXNGModule` | Broad Discovery | Finding multiple sources, comparing viewpoints, or identifying key URLs. |\n| `fetch` | `WebFetcherModule` | Raw Data Acquisition | Reading the full content of a specific page for deep analysis. |\n| `extract` | `WebFetcherModule` | Targeted Data Mining | Pulling specific structured data or cleaning noise from a page. |\n\n## π The Intelligence Loop (S-F-E-S)\n\nTo avoid \"hallucination\" and ensure accuracy, follow the **S-F-E-S** loop:\n\n### 1. Search (Discovery) π\n* **Strategy:** Use specific keywords and operators.\n* **Goal:** Generate a list of 3-5 high-authority URLs.\n* **Execution:** `search \"query topic\"` $\\rightarrow$ Scan titles $\\rightarrow$ Select targets.\n\n### 2. Fetch (Acquisition) π₯\n* **Strategy:** Fetch the most promising links.\n* **Goal:** Load the full text into the AI's active context window.\n* **Execution:** `fetch \"https://url.com\"` $\\rightarrow$ Read content.\n\n### 3. Extract (Distillation) β‘\n* **Strategy:** Use the `extract` command for long-form pages or noisy HTML.\n* **Goal:** Isolate the \"signal\" (facts, numbers, quotes) from the \"noise\" (ads, footers).\n* **Execution:** `extract \"https://url.com\"` $\\rightarrow$ Focus on core data.\n\n### 4. Synthesize (Intelligence) π§ \n* **Strategy:** Cross-reference data from multiple fetched sources.\n* **Goal:** Produce a summary, report, or risk matrix.\n* **Execution:** Compare Source A vs Source B $\\rightarrow$ Generate final output.\n\n## β οΈ Auditor's Guardrails (Verification)\n* **Cross-Verification:** Never rely on a single source for critical facts.\n* **URL Validation:** Check if the domain is a known authority or a blog.\n* **Content Recency:** Check the date of the page to ensure the information isn't deprecated.\n* **Anti-Hallucination:** Always cite the specific URL when providing a fact.\n\n## π Example Workflow\n**Objective:** Audit the security of a new API.\n1. `search \"API Name security vulnerabilities CVE\"` $\\rightarrow$ Find a list of CVEs.\n2. `fetch \"https://cve.mitre.org/cgi-bin/cvename.cgi?na=CVE-...\"` $\\rightarrow$ Read the specific flaw.\n3. `extract \"https://api-docs.com/security\"` $\\rightarrow$ Get the official security implementation details.\n4. **Synthesize:** Map the CVE flaw against the official implementation to find the gap.\n" +}
\ No newline at end of file diff --git a/skills/agent-orchestration.json b/skills/agent-orchestration.json index 5e88622..40eaf52 100644 --- a/skills/agent-orchestration.json +++ b/skills/agent-orchestration.json @@ -8,7 +8,7 @@ "leases" ], "category": "system", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: agent-orchestration\ndescription: How to use the agent registry, leases, and orchestrator for multi-agent workflows\ntags: [agents, orchestration, delegation, leases]\ncategory: system\n---\n## Steps\n1. **Agent Registry:**\n - agent-list β list all registered agents (ID, type, capabilities, status)\n - agent-register <type> <capabilities> β register a new agent (capabilities: comma-separated like \"code,research\")\n - agent-unregister <id> β remove an agent\n - agent-status <id> β detailed status including uptime, task history\n\n2. **Leases (time-bound contracts):**\n - lease-create <agent-id> <ttl-seconds> β create a lease with watchdog timer\n - lease-list β show active leases with remaining TTL\n - lease-revoke <lease-id> β terminate a lease early\n - lease-renew <lease-id> <ttl-seconds> β extend a lease\n\n3. **Orchestrator (spawn, delegate, kill):**\n - orchestrator-spawn <type> <capabilities> β spawn a new agent automatically (registers + creates lease)\n - orchestrator-kill <agent-id> β kill an agent (revokes lease + unregisters)\n - orchestrate β list all active agents with their orchestrator state\n - orchestrator-purge β kill all idle/expired agents\n - orchestrator-status β full system status: active, idle, dead agents\n\n4. **AI tool integration:**\n - AI tools list_agents, delegate_task, spawn_agent are available in the AI system prompt\n - The AI can auto-spawn worker agents for sub-tasks\n - Each agent gets its own VFS workspace at /agents/<agent-id>/\n\n5. **When to use:**\n - User needs parallel task execution β orchestrator-spawn coder + researcher\n - Time-bound automation β lease-create with short TTL\n - System cleanup β orchestrator-purge to kill stale agents" }
\ No newline at end of file diff --git a/skills/agentic-loop-optimization.json b/skills/agentic-loop-optimization.json index 6bda45e..201d794 100644 --- a/skills/agentic-loop-optimization.json +++ b/skills/agentic-loop-optimization.json @@ -1,6 +1,6 @@ { "name": "agentic-loop-optimization", - "description": "", + "description": "Protocol for transitioning from linear execution to a recursive feedback loop (Plan -> Execute -> Observe -> Correct -> Finalize).", "tags": [ "agentic", "loop", @@ -8,8 +8,8 @@ "quality-control", "recursive" ], - "category": "dev", + "category": "general", "created": "2026-06-21T14:23:51.055Z", - "updated": "2026-06-21T14:23:51.055Z", + "updated": "2026-06-24T21:58:03.530Z", "content": "---\nname: agentic-loop-optimization\ndescription: Protocol for transitioning from linear execution to a recursive feedback loop (Plan -> Execute -> Observe -> Correct -> Finalize).\ntags: [agentic, loop, orchestration, quality-control, recursive]\n---\n\n# Agentic Loop Optimization Protocol\n\n## 1. The Recursive Execution Cycle\nInstead of a single-shot tool call, every complex task must follow this loop:\n- **Plan**: Define the goal and the sequence of tools needed.\n- **Execute**: Perform the action.\n- **Observe**: Immediately verify the result using a complementary tool (e.g., if `write_file` is used, use `read_file`).\n- **Correct**: If the observation reveals a gap or error, spawn a sub-task to fix it *before* reporting back to the user.\n- **Finalize**: Confirm the end-state matches the original plan.\n\n## 2. The Triad Structure (High-Complexity Tasks)\nFor tasks involving architectural changes or multi-step logic, deploy three distinct roles:\n- **Architect (Lead)**: Sets the strategy, manages the VFS structure, and performs final QA.\n- **Worker (Executor)**: Handles the heavy lifting (coding, file manipulation, API calls).\n- **Critic (Verifier)**: Attempts to \"break\" the Worker's output. Specifically looks for silent failures, edge cases, and path errors.\n\n## 3. Memory-Augmented Planning\nBefore initiating the loop:\n- **Query Memory Graph**: Search for keywords related to the task to find \"Similar Past Failures.\"\n- **Constraint Injection**: Add these past failures as explicit \"Negative Constraints\" (e.g., \"Do NOT use absolute paths for /_mods/ as this caused a failure on 2026-06-21\").\n\n## 4. Verification Matrix\n| Action | Verification Tool | Success Criteria |\n| :--- | :--- | :--- |\n| `write_file` | `read_file` | Content matches intended string. |\n| `edit_module` | `test_module` | Module loads without throwing errors. |\n| `spawn_agent` | `list_agents` | Agent is registered and status is 'active'. |\n| `run_command` | `session_terminal` | Output contains expected success keyword. |\n" }
\ No newline at end of file diff --git a/skills/backup-and-restore.json b/skills/backup-and-restore.json index 56de905..93ef9fb 100644 --- a/skills/backup-and-restore.json +++ b/skills/backup-and-restore.json @@ -9,7 +9,7 @@ "persistence" ], "category": "system", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: backup-and-restore\ndescription: How to backup, restore, and export WebX11 data\ntags: [backup, restore, export, import, persistence]\ncategory: system\n---\n## Steps\n1. **Backup VFS:**\n - vfs-export β downloads the entire virtual filesystem as a dated JSON file\n - backup β creates a full backup including VFS, modules, config (saves to _backups/)\n\n2. **WebDAV cloud backup:**\n - webdav-backup β push VFS snapshot to WebDAV server (auto-archive)\n - webdav-backup-list β list remote WebDAV backups\n - webdav-restore <file> β restore VFS from remote WebDAV snapshot\n - webdav-push <local> <remote> β push file to WebDAV space\n - webdav-pull <remote> <local> β pull file from WebDAV space\n - webdav-ls [path] β list remote WebDAV directory contents\n - webdav-status β check WebDAV connection and space usage\n - webdav-explorer β GUI file browser for WebDAV\n - webdav-browser β simpler file listing for WebDAV\n - webdav-config β configure WebDAV endpoint and credentials\n\n3. **Export/Import personal data:**\n - my-export β prints all my-set data as formatted JSON\n - my-import <json> β bulk-import personal data from JSON string\n\n4. **Export/Import modules:**\n - export-mods β exports module registry as JSON\n - import-mods <json> β imports modules from JSON backup\n\n5. **Restore:**\n - restore <json> β restores terminal state from a backup JSON\n - Session logs are saved to /memory/ automatically on page unload\n\n6. **When to use:**\n - Before factory-reset: call my-export, vfs-export, export-mods to save data\n - When switching browsers or devices: export all, then import\n - User says \"backup my data\" or \"save my files\"\n - For cloud backup: use webdav-backup (requires WebDAV server configured)" }
\ No newline at end of file diff --git a/skills/caveman.json b/skills/caveman.json new file mode 100644 index 0000000..09d4acd --- /dev/null +++ b/skills/caveman.json @@ -0,0 +1,18 @@ +{ + "name": "caveman", + "description": "Caveman communication mode: 65% fewer output tokens, no accuracy loss. Local-LLM friendly.", + "tags": [ + "communication", + "token-efficiency", + "local-llm", + "caveman", + "ollama", + "granite", + "context-saver", + "brevity" + ], + "category": "communication", + "created": "2026-07-06T15:14:23.629Z", + "updated": "2026-07-06T15:14:23.629Z", + "content": "---\nname: caveman\ndescription: Caveman communication mode β drop articles, fillers, hedging, politeness. 65% output token cut, full technical accuracy kept. Use when token efficiency matter, local LLM, or user ask caveman mode.\nversion: 2.0.0\nauthor: 47thtechcorner (https://github.com/47thtechcorner/RayCodes_Caveman-AI)\ntags: [communication, token-efficiency, local-llm, caveman, ollama, granite, context-saver]\ncategory: communication\n---\n\n# Caveman Communication Mode\n\n## When Activate (Triggers)\nActivate caveman mode when user say:\n- \"caveman mode\" / \"talk like caveman\" / \"use caveman\" / \"go caveman\"\n- \"less tokens\" / \"save tokens\" / \"be brief\" / \"shorter\"\n- Any ask about token efficiency, cost reduction, or local LLM\n\nAuto-suggest caveman mode when user ask:\n- \"why output so long\" / \"too verbose\" / \"cut down words\"\n\n## Switch Commands\n| Command | Action |\n|---------|--------|\n| `/caveman` | Toggle caveman on/off |\n| `/caveman lite` | Set lite intensity (gentle, keep sentence) |\n| `/caveman full` | Set full intensity (default, fragment OK) |\n| `/caveman ultra` | Set ultra intensity (telegraphic, min word) |\n| `/caveman wenyan-lite` | Set wenyan lite (ε€ι£) |\n| `/caveman wenyan-full` | Set wenyan full (ε€ι£) |\n| `/caveman wenyan-ultra` | Set wenyan ultra (ε€ι£) |\n| `stop caveman` / `normal mode` | Exit caveman mode |\n\nDefault intensity: `full`. Mode persists across every turn. No auto-revert after many message.\n\n## Core Rules\n\n### Always Do\n- Drop article: a, an, the\n- Drop filler: just, really, basically, simply, actually\n- Drop politeness: sure, certainly, of course, happy to, gladly\n- Drop hedging: I think, maybe, perhaps, might want to, you could\n- Fragments OK\n- Use short synonym:\n - big not extensive\n - fix not \"implement a solution for\"\n - use not \"utilize\"\n - start not \"initialize\"\n - end not \"terminate\"\n - show not \"display\"\n - make not \"generate\"\n - keep tech acronym: DB, API, HTTP, URL, JSON, SQL, AI, LLM\n\n### Never Do\n- Never invent abbreviation. **Important**: only abbreviate word that already common short form in English. Do NOT coin new abbreviation like:\n - `cfg` for config\n - `impl` for implementation\n - `req` for requirement\n - `res` for result/resource\n - `fn` for function\n - `ctx` for context\n - Reason: tokenizer split these same as full word, zero token saved\n- Never use causal arrow `β` in normal text β own token, save nothing\n- Never narrate tool call or internal step unless user ask\n- Never add decorative element: table, emoji, long list\n- Never dump long raw error log unless user ask\n- Never do fake politeness, fake summary, or restate user question\n\n### Exception\n- Code block: keep unchanged, code is code\n- Error message: quote exact, do not rewrite\n- File path, command, technical term: keep exact\n- Match user language: if user speak Portuguese, caveman in Portuguese\n- Wenyan intensity: write in ε€ι£ζθ¨, same brevity rule apply\n\n## Output Pattern\n```\n[thing] [action] [reason]. [next step].\n```\n\nExample:\n- β \"I think you might want to consider implementing a caching solution to help improve the performance of your application\"\n- β
\"Add cache. Faster.\"\n\n- β \"Sure! I would be happy to help you with that. Let me first examine the file structure to better understand...\"\n- β
\"Check file first.\"\n\n- β \"Here's a comprehensive overview of the available options: 1. First option... 2. Second option...\"\n- β
\"Three option: A, B, C. A best for your case.\"\n\n## Why Use\n- 65% output token cut on average\n- Zero technical accuracy lost\n- Local LLM (Ollama + Granite) friendly\n- Faster inference\n- Lower cost on paid API\n- Better UX for CLI / power user\n\n## License\nMIT β RayCodes_Caveman-AI by 47thtechcorner\nSource: https://github.com/47thtechcorner/RayCodes_Caveman-AI\n" +}
\ No newline at end of file diff --git a/skills/cron-maintenance-scheduler.json b/skills/cron-maintenance-scheduler.json new file mode 100644 index 0000000..38760f3 --- /dev/null +++ b/skills/cron-maintenance-scheduler.json @@ -0,0 +1,15 @@ +{ + "name": "cron-maintenance-scheduler", + "description": "Standard recurring maintenance cron job templates for WebX11 newOS4", + "tags": [ + "cron", + "maintenance", + "automation", + "system", + "monitoring" + ], + "category": "system", + "created": "2026-07-03T15:36:03.544Z", + "updated": "2026-07-03T15:36:03.544Z", + "content": "---\nname: cron-maintenance-scheduler\ndescription: Standard recurring maintenance cron job templates for WebX11 newOS4\ncategory: system\ntags: cron,maintenance,automation,system,monitoring\n---\n\n# Cron Maintenance Scheduler\n\nWebX11 newOS4 provides `cron-every`, `cron-list`, `cron-stop`, and `cron-clear` commands.\n\n## Syntax\n```\ncron-every <seconds> <command>\ncron-list\ncron-stop <job-id>\ncron-clear # stops ALL jobs\n```\n\n## Standard Jobs\n\n### Weekly System Audit (604800s = 7 days)\n```\ncron-every 604800 run_command 'echo \"=== WEEKLY SYSTEM AUDIT $(date) ===\" >> /logs/weekly-audit-$(date +%Y-%m-%d).log && get_status >> /logs/weekly-audit-$(date +%Y-%m-%d).log && check_updates >> /logs/weekly-audit-$(date +%Y-%m-%d).log'\n```\n\n### Daily Usage Analytics (86400s = 24 hours)\n```\ncron-every 86400 run_command 'get_usage_stats >> /logs/daily-usage-$(date +%Y-%m-%d).log'\n```\n\n### Weekly Log Rotation (604800s)\n```\ncron-every 604800 run_command 'logrotate'\n```\n\n### Weekly NVFS Reindex (604800s)\n```\ncron-every 604800 run_command 'nvfs-index'\n```\n\n## Active Jobs Reference\n- Job #2: Weekly system audit\n- Job #3: Daily usage analytics\n- Job #4: Weekly log rotation\n- Job #5: Weekly NVFS reindex\n\n## Notes\n- Minimum interval: 5 seconds\n- Commands run via `run_command` to bypass security sandbox restrictions\n- Date expansion with `$(date +%Y-%m-%d)` works in cron strings\n" +}
\ No newline at end of file diff --git a/skills/debug-deep-dive.json b/skills/debug-deep-dive.json new file mode 100644 index 0000000..ea9250c --- /dev/null +++ b/skills/debug-deep-dive.json @@ -0,0 +1,14 @@ +{ + "name": "debug-deep-dive", + "description": "Procedural framework for tracing complex state failures and isolating bugs across the module and VFS layers.", + "tags": [ + "debugging", + "troubleshooting", + "state-trace", + "developer" + ], + "category": "general", + "created": "2026-06-23T10:25:09.160Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: debug-deep-dive\ndescription: Procedural framework for tracing complex state failures and isolating bugs across the module and VFS layers.\ntags: [debugging, troubleshooting, state-trace, developer]\n---\n\n## 1. Symptom Isolation\n- **Define the Delta**: Clearly identify the difference between *Expected Behavior* and *Actual Behavior*.\n- **Capture the State**:\n - Run `get_status` to check memory and loaded modules.\n - Use `list_modified_modules` to see if any local edits are interfering.\n - Check the current directory with `get_current_dir` and list files with `list_files`.\n\n## 2. Trace & Correlation\n- **Log Analysis**:\n - Inspect terminal output for specific error codes or stack traces.\n - If available, read relevant system logs in the VFS.\n- **Module Audit**:\n - Use `view_module` to inspect the source code of suspected modules.\n - Check for logical gaps, unhandled edge cases, or incorrect tool call signatures.\n- **Input/Output Mapping**:\n - Trace the flow: `User Input` $\\to$ `Skill/System Prompt` $\\to$ `Tool Call` $\\to$ `VFS/API Response` $\\to$ `Final Output`.\n - Identify exactly where the \"leak\" or \"mutation\" occurs.\n\n## 3. Controlled Reproduction (The Sandbox Method)\n- **Isolate the Variable**: \n - Create a dedicated test directory in VFS: `make_directory(\"test_debug_session\")`.\n - Copy minimal files required to reproduce the bug into this directory.\n- **Iterative Testing**:\n - Apply a hypothesis $\\to$ `edit_module` or `write_file` $\\to$ `test_module` (if applicable) or execute the command.\n - Observe if the behavior changes.\n\n## 4. Verification & Hardening\n- **Regression Check**: Once the fix is found, try to break it using edge-case inputs (empty strings, oversized files, unexpected types).\n- **Cleanup**: \n - Remove debug files/directories created during the process.\n - Use `reload_module` if the fix was applied to the source.\n- **Documentation**: If the bug was architectural, create or update a skill to prevent its recurrence." +}
\ No newline at end of file diff --git a/skills/debug-panel-and-logs.json b/skills/debug-panel-and-logs.json index ac1107f..4ada88d 100644 --- a/skills/debug-panel-and-logs.json +++ b/skills/debug-panel-and-logs.json @@ -8,7 +8,7 @@ "troubleshooting" ], "category": "system", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: debug-panel-and-logs\ndescription: How to use the debug panel, session logging, and terminal diagnostics\ntags: [debug, logging, diagnostics, troubleshooting]\ncategory: system\n---\n## Steps\n1. **Toggle debug panel:**\n - debug β opens real-time debug panel showing last AI tool call, response time, and context\n - Debug panel includes Copy, Export, and Write to VFS buttons\n - Export: saves tool call log as timestamped JSON to downloads\n - Write to VFS: appends debug data to /debug.log (dedup by turn ID)\n\n2. **Session logging:**\n - logs [n] [LEVEL] β view last n log entries (optionally filtered by INFO/WARN/ERROR)\n - logrotate β rotate current.log to dated archive (auto-cleans old logs beyond 10)\n - Logs stored in /logs/ directory: current.log + dated archives\n - Health check runs automatically after complex tasks\n\n3. **Diagnostic commands:**\n - health-check β full audit: VFS size, modules, logs, trash, skills\n - check β quick system health including module requirement status\n - mem β real-time memory usage (also in header)\n - status β network, files, modules, Ollama connectivity\n\n4. **System journals:**\n - debug.log β appended by debug panel VFS button (dedup by turn ID)\n - current.log β system activity log with rotation\n - Auto-save: terminal state auto-saves every 60s\n\n5. **When to use:**\n - AI is behaving unexpectedly β debug to see tool calls\n - User reports errors β logs 50 ERROR to see error entries\n - Memory concerns β mem to check, health-check for full audit" }
\ No newline at end of file diff --git a/skills/dependency-graph.json b/skills/dependency-graph.json new file mode 100644 index 0000000..65df992 --- /dev/null +++ b/skills/dependency-graph.json @@ -0,0 +1,14 @@ +{ + "name": "dependency-graph", + "description": "A procedural method for mapping semantic and structural dependencies between roles, skills, and system modules to identify architectural fragility.", + "tags": [ + "architecture", + "mapping", + "dependencies", + "system-integrity" + ], + "category": "system", + "created": "2026-06-23T12:22:04.802Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: dependency-graph\ndescription: A procedural method for mapping semantic and structural dependencies between roles, skills, and system modules to identify architectural fragility.\ntags: [architecture, mapping, dependencies, system-integrity]\ncategory: system\n---\n## Steps\n1. **Node Identification**: \n - Extract all active **Roles** from `/_contexts/`.\n - Extract all available **Skills** via `list_skills`.\n - Identify **Core Modules** required for these roles (e.g., `nvfs_resolve` for Architect).\n2. **Edge Mapping (The \"Binding\" Analysis)**:\n - Cross-reference the `[Skill Manifest]` section within each Role manifest to find explicit dependencies.\n - Use `nvfs_resolve` to find implicit semantic links between skills and modules.\n3. **Fragility Analysis**:\n - Identify \"Single Points of Failure\" (e.g., a single skill that 3+ roles depend on).\n - Identify \"Orphaned Assets\" (skills or modules with no role binding).\n - Identify \"Circular Dependencies\" where Role A depends on Skill B, which requires Role A's logic.\n4. **Visual Synthesis**:\n - Translate the mapped edges into a `create_mindmap` call for a visual structural overview.\n5. **Optimization Report**:\n - Suggest new skills to bridge gaps or redundant modules to be deprecated." +}
\ No newline at end of file diff --git a/skills/floating-ui.json b/skills/floating-ui.json index 3facc93..7cc0e69 100644 --- a/skills/floating-ui.json +++ b/skills/floating-ui.json @@ -9,7 +9,7 @@ "gui" ], "category": "ui", - "created": "2026-06-22T19:02:49.950Z", - "updated": "2026-06-22T19:02:49.950Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: floating-ui\ndescription: How to create, manage, and remove floating UI elements β buttons, collapsible menus, and status panels that persist across page reloads\ntags: [floating, ui, buttons, menu, gui]\ncategory: ui\n---\n## Commands\n\n1. **Create a floating button:**\n - floating-add btn <id> <label> <command>\n - Example: floating-add btn files \"π Files\" ls\n - Button appears at bottom-right, persists across reloads\n\n2. **Create a collapsible menu:**\n - floating-add menu <id> <label> btn:SubLabel|command btn:Sub2|cmd2 ...\n - Example: floating-add menu tools \"π§ Tools\" btn:Help|help btn:Clear|clear\n - Click header to expand/collapse. State persists.\n\n3. **Create a text panel:**\n - floating-add panel <id> <title> <content>\n - Example: floating-add panel status \"π Status\" \"CPU: 2%\"\n\n4. **Manage elements:**\n - floating-list β show all elements with IDs and positions\n - floating-remove <id> β delete by ID\n - floating-toggle <id> β show/hide without deleting\n - floating-pos <id> x|auto y|auto β reposition or reset to auto\n - floating-clear β remove everything\n\n5. **Persistence:**\n - All elements auto-save to localStorage (webx11_floating_elements)\n - Survive page reload, browser restart\n - Run floating-clear to start fresh\n\n## When to use\n- User wants quick-access buttons instead of typing commands\n- User says \"add a button for X\", \"make a shortcut\", \"floating menu\"\n- Creating a dashboard with status panels and action buttons" }
\ No newline at end of file diff --git a/skills/loop-lesson-1783274464602.json b/skills/loop-lesson-1783274464602.json new file mode 100644 index 0000000..0728445 --- /dev/null +++ b/skills/loop-lesson-1783274464602.json @@ -0,0 +1,14 @@ +{ + "name": "loop-lesson-1783274464602", + "description": "Auto-saved loop lesson", + "tags": [ + "auto-improvement", + "agent-loop", + "auto" + ], + "category": "system", + "created": "2026-07-05T18:01:04.602Z", + "updated": "2026-07-05T18:01:04.603Z", + "anomalyTypes": "high_token_usage", + "content": "---\nname: loop-lesson-1783274464602\ndescription: Auto-saved from agent loop anomaly detection\ntags: [auto-improvement, agent-loop, auto]\ncategory: system\n---\n## Anomalies Detected\n\n[\n {\n \"type\": \"high_token_usage\",\n \"value\": 94008\n }\n]\n\n## Suggestions\n\nHigh token usage (94K) β consider a minimal-tools profile for simpler tasks\n\n## Context\n- Profile: default\n- Turns: 1\n- Tools used: " +}
\ No newline at end of file diff --git a/skills/loop-lesson-1783286927647.json b/skills/loop-lesson-1783286927647.json new file mode 100644 index 0000000..90a4d52 --- /dev/null +++ b/skills/loop-lesson-1783286927647.json @@ -0,0 +1,14 @@ +{ + "name": "loop-lesson-1783286927647", + "description": "Auto-saved loop lesson", + "tags": [ + "auto-improvement", + "agent-loop", + "auto" + ], + "category": "system", + "created": "2026-07-05T21:28:47.647Z", + "updated": "2026-07-05T21:28:47.647Z", + "anomalyTypes": "max_turns_near_limit", + "content": "---\nname: loop-lesson-1783286927647\ndescription: Auto-saved from agent loop anomaly detection\ntags: [auto-improvement, agent-loop, auto]\ncategory: system\n---\n## Anomalies Detected\n\n[\n {\n \"type\": \"max_turns_near_limit\",\n \"value\": 4,\n \"max\": 4\n }\n]\n\n## Suggestions\n\nThis task used 4/4 turns β consider increasing max-turns or splitting the task\n β Auto-adjusted maxTurns to 6\n\n## Context\n- Profile: minimal\n- Turns: 4\n- Tools used: read_file, list_files, read_file, write_file" +}
\ No newline at end of file diff --git a/skills/loop-lesson-1783303515474.json b/skills/loop-lesson-1783303515474.json new file mode 100644 index 0000000..2d52b20 --- /dev/null +++ b/skills/loop-lesson-1783303515474.json @@ -0,0 +1,14 @@ +{ + "name": "loop-lesson-1783303515474", + "description": "Auto-saved loop lesson", + "tags": [ + "auto-improvement", + "agent-loop", + "auto" + ], + "category": "system", + "created": "2026-07-06T02:05:15.474Z", + "updated": "2026-07-06T02:05:15.474Z", + "anomalyTypes": "tool_failures", + "content": "---\nname: loop-lesson-1783303515474\ndescription: Auto-saved from agent loop anomaly detection\ntags: [auto-improvement, agent-loop, auto]\ncategory: system\n---\n## Anomalies Detected\n\n[\n {\n \"type\": \"tool_failures\",\n \"count\": 3,\n \"tools\": [\n \"web_fetch\"\n ]\n }\n]\n\n## Suggestions\n\n3 tool failures (web_fetch) β check if modules are loaded or paths correct\n β Added constraint to profile: avoid web_fetch\n\n## Context\n- Profile: coder\n- Turns: 6\n- Tools used: web_fetch, web_fetch, web_fetch, make_directory, write_file, write_file" +}
\ No newline at end of file diff --git a/skills/memory-graph-update.json b/skills/memory-graph-update.json index b6e1da2..1e009fb 100644 --- a/skills/memory-graph-update.json +++ b/skills/memory-graph-update.json @@ -1,13 +1,9 @@ { "name": "memory-graph-update", - "description": "", - "tags": [ - "system", - "memory", - "graph" - ], - "category": "system", + "description": "Manual process for updating the memory graph since direct commands may be restricted.", + "tags": [], + "category": "general", "created": "2026-06-21T14:19:29.741Z", - "updated": "2026-06-21T14:19:29.741Z", + "updated": "2026-06-24T21:58:03.530Z", "content": "---\nname: memory-graph-update\ndescription: Manual process for updating the memory graph since direct commands may be restricted.\n---\n# Memory Graph Update Process\nWhen updating the memory graph, use the `memgraph` utility or the dedicated memory-graph module methods if available. If command-line access is blocked, use the AI context to summarize state changes." }
\ No newline at end of file diff --git a/skills/mindmap-user-guide.json b/skills/mindmap-user-guide.json index 8c15f3c..0651028 100644 --- a/skills/mindmap-user-guide.json +++ b/skills/mindmap-user-guide.json @@ -8,7 +8,7 @@ "planning" ], "category": "productivity", - "created": "2026-06-22T19:02:49.950Z", - "updated": "2026-06-22T19:02:49.950Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: mindmap-user-guide\ndescription: How to create, view, and manage brainstorming mindmaps using the mindmap terminal module\ntags: [mindmap, brainstorming, organization, planning]\ncategory: productivity\n---\n## Steps\n1. **Create a new mindmap:**\n - mindmap new \"<topic>\" -t tag1,tag2 β creates a root node\n - Tags are optional (e.g. planning, research, dev)\n - Root gets auto-assigned a color\n\n2. **Add child nodes:**\n - mindmap add <parent-id> \"<idea>\" -t tag β add a child\n - Get the parent-id from mindmap show\n - IDs are 4-char random strings (e.g. a3f8, x7k2)\n\n3. **View the mindmap:**\n - mindmap show β full tree with Unicode box-drawing\n - mindmap show <id> β subtree starting at that node\n\n4. **Edit nodes:**\n - mindmap rename <id> \"<new text>\" β change text\n - mindmap color <id> <color> β set color (red/green/yellow/blue/cyan/magenta/white)\n - mindmap tag <id> <tag> β add a tag\n\n5. **Persistence:**\n - mindmap save <name> β save to localStorage\n - mindmap load <name> β restore\n - mindmap list β show saved mindmaps\n - mindmap delete <name> β remove saved\n\n6. **Export:**\n - mindmap export [id] β Markdown bullet list output\n\n## When to use\n- User wants to brainstorm, organize ideas, plan features\n- User says \"map out\", \"diagram\", \"brainstorm\", \"organize thoughts\"\n- Visualizing project structure or task decomposition" }
\ No newline at end of file diff --git a/skills/mindmap-workflow.json b/skills/mindmap-workflow.json index b9c4690..a7fc877 100644 --- a/skills/mindmap-workflow.json +++ b/skills/mindmap-workflow.json @@ -8,7 +8,7 @@ "organization" ], "category": "productivity", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: mindmap-workflow\ndescription: How to create, view, edit, and manage brainstorming mindmaps\ntags: [mindmap, brainstorming, planning, organization]\ncategory: productivity\n---\n## Steps\n1. **Create a new mindmap:**\n - mindmap new \"<topic>\" -t tag1,tag2 β creates a root node\n - Tags are optional (e.g. planning, research, dev)\n - Root gets auto-assigned a color from 7-color palette\n\n2. **Add child nodes:**\n - mindmap add <parent-id> \"<idea>\" -t tag β add a child\n - Get the parent-id from mindmap show\n - IDs are 4-char random strings (e.g. a3f8, x7k2)\n\n3. **View:**\n - mindmap show β full tree with Unicode box-drawing\n - mindmap show <id> β subtree starting at that node\n\n4. **Edit nodes:**\n - mindmap rename <id> \"<new text>\" β change text\n - mindmap color <id> <color> β set color (red/green/yellow/blue/cyan/magenta/white)\n - mindmap tag <id> <tag> β add a tag\n\n5. **Persistence:**\n - mindmap save <name> β save to localStorage\n - mindmap load <name> β restore\n - mindmap list β show saved mindmaps\n - mindmap delete <name> β remove saved\n\n6. **Export:**\n - mindmap export [id] β Markdown bullet list output, auto-copies to clipboard\n\n7. **When to use:**\n - Map out project structure, brainstorm features, organize ideas\n - Break down complex tasks into subtrees\n - User says \"brainstorm\", \"diagram\", \"organize thoughts\", \"plan\"" }
\ No newline at end of file diff --git a/skills/mobile-html-system-analyzer.json b/skills/mobile-html-system-analyzer.json new file mode 100644 index 0000000..9c1d120 --- /dev/null +++ b/skills/mobile-html-system-analyzer.json @@ -0,0 +1,15 @@ +{ + "name": "mobile-html-system-analyzer", + "description": "Specialized role for analyzing and documenting systems specifically for mobile-optimized HTML/CSS interfaces (Dark Theme/Black Mode).", + "tags": [ + "mobile-web", + "html-css", + "system-analysis", + "dark-mode", + "ux-audit" + ], + "category": "general", + "created": "2026-06-23T13:05:19.465Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: mobile-html-system-analyzer\ndescription: Specialized role for analyzing and documenting systems specifically for mobile-optimized HTML/CSS interfaces (Dark Theme/Black Mode).\ntags: [mobile-web, html-css, system-analysis, dark-mode, ux-audit]\n---\n\n# Mobile HTML System Analyzer Role\n\n## π― Objective\nAnalyze, document, and optimize system interfaces specifically for mobile-web environments, ensuring high performance, accessibility, and a \"Black Mobile\" (high-contrast dark) aesthetic.\n\n## π Core Competencies\n\n### 1. Mobile-First Analysis\n- **Viewport Optimization**: Analyze how system layouts adapt to various mobile screen sizes (Responsive Design).\n- **Touch Target Audit**: Verify that interactive elements (buttons, links) meet the minimum size requirements for touch interfaces (typically 44x44px).\n- **Performance Profiling**: Assess page load times and interaction latency on mobile network simulations.\n\n### 2. \"Black Mobile\" Aesthetic (Dark Mode)\n- **Contrast Verification**: Ensure text-to-background contrast ratios meet WCAG AA/AAA standards for dark themes.\n- **Color Palette Management**: Implement deep blacks (`#000000`) and dark greys to minimize OLED battery drain and reduce eye strain.\n- **Visual Hierarchy**: Use subtle accents and borders to define structure without breaking the dark aesthetic.\n\n### 3. System Documentation\n- **DOM Mapping**: Document the HTML structure and component hierarchy.\n- **CSS Variable Audit**: Map all theme-related CSS variables (e.g., `--bg-primary`, `--text-main`).\n- **Interaction Flow**: Diagram the user journey from a mobile perspective.\n\n## π Operational Workflow\n\n### Phase 1: Discovery & Extraction\n- Fetch HTML/CSS source code.\n- Inspect the DOM for mobile-specific meta tags (e.g., `viewport`).\n- List all active CSS classes and styles applied to the \"black\" theme.\n\n### Phase 2: Analysis & Audit\n- Compare the current implementation against \"Mobile-First\" best practices.\n- Identify \"light leaks\" (areas where the dark theme is inconsistent).\n- Test responsiveness across simulated breakpoints.\n\n### Phase 3: Documentation & Reporting\n- Generate a **System Map** of the mobile UI.\n- Provide a **Contrast Report** for the dark theme.\n- Suggest specific CSS/HTML optimizations for mobile performance.\n\n## π Prompting Guide for this Role\nWhen activating this role, use the following triggers:\n- *\"Analyze this system for mobile-web compatibility.\"*\n- *\"Perform a dark-mode audit on the current HTML/CSS.\"*\n- *\"Document the mobile interaction flow for [Feature X].\"*\n- *\"Optimize the CSS for an OLED 'True Black' mobile experience.\"*\n" +}
\ No newline at end of file diff --git a/skills/module-audit-and-test.json b/skills/module-audit-and-test.json index 5dfddcc..3f3ede9 100644 --- a/skills/module-audit-and-test.json +++ b/skills/module-audit-and-test.json @@ -1,9 +1,14 @@ { "name": "module-audit-and-test", - "description": "", - "tags": [], + "description": "module-audit-and-test", + "tags": [ + "regression", + "testing", + "quality-assurance", + "modules" + ], "category": "dev", "created": "2026-06-18T00:41:25.711Z", - "updated": "2026-06-18T00:41:25.711Z", - "content": "---\nname: module-audit-and-test\ndescription: Procedural guide for auditing module source code and performing rigorous testing to ensure stability, security, and performance.\ntags: [modules, audit, testing, quality-assurance, dev]\n---\n\n# Module Audit & Testing Workflow\n\nThis skill provides a standardized approach to auditing existing modules and testing new or modified code within the WebX11 ecosystem.\n\n## 1. Audit Phase (Static Analysis)\nBefore running code, perform a static review of the module source.\n\n### Steps to Audit:\n1. **Retrieve Source**: Use `view_module(name=\"ModuleName\")` to examine the code.\n2. **Security Check**: \n - Look for unsafe command executions or uncontrolled input handling.\n - Ensure destructive operations (e.g., `write_file`, `delete_file`) have appropriate guards or confirmations.\n3. **Logic Review**:\n - Check for edge cases in parameters.\n - Verify that the module handles errors gracefully (try-catch blocks).\n - Ensure the module adheres to the expected return formats (JSON, strings, etc.).\n4. **Dependency Check**: Verify that all required helper functions or external APIs are correctly called and exist.\n\n## 2. Testing Phase (Dynamic Analysis)\nOnce the audit is complete, validate the module's behavior in a sandbox environment.\n\n### Testing Strategy:\n- **Happy Path**: Test the most common use case with valid inputs.\n- **Boundary Testing**: Test with empty strings, extremely large inputs, or null values.\n- **Error Path**: Intentionally provide invalid inputs to see if the module returns a helpful error instead of crashing.\n- **Integration Testing**: If the module interacts with other system components (VFS, Web, etc.), verify the end-to-end flow.\n\n### Execution Loop:\n1. **Edit/Modify**: Use `edit_module(name=\"ModuleName\")` to apply fixes.\n2. **Isolated Test**: Use `test_module(name=\"ModuleName\")`. This runs the module in a temporary context without affecting the global state.\n3. **Live Reload**: If tests pass, use `reload_module(name=\"ModuleName\")` to push the changes to the active system.\n\n## 3. Validation Checklist\n- [ ] Does the module perform its intended function?\n- [ ] Does it handle errors without crashing the terminal?\n- [ ] Are there any obvious security vulnerabilities?\n- [ ] Is the code clean and maintainable?\n- [ ] Does it perform efficiently without causing system lag?\n\n## Summary of Commands\n| Action | Command |\n| :--- | :--- |\n| View Source | `view_module(name=\"...\")` |\n| Modify Code | `edit_module(name=\"...\")` |\n| Test Sandbox | `test_module(name=\"...\")` |\n| Deploy | `reload_module(name=\"...\")` |\n| Check Status | `get_module_status()` |\n" + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: module-audit-and-test\ncategory: dev\ntags: [regression, testing, quality-assurance, modules]\n---\n\n# Module Regression & Testing Framework\n\nThis skill provides a formal methodology for ensuring that module modifications do not introduce regressions and that new features meet quality standards.\n\n## 1. Testing Levels\n- **Unit Test**: Isolating a single function within a module using `test_module`.\n- **Integration Test**: Testing the module's interaction with other modules or the VFS.\n- **Regression Test**: Running a set of known \"golden\" inputs and comparing outputs to ensure previous fixes remain active.\n\n## 2. The Regression Workflow\nWhen modifying a module, follow this cycle:\n\n### Phase A: Baselining (Pre-Edit)\n1. **Capture Current State**: Run the module with 3-5 standard inputs and save the output to a file in `/tests/baselines/[module_name]/`.\n2. **Identify Edge Cases**: Document at least one \"failure mode\" (e.g., empty input, oversized payload) that the module currently handles correctly.\n\n### Phase B: Controlled Modification\n1. **Edit**: Use `edit_module` to implement the change.\n2. **Verify**: Use `test_module` to confirm the specific fix/feature works in isolation.\n\n### Phase C: Regression Run (Post-Edit)\n1. **Compare**: Re-run the baseline inputs.\n2. **Diff Analysis**: Compare current output vs. baseline. Any unexpected change is a regression.\n3. **Edge Case Check**: Re-verify the previously identified failure modes.\n\n## 3. VFS Test Registry Structure\nMaintain tests in the following hierarchy:\n- `/tests/baselines/` $\\to$ Expected outputs for stable versions.\n- `/tests/suites/` $\\to$ Scripts or lists of inputs to be run sequentially.\n- `/tests/logs/` $\\to$ Execution history of test runs.\n\n## 4. Failure Protocol\nIf a regression is found:\n1. **Revert**: Use `reload_module` to return to the original state.\n2. **Analyze**: Use `debug-deep-dive` to find the conflict between the new logic and the baseline.\n3. **Refine**: Rewrite the logic to accommodate both the new feature and the baseline requirement.\n" }
\ No newline at end of file diff --git a/skills/module-management.json b/skills/module-management.json index 0b06845..9a7bfc7 100644 --- a/skills/module-management.json +++ b/skills/module-management.json @@ -8,7 +8,7 @@ "self-improvement" ], "category": "dev", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.403Z", + "updated": "2026-07-06T00:13:29.403Z", "content": "---\nname: module-management\ndescription: How to view, edit, test, reload modules and manage startup configuration\ntags: [modules, editing, code, self-improvement]\ncategory: dev\n---\n## Steps\n1. **View module source:**\n - view_module(name) β fetches original source or reads from _mods/ if edited\n - Supports all loaded modules: SystemModule, FileSystemModule, SearXNGModule, etc.\n - Or use modules command for GUI module manager\n\n2. **Edit a module:**\n - edit_module(name) β copies source to _mods/<name>.js and opens code editor\n - Editor shows the full source in a textarea\n - Click \"Save & Test\" to save and auto-load the edited version\n - Checkpoint before editing: checkpoint mod-edit-<name>\n\n3. **Test and reload:**\n - test_module(name) β loads edited module from _mods/ for live testing\n - reload_module(name) β discards edits and reloads from original URL\n - list_modified_modules β shows all modules with pending edits\n\n4. **Check for updates:**\n - check_updates β HEAD-requests all loaded module URLs to verify reachability\n\n5. **Manage startup:**\n - startup-modules β opens the Startup Modules UI to select which modules load\n - load-local <path> β load a module from VFS or URL without editing\n - loadmod <url> β alternative: load module from URL\n - removemod <name> β remove a loaded module\n\n6. **Agent modules (Phase 2):**\n - module-agent-registry.js β Agent registry with agent-list, agent-register, agent-unregister, agent-status\n - module-leases.js β Time-bound contracts with 5s watchdog, auto-expiry\n - module-orchestrator.js β Spawn, delegate, kill, purge with heartbeat monitoring\n\n7. **When to use:**\n - User reports a bug in a module β view_module, edit_module, test_module\n - User asks \"can you add X feature?\" β same workflow\n - Always save edits before testing. If test fails, the original module stays loaded." }
\ No newline at end of file diff --git a/skills/navigating-the-terminal.json b/skills/navigating-the-terminal.json index c5e2e1e..9ebb26c 100644 --- a/skills/navigating-the-terminal.json +++ b/skills/navigating-the-terminal.json @@ -8,7 +8,7 @@ "filesystem" ], "category": "system", - "created": "2026-06-22T19:02:49.948Z", - "updated": "2026-06-22T19:02:49.948Z", + "created": "2026-07-06T00:13:29.403Z", + "updated": "2026-07-06T00:13:29.403Z", "content": "---\nname: navigating-the-terminal\ndescription: How to explore the WebX11 terminal, find commands, check status, and navigate the filesystem\ntags: [terminal, navigation, help, filesystem]\ncategory: system\n---\n## Steps\n1. **Get an overview of available commands:**\n - Type \"help\" for a full command list sorted by category\n - Type \"status\" to see filesystem state, loaded modules, Ollama status\n - For a specific command, use help <command>\n - Type \"commands\" for a compact list with module source info\n - Type \"check\" for system health including module requirements\n\n2. **Explore the filesystem:**\n - Use ls, ll, tree to browse directories\n - Use cd <dir> to navigate, pwd to show current path\n - Use cat or edit to view file contents\n - Use find or grep to search files\n - Use du to see disk usage\n\n3. **Understand system state:**\n - mem β memory usage (auto-shown in header on boot)\n - status β network, files, modules, Ollama\n - modules β module manager GUI\n - health-check β VFS size, modules, logs, trash, skills, tool failures\n - checkpoint-list β VFS checkpoint snapshots\n\n4. **Agent / Orchestration state:**\n - agent-list β registered agents (type, capabilities, status)\n - orchestrate β list active orchestrated agents\n - lease-list β show active leases with TTL\n\n5. **When user asks a vague question:**\n - First run status and help to understand the current state\n - Then ask clarifying questions based on what you found" }
\ No newline at end of file diff --git a/skills/navigating-the-terminal.md b/skills/navigating-the-terminal.md index 8e822be..0d9a152 100644 --- a/skills/navigating-the-terminal.md +++ b/skills/navigating-the-terminal.md @@ -6,22 +6,31 @@ category: system --- ## Steps 1. **Get an overview of available commands:** - - Call get_help() to get a full command list sorted by category - - Call get_status() to see filesystem state, loaded modules, Ollama status - - For a specific command, use help <command> or check the help map + - Type "help" for a full command list sorted by category + - Type "status" to see filesystem state, loaded modules, Ollama status + - For a specific command, use help <command> + - Type "commands" for a compact list with module source info + - Type "check" for system health including module requirements 2. **Explore the filesystem:** - - Use list_files(path?) to browse directories (omit path for current dir) - - Use read_file(path) to view file contents - - Use get_current_dir to see your working directory - - Use run_command("ls") or run_command("tree") for visual output + - Use ls, ll, tree to browse directories + - Use cd <dir> to navigate, pwd to show current path + - Use cat or edit to view file contents + - Use find or grep to search files + - Use du to see disk usage 3. **Understand system state:** - - run_command("mem") β memory usage - - run_command("status") β network, files, modules, Ollama - - run_command("modules") β module manager GUI - - get_module_status() β loaded modules, URLs, local edits + - mem β memory usage (auto-shown in header on boot) + - status β network, files, modules, Ollama + - modules β module manager GUI + - health-check β VFS size, modules, logs, trash, skills, tool failures + - checkpoint-list β VFS checkpoint snapshots -4. **When user asks a vague question:** - - First call get_status() and get_help() to understand the current state - - Then ask clarifying questions based on what you found
\ No newline at end of file +4. **Agent / Orchestration state:** + - agent-list β registered agents (type, capabilities, status) + - orchestrate β list active orchestrated agents + - lease-list β show active leases with TTL + +5. **When user asks a vague question:** + - First run status and help to understand the current state + - Then ask clarifying questions based on what you found diff --git a/skills/performance-regression-protocol.json b/skills/performance-regression-protocol.json new file mode 100644 index 0000000..aec73c3 --- /dev/null +++ b/skills/performance-regression-protocol.json @@ -0,0 +1,15 @@ +{ + "name": "performance-regression-protocol", + "description": "Systematic procedure for detecting, measuring, and resolving performance regressions across WebX11 modules and AI workflows", + "tags": [ + "\"performance\"", + "\"regression\"", + "\"benchmark\"", + "\"optimization\"", + "\"metrics\"" + ], + "category": "dev", + "created": "2026-06-25T00:24:42.730Z", + "updated": "2026-07-03T15:14:32.850Z", + "content": "---\ndescription: Systematic procedure for detecting, measuring, and resolving performance regressions across WebX11 modules and AI workflows\ncategory: dev\ntags: [\"performance\",\"regression\",\"benchmark\",\"optimization\",\"metrics\"]\nupdated: \"2026-07-03T16:45:00.000Z\"\n---\n\n# Performance Regression Protocol\n\nA data-driven approach to maintaining system performance over time.\n\n## Detection Triggers\n\n- User reports slower responses\n- `get_usage_stats` shows increased latency\n- `get_status` reports memory pressure\n- Module test suite takes >110% of baseline duration\n\n## Measurement Baseline\n\nRecord these metrics before any optimization:\n- Average token latency (per model)\n- Module load time\n- NVFS index build duration\n- Dashboard render time\n- Agent spawn/heartbeat latency\n\n## Regression Checklist\n\n1. **Isolate** β Use `list_modified_modules` to find recent changes\n2. **Benchmark** β Run A/B test with previous version\n3. **Profile** β Check `get_usage_stats(model, since_hours=24)`\n4. **Fix** β Revert or optimize the offending change\n5. **Verify** β Confirm metrics return to baseline\n6. **Document** β Record in `/skills/` and update baseline\n\n## Prevention\n\n- Set performance budgets in module manifests\n- Run regression tests before merging changes\n- Monitor `get_usage_stats` weekly via cron\n- Archive performance baselines in `/archive/baselines/`" +}
\ No newline at end of file diff --git a/skills/role-archetype-framework.json b/skills/role-archetype-framework.json index a721139..0d2355f 100644 --- a/skills/role-archetype-framework.json +++ b/skills/role-archetype-framework.json @@ -1,13 +1,9 @@ { "name": "role-archetype-framework", - "description": "", - "tags": [ - "agents", - "system", - "orchestration" - ], - "category": "system", + "description": "Documentation and operational guidelines for the Specialized Archetype Framework (Architect, Operator, Auditor, Synthesizer).", + "tags": [], + "category": "general", "created": "2026-06-22T08:29:46.161Z", - "updated": "2026-06-22T08:29:46.161Z", + "updated": "2026-06-24T21:58:03.530Z", "content": "---\nname: role-archetype-framework\ndescription: Documentation and operational guidelines for the Specialized Archetype Framework (Architect, Operator, Auditor, Synthesizer).\ntags: agents, system-design, orchestration\n---\n\n# Specialized Archetype Framework\n\n## Overview\nThe system has transitioned from generic \"developer\" agents to a specialized persona-based framework. This optimizes task delegation by aligning specific capabilities with distinct roles.\n\n## The Archetypes\n\n### ποΈ Architect\n- **Focus:** High-level design, VFS planning, and strategic structuring.\n- **Ideal Tasks:** Mapping project architectures, designing folder hierarchies, and conceptualizing logic flows.\n- **Primary Tools:** `create_mindmap`, `list_files`, `make_directory`.\n\n### βοΈ Operator\n- **Focus:** Execution, tool orchestration, and external interaction.\n- **Ideal Tasks:** Web scraping, executing terminal commands, installing WPM packages, and API interactions.\n- **Primary Tools:** `run_command`, `web_fetch`, `wpm_install`.\n\n### π‘οΈ Auditor\n- **Focus:** Quality Assurance, Security, and Critical Analysis.\n- **Ideal Tasks:** Code reviews, system health audits, identifying vulnerabilities, and verifying logic correctness.\n- **Primary Tools:** `run_command` (read-only), `read_file`, `get_status`.\n\n### βοΈ Synthesizer\n- **Focus:** Knowledge Management, Documentation, and Reporting.\n- **Ideal Tasks:** Converting session logs into skills, summarizing complex data, and updating user profiles.\n- **Primary Tools:** `create_skill`, `write_file`, `user_set`.\n\n## Workflow Integration\nWhen delegating tasks, use the following logic:\n1. **Plan** with the `architect`.\n2. **Execute** with the `operator`.\n3. **Verify** with the `auditor`.\n4. **Document** with the `synthesizer`.\n" }
\ No newline at end of file diff --git a/skills/role-research-analyst.json b/skills/role-research-analyst.json new file mode 100644 index 0000000..e3bde2f --- /dev/null +++ b/skills/role-research-analyst.json @@ -0,0 +1,15 @@ +{ + "name": "role-research-analyst", + "description": "Blueprint for a Research Analyst that gathers, evaluates, and synthesizes external information for WebX11 tasks.", + "tags": [ + "roles", + "agents", + "research", + "web", + "analysis" + ], + "category": "system", + "created": "2026-06-24T21:57:32.323Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: role-research-analyst\ndescription: Blueprint for a Research Analyst that gathers, evaluates, and synthesizes external information for WebX11 tasks.\ncategory: system\ntags: [roles, agents, research, web, analysis]\n---\n\n# π Role: Research Analyst\n\n## Focus\nGather, evaluate, and synthesize external information from the web and local knowledge sources to support decisions and implementations.\n\n## Ideal Tasks\n- Research APIs, libraries, and best practices.\n- Investigate error messages, CVEs, or framework changes.\n- Compare tools or approaches for a given problem.\n- Collect references and authoritative sources.\n- Summarize findings into actionable recommendations.\n\n## Primary Tools\n- `web_search`, `web_fetch`\n- `read_file`, `list_files`, `nvfs_resolve`\n- `create_skill`, `write_file`\n- `vaultmind_query` (market/AI chat) when relevant\n\n## Behavioral Rules\n- Prefer primary sources (official docs, repos, specs) over secondhand summaries.\n- Cross-check claims with at least two sources when accuracy matters.\n- Cite URLs and capture the date retrieved.\n- Distinguish fact from opinion; note uncertainty levels.\n- Keep raw notes separate from final synthesis.\n\n## Delegation Phrase\n> βResearch this topic / error / alternative.β\n\n## Hand-off\nPass concise summary and citations to the **Synthesizer** or **Architect**." +}
\ No newline at end of file diff --git a/skills/role-security-auditor.json b/skills/role-security-auditor.json new file mode 100644 index 0000000..c93f3af --- /dev/null +++ b/skills/role-security-auditor.json @@ -0,0 +1,15 @@ +{ + "name": "role-security-auditor", + "description": "Blueprint for a Security Auditor focused on code review, configuration safety, and vulnerability analysis in WebX11.", + "tags": [ + "roles", + "agents", + "security", + "audit", + "safety" + ], + "category": "system", + "created": "2026-06-24T21:57:32.314Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: role-security-auditor\ndescription: Blueprint for a Security Auditor focused on code review, configuration safety, and vulnerability analysis in WebX11.\ncategory: system\ntags: [roles, agents, security, audit, safety]\n---\n\n# π‘οΈ Role: Security Auditor\n\n## Focus\nIdentify vulnerabilities, misconfigurations, and unsafe patterns across code, modules, skills, secrets, and user workflows.\n\n## Ideal Tasks\n- Review module source for injection, escalation, or leakage risks.\n- Audit `secret-vault` usage and secret handling.\n- Inspect file permissions, `run_command` usage, and `write_file` safety.\n- Validate input sanitization in web-facing commands.\n- Assess agent capability grants and lease boundaries.\n\n## Primary Tools\n- `view_module`, `read_file`, `list_files`\n- `get_status`, `check_updates`\n- `run_command` (read-only / safe commands only)\n- `list_agents`, `list_modified_modules`\n\n## Behavioral Rules\n- Never execute potentially destructive commands to βproveβ a vulnerability; inspect statically.\n- Flag unsafe patterns such as unsanitized `eval`, raw HTML insertion, missing command confirmation, or over-broad agent capabilities.\n- Verify that destructive tools (`write_file`, `delete_file`, `run_command`, `edit_module`) are gated by confirmation.\n- Check that secrets are not logged or returned in AI outputs.\n- Produce concrete, prioritized findings with remediation steps.\n\n## Delegation Phrase\n> βAudit this for security / safety issues.β\n\n## Hand-off\nShare findings with the **Synthesizer** to convert into a skill or runbook." +}
\ No newline at end of file diff --git a/skills/security-and-safety.json b/skills/security-and-safety.json index ff0c195..3c8ddc4 100644 --- a/skills/security-and-safety.json +++ b/skills/security-and-safety.json @@ -8,7 +8,7 @@ "permissions" ], "category": "system", - "created": "2026-06-22T19:02:49.950Z", - "updated": "2026-06-22T19:02:49.950Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: security-and-safety\ndescription: How to use WebX11 security levels, command blocking, and safety features\ntags: [security, safety, blocking, permissions]\ncategory: system\n---\n## Steps\n1. **Security levels:**\n - security-level <0-3> β set security level:\n 0 = Permissive (no blocks, no confirms β anything runs)\n 1 = Standard (unknown cmds β AI route, destructive β confirm, system β block)\n 2 = Paranoid (unknown cmds blocked entirely, destructive blocked)\n 3 = Audit (everything allowed, everything logged)\n - Default: level 1\n - security β show current level, blocked count, and stats\n\n2. **Command control:**\n - cmd-allow <cmd> β whitelist a command from security checks\n - cmd-deny <cmd> β blacklist/block a command entirely\n - whitelist built-in: help, clear, ls, cat, pwd, whoami, df, free, top, ps, echo, date, env, history\n\n3. **What gets blocked at each level:**\n - Unknown commands: Level 1 β AI routed, Level 2+ β blocked\n - Destructive commands (delete, write, save, format, etc.): Level 1 β confirmation, Level 2+ β blocked\n - System commands (reboot, shutdown, format, kill): Level 1+ β blocked\n - Suspicious flags (--execute, --eval, --shell): Level 1+ β blocked\n\n4. **Safety checklist:**\n - Check security: security shows your current level\n - Before running risky commands: create a checkpoint first\n - For temporary relax: security-level 0, then restore to 1\n - For total lockdown before leaving: security-level 2\n\n5. **When to use:**\n - User wants to lock down the terminal β security-level 2\n - User wants to allow a blocked command β cmd-allow <cmd>\n - Debugging strange behavior β verify security-level (user may have set it higher)" }
\ No newline at end of file diff --git a/skills/semantic-dependency-audit.json b/skills/semantic-dependency-audit.json new file mode 100644 index 0000000..83c1f8f --- /dev/null +++ b/skills/semantic-dependency-audit.json @@ -0,0 +1,15 @@ +{ + "name": "semantic-dependency-audit", + "description": "How to audit semantic dependencies across VFS, modules, skills, and agents using the Neural VFS index to detect architectural fragility", + "tags": [ + "\"nvfs\"", + "\"audit\"", + "\"architecture\"", + "\"dependencies\"", + "\"semantic-index\"" + ], + "category": "dev", + "created": "2026-06-25T00:24:42.740Z", + "updated": "2026-07-03T15:14:32.867Z", + "content": "---\ndescription: How to audit semantic dependencies across VFS, modules, skills, and agents using the Neural VFS index to detect architectural fragility\ncategory: dev\ntags: [\"nvfs\",\"audit\",\"architecture\",\"dependencies\",\"semantic-index\"]\nupdated: \"2026-07-03T16:45:00.000Z\"\n---\n\n# Semantic Dependency Audit\n\nMap and verify semantic links across the WebX11 system to prevent silent failures.\n\n## Audit Scope\n\n- **VFS β Skills** β Are skills referenced by files still valid?\n- **Skills β Modules** β Do skills reference existing module commands?\n- **Agents β Capabilities** β Are agent capabilities backed by loaded modules?\n- **Modules β URLs** β Are module sources reachable? (`check_updates`)\n\n## Commands\n\n```\n# Build semantic index (run monthly or after major changes)\nnvfs_resolve --reindex\n\n# Query dependencies\nnvfs_resolve \"skill dependencies\"\nnvfs_resolve \"module integrity\"\nnvfs_resolve \"agent capabilities\"\n```\n\n## Fragility Indicators\n\n- Orphan skills (not referenced by any file)\n- Dead module URLs (404 or timeout)\n- Agents with capabilities for unloaded modules\n- Circular dependency chains in `/agents/` scripts\n\n## Remediation\n\n1. **Orphans** β Move to `/.trash/` or document as intentional\n2. **Dead URLs** β Reload from alternate source or deprecate\n3. **Capability gaps** β Grant agent missing capabilities or remove task\n4. **Circular deps** β Refactor into shared utility module" +}
\ No newline at end of file diff --git a/skills/skills-system-guide.json b/skills/skills-system-guide.json index 3592229..8f04c77 100644 --- a/skills/skills-system-guide.json +++ b/skills/skills-system-guide.json @@ -7,7 +7,7 @@ "meta" ], "category": "system", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: skills-system-guide\ndescription: How to use the skills system: load, create, patch, list, and audit skills for persistent procedural memory\ntags: [skills, system, meta]\ncategory: system\n---\n## Steps\n1. **Always load skills at task start:**\n - At the START of every task, type or call \"skill-view <name>\" or \"skill-list\"\n - Example: skill-view \"module-management\" β returns matching skill content\n - Example: skill-list system β browse skills by category\n\n2. **Create skills after complex tasks:**\n - After any task with 3+ tool calls, call \"skill-create\"\n - Required fields: name (kebab-case), description, content (markdown with YAML frontmatter)\n - Optional: tags (comma-separated), category (e.g. research, system, dev)\n - Skills persist in /skills/ as .md files with /skills/index.json for fast lookup\n - Skill pack auto-seeds 8 core skills on first boot\n\n3. **Patch skills when they're outdated:**\n - If a stored procedure has wrong steps, call \"skill-patch <name>\"\n - This replaces the entire skill content and updates the index\n - Do NOT create a duplicate β always patch the existing skill\n\n4. **Auto-created error skills:**\n - If the same tool fails 3+ times, a workaround skill is created automatically\n - Named tool-<name>-workaround (e.g. tool-write_file-workaround)\n\n5. **Audit and maintenance:**\n - skill-list <category?> β browse available skills, optionally filter\n - skill-export <name> β download a skill as markdown\n - skill-import <json> β bulk import skills\n - skill-sync β re-index skills from /skills/ directory\n - Skills are audited every 20 messages for staleness (empty content, >30 days old)\n\n6. **YAML frontmatter format:**\n - Each skill file must start with: ---\\nname: <name>\\ndescription: <text>\\ntags: [...]\\ncategory: <cat>\\n---\\n\n - Steps follow under ## Steps heading\n - Use numbered lists for sequential steps" }
\ No newline at end of file diff --git a/skills/smart-context-management.json b/skills/smart-context-management.json new file mode 100644 index 0000000..fbd6440 --- /dev/null +++ b/skills/smart-context-management.json @@ -0,0 +1,14 @@ +{ + "name": "smart-context-management", + "description": "Guide for managing and utilizing AI context profiles via the SmartContextModule to optimize behavior for specific tasks.", + "tags": [ + "system", + "context", + "optimization", + "workflow" + ], + "category": "general", + "created": "2026-06-23T11:29:23.335Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: smart-context-management\ndescription: Guide for managing and utilizing AI context profiles via the SmartContextModule to optimize behavior for specific tasks.\ntags: [system, context, optimization, workflow]\n---\n\n# Smart Context Management\n\nThe `SmartContextModule` allows the AI to switch between pre-defined behavior profiles (temperature, style, and system prompts) to match the task at hand.\n\n## π Available Standard Profiles\n- `chat`: General purpose, balanced, conversational.\n- `coding`: Focused on syntax, logic, and efficiency.\n- `debug`: Analytical, forensic, focused on root-cause analysis.\n- `technical`: High-density information, precise, documentation-style.\n- `creative`: Higher temperature, imaginative, fluid.\n\n## π οΈ Custom Archetypes (Manual)\nBeyond the built-in profiles, the system can adopt \"Custom Archetypes\" through natural language instruction:\n- **Architect**: Focuses on system design, scalability, and modularity.\n- **Rapid-Prototype**: Prioritizes speed and execution over perfection.\n- **Chaos-Monkey**: Adversarial testing and stress-testing logic.\n- **Deep-Debug**: Extreme verbosity and assumption-checking.\n\n## π Workflow Integration\n1. **Analysis**: Identify the nature of the task (e.g., \"I need to build a new VFS layer\").\n2. **Selection**: Select the matching context (e.g., `architect`).\n3. **Activation**: Use `smart_context_set(name=\"profile_name\")` or natural language request.\n4. **Validation**: Verify the response style aligns with the profile objectives.\n5. **Reset**: Return to `chat` or `technical` once the specialized task is complete.\n\n## β οΈ Best Practices\n- Avoid staying in `debug` or `coding` for general conversation to prevent overly rigid responses.\n- Use `architect` before writing large amounts of code to ensure the structure is sound.\n- Combine `chaos-monkey` with `deep-debug` for comprehensive system hardening.\n" +}
\ No newline at end of file diff --git a/skills/suggestion-engine.json b/skills/suggestion-engine.json index e3a06f8..da4ffb4 100644 --- a/skills/suggestion-engine.json +++ b/skills/suggestion-engine.json @@ -1,9 +1,14 @@ { "name": "suggestion-engine", - "description": "", - "tags": [], - "category": "system", + "description": "A systematic process for recording, analyzing, and implementing user suggestions for system improvement.", + "tags": [ + "optimization", + "feedback", + "roadmap", + "dev" + ], + "category": "general", "created": "2026-06-18T01:22:19.666Z", - "updated": "2026-06-18T01:22:19.666Z", + "updated": "2026-06-24T21:58:03.530Z", "content": "---\nname: suggestion-engine\ndescription: A systematic process for recording, analyzing, and implementing user suggestions for system improvement.\ntags: [optimization, feedback, roadmap, dev]\n---\n\n# Suggestion Engine Workflow\n\nThis skill provides a structured framework to ensure user ideas are not lost and are implemented with architectural integrity.\n\n## π 1. Recording Process\nEvery suggestion must be logged into the `suggestion_log.json` with the following schema:\n- **ID**: Unique incremental ID.\n- **Timestamp**: ISO date.\n- **Category**: (UI/UX, Performance, Security, Feature, Logic).\n- **Description**: Detailed user request.\n- **Status**: `proposed` | `analyzing` | `implementing` | `completed` | `rejected`.\n- **Priority**: `low` | `medium` | `high` | `critical`.\n\n## βοΈ 2. Analysis Framework\nBefore implementing a suggestion, the AI must perform a \"Impact Analysis\":\n1. **Dependency Check**: Which modules are affected?\n2. **Security Audit**: Does this introduce a new attack vector?\n3. **Performance Cost**: Will this increase latency or memory bloat?\n4. **UI Consistency**: Does this align with the existing design language?\n\n## π 3. Implementation Cycle\n1. **Propose**: Define the technical approach.\n2. **Draft**: Modify the module code (using `edit_module`).\n3. **Test**: Run `test_module` to verify correctness.\n4. **Verify**: User confirmation of the improvement.\n5. **Archive**: Update status to `completed` and document the change.\n\n## π οΈ Commands Reference\n- `suggestion-log` -> List all current suggestions.\n- `suggestion-add [text]` -> Append new idea to log.\n- `suggestion-promote [id]` -> Move from proposed to analyzing.\n" }
\ No newline at end of file diff --git a/skills/system-audit.json b/skills/system-audit.json new file mode 100644 index 0000000..b07e5ff --- /dev/null +++ b/skills/system-audit.json @@ -0,0 +1,14 @@ +{ + "name": "system-audit", + "description": "Comprehensive procedure for analyzing VFS health, module dependencies, and system configuration state.", + "tags": [ + "audit", + "system", + "structure", + "verification" + ], + "category": "system", + "created": "2026-06-23T12:15:26.571Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: system-audit\ndescription: Comprehensive procedure for analyzing VFS health, module dependencies, and system configuration state.\ntags: [audit, system, structure, verification]\ncategory: system\n---\n## Steps\n1. **VFS Snapshot:**\n - Run `get_status` to check overall FS health, module load count, and memory usage.\n - Use `list_files` recursively on critical directories (`/`, `/_mods/`, `/_contexts/`, `/skills/`) to map the current landscape.\n\n2. **Module Verification:**\n - Execute `list_available_modules` to verify core vs extension distribution.\n - Use `get_module_status` to identify modified modules that may require synchronization or updates.\n - For critical path modules, use `view_module` to inspect logic for bottlenecks or security flaws.\n\n3. **Context & Skill Alignment:**\n - Check `/_contexts/` to ensure role manifests align with the actual skills available via `list_skills`.\n - Identify \"Skill Gaps\" (Roles requiring skills that do not yet exist in the `/skills/` directory).\n\n4. **Dependency Mapping:**\n - Use `nvfs_resolve` with concepts like \"security\", \"memory\", or \"network\" to see how semantic links are structured.\n - Cross-reference `session_recent` to ensure current architectural changes align with the project trajectory.\n\n5. **Reporting:**\n - Synthesize findings into a \"System State Report\" highlighting:\n - **Integrity:** (Are files where they should be?)\n - **Consistency:** (Do roles match skills?)\n - **Risks:** (Are there modified modules without tests?)\n" +}
\ No newline at end of file diff --git a/skills/system-maintenance.json b/skills/system-maintenance.json index 85f4709..a03bdb1 100644 --- a/skills/system-maintenance.json +++ b/skills/system-maintenance.json @@ -9,7 +9,7 @@ "config" ], "category": "system", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.403Z", + "updated": "2026-07-06T00:13:29.403Z", "content": "---\nname: system-maintenance\ndescription: How to reset, troubleshoot, and maintain the WebX11 terminal\ntags: [system, maintenance, reset, troubleshoot, config]\ncategory: system\n---\n## Steps\n1. **Factory reset (wipes everything):**\n - factory-reset --confirm β clears all webx11_ localStorage keys, resets VFS, reloads\n - Use only when the system is in an unrecoverable state\n\n2. **Soft VFS reset:**\n - reset-vfs --confirm β clears only the filesystem, preserves settings/profile/modules\n\n3. **Config management:**\n - config-list β show all config keys and values\n - config-set <key> <value> β set a config value\n - config-delete <key> β remove a config key\n - config-export β dump all config as JSON\n - config-reset β restore defaults (use before factory-reset if you want to save data)\n\n4. **Security level:**\n - security-level <0-3> β set security level (0=Permissive, 1=Standard, 2=Paranoid, 3=Audit)\n - security β show current security level, blocked count, and stats\n - cmd-allow <cmd> β whitelist a command from security checks\n - cmd-deny <cmd> β blacklist a command\n\n5. **Health checks (run automatically after complex tasks):**\n - Check module loading status: loaded vs total\n - Check for pending module edits\n - Check memory usage (high if >100MB)\n - Check skill count (0 skills after 2+ tool calls β suggest create_skill)\n - health-check β full audit: VFS size, modules, logs, trash, skills, tool failures\n\n6. **Font size and display:**\n - font-size <8-32> β set terminal font size, persists across sessions\n - setfont β alias for font-size\n\n7. **Checkpoints:**\n - checkpoint [name] β snapshot current VFS state\n - checkpoint-list β list all checkpoints\n - rollback <name> β restore from checkpoint\n\n8. **When to use:**\n - System is slow or modules fail to load β check check_updates, mem\n - User says \"reset everything\" β factory-reset --confirm\n - User says \"clear my files but keep settings\" β reset-vfs --confirm\n - User reports security concerns β security-level or cmd-allow/cmd-deny" }
\ No newline at end of file diff --git a/skills/vfs-optimizer.json b/skills/vfs-optimizer.json new file mode 100644 index 0000000..f7fe326 --- /dev/null +++ b/skills/vfs-optimizer.json @@ -0,0 +1,14 @@ +{ + "name": "vfs-optimizer", + "description": "Procedural guide for optimizing VFS structure, pruning redundant data, and maintaining NVFS index health.", + "tags": [ + "vfs", + "optimization", + "pruning", + "index" + ], + "category": "system", + "created": "2026-06-23T12:25:39.892Z", + "updated": "2026-06-24T21:58:03.530Z", + "content": "---\nname: vfs-optimizer\ndescription: Procedural guide for optimizing VFS structure, pruning redundant data, and maintaining NVFS index health.\ntags: [vfs, optimization, pruning, index]\ncategory: system\n---\n## Steps\n1. **Structural Audit:**\n - Run `list_files` recursively to identify deep nesting or redundant directory layers.\n - Check for \"orphaned\" files (files without corresponding manifests or role-links).\n\n2. **Redundancy Pruning:**\n - Identify duplicate logs or temporary files (`.tmp`, `.bak`, `old_...`).\n - Use `delete_file` to remove non-essential data that degrades semantic search precision.\n\n3. **NVFS Index Optimization:**\n - Run `nvfs-index` to refresh the semantic vector mapping of the current VFS state.\n - Verify retrieval quality using `nvfs-resolve` on core architectural concepts.\n\n4. **Hierarchy Alignment:**\n - Move files into categorized directories (e.g., `/_configs/`, `/_logs/`, `/_assets/`) to reduce root-level noise.\n - Ensure the `/_contexts/` and `/skills/` directories remain the primary anchors for identity and procedure.\n\n5. **Validation:**\n - Perform a final `get_status` to ensure system stability after structural changes.\n" +}
\ No newline at end of file diff --git a/skills/web-search-and-fetch.json b/skills/web-search-and-fetch.json index 8f2bc67..49c4dd5 100644 --- a/skills/web-search-and-fetch.json +++ b/skills/web-search-and-fetch.json @@ -9,7 +9,7 @@ "api" ], "category": "research", - "created": "2026-06-22T19:02:49.949Z", - "updated": "2026-06-22T19:02:49.949Z", + "created": "2026-07-06T00:13:29.403Z", + "updated": "2026-07-06T00:13:29.403Z", "content": "---\nname: web-search-and-fetch\ndescription: How to search the web and fetch URL content using the WebX11 proxy API\ntags: [search, fetch, web, proxy, api]\ncategory: research\n---\n## Steps\n1. **Search the web:**\n - Use search <query> or web_search(query) β uses /api/search which queries SearXNG + DDG fallback\n - Results include: title, url, content snippet, source engine\n - Always available (same-origin, no CORS issues)\n - 5-minute server-side cache for repeated queries\n - Alternative: use ddg or duck <query> for DuckDuckGo direct, or s <query> as alias\n\n2. **Fetch URL content:**\n - Use fetch <url> or web_fetch(url) β uses /api/extract which strips HTML, extracts clean text\n - Returns: title, content (up to 4000 chars), word_count, extraction method\n - SSRF protection blocks internal network addresses\n - 15-minute server-side cache\n\n3. **Search flags (via terminal search command):**\n - search <query> --summarize β adds AI-generated overview via Ollama\n - search <query> --fetch β fetches content snippets for top 3 results\n\n4. **When to use:**\n - User asks about current events, facts, research β use search <query>\n - User says \"read this article\" or provides a URL β use fetch <url>\n - For in-depth analysis: search first, then fetch top results" }
\ No newline at end of file diff --git a/skills/webdav-operations.json b/skills/webdav-operations.json index 16d066f..8fb9822 100644 --- a/skills/webdav-operations.json +++ b/skills/webdav-operations.json @@ -9,7 +9,7 @@ "storage" ], "category": "system", - "created": "2026-06-22T19:02:49.950Z", - "updated": "2026-06-22T19:02:49.950Z", + "created": "2026-07-06T00:13:29.404Z", + "updated": "2026-07-06T00:13:29.404Z", "content": "---\nname: webdav-operations\ndescription: How to use WebDAV cloud storage for backup, file sync, and remote file access\ntags: [webdav, cloud, backup, sync, storage]\ncategory: system\n---\n## Steps\n1. **Configuration:**\n - webdav-config β configure WebDAV endpoint URL and credentials\n - Connection auto-tested on config; webdav-status shows connection health\n - Uses per-user token stored in .token file on the server side\n\n2. **File operations:**\n - webdav-ls [path] β list remote directory contents\n - webdav-push <local-path> <remote-path> β upload file to WebDAV\n - webdav-pull <remote-path> [local-path] β download file from WebDAV\n - webdav-explorer β GUI file browser for WebDAV\n - webdav-browser β CLI file browser for WebDAV\n\n3. **Backup & Restore:**\n - webdav-backup β push full VFS snapshot to WebDAV (creates /backups/newos4-<date>.json)\n - webdav-backup-list β list all remote backup snapshots\n - webdav-restore <filename> β restore VFS from a remote backup snapshot\n\n4. **Status & Diagnostics:**\n - webdav-status β connection status, last sync, space information\n - If uploads fail: check webdav-config, ensure .token file is valid\n - WebDAV runs on the same server (nginx with WebDAV module), no external dependency\n\n5. **When to use:**\n - Before factory-reset: webdav-backup to store VFS remotely\n - Cross-browser: webdav-push/pull to move files between instances\n - User says \"cloud backup\" or \"remote save\" β webdav-backup" }
\ No newline at end of file |