.claude/skills/web-research/SKILL.md
Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.
npx skillsauth add gonzalezpazmonica/pm-workspace web-researchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3-layer search: cache → SearxNG (Docker auto-start) → Claude WebSearch. Inspired by FAIR-Perplexica.
[web:N] with source URLs in footer1. Python 3.x available → always true in pm-workspace
2. Docker (optional) for SearxNG → graceful fallback if missing
3. Internet connection (optional) → cache-only mode if offline
User query or gap detected
→ Sanitize (strip PII, projects, emails, IPs)
→ Check cache (TTL by category)
→ If miss: try SearxNG (auto-start Docker)
→ If SearxNG unavailable: use Claude WebSearch
→ Rerank results (keyword + domain authority)
→ Cache results
→ Format with [web:N] citations
→ Show follow-up suggestions
| Module | Lines | Purpose |
|--------|-------|---------|
| cache.py | 137 | LRU cache, TTL, stats |
| sanitizer.py | 107 | PII removal, classification |
| rerank.py | 86 | Heuristic scoring |
| formatter.py | 88 | Citation formatting |
| gap_detector.py | 110 | External vs internal detection |
| searxng.py | 149 | Docker auto-start, cross-platform |
| search.py | 88 | 3-layer orchestrator |
| suggestions.py | 81 | Post-command follow-ups |
docs/propuestas/SPEC-003-web-research-system.mddocs/rules/domain/web-research-config.mddocs/web-research.mddocs/web-research.en.mdtests/test-web-research.batstesting
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
tools
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
tools
Sistema proactivo de bienestar individual
testing
Transcripción de audio y flujo audio→texto→acción para mensajes de voz