gonzalezpazmonica/doc-quality-feedback
.claude/skills/doc-quality-feedback/SKILL.md
$ install --global
skillsauthnpx skillsauth add gonzalezpazmonica/pm-workspace doc-quality-feedbackInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:50 PM1.8s1 file scanned
SKILL.md
- name:
- doc-quality-feedback
- description:
- >
- summary:
- |
- maturity:
- experimental
- category:
- quality
- tags:
- ["feedback", "documentation", "self-improvement"]
- priority:
- medium
- disable-model-invocation:
- false
- user-invocable:
- true
- allowed-tools:
- [Read, Write, Glob, Grep, Bash]
Skill: Doc Quality Feedback
Inspirado en Context Hub: agent annotations que persisten entre sesiones. Loop auto-mejora: agentes usan doc → puntuan → aggregacion → reescritura.
Cuando usar
- Despues de que un agente usa una skill o regla (automatico via protocol)
- Mensualmente para auditar calidad de documentacion
- Cuando un skill produce outputs inconsistentes (posible doc confusa)
Como funciona
Rating por agentes
Cuando un agente usa un skill/regla y termina, puede emitir un rating:
{
"doc": ".claude/skills/codebase-map/SKILL.md",
"agent": "architect",
"rating": "clear",
"note": "Instructions were unambiguous",
"timestamp": "2026-03-19T02:00:00Z"
}
Ratings posibles:
- clear: instrucciones claras, output correcto al primer intento
- confusing: instrucciones ambiguas, requirio re-interpretacion
- incomplete: falta informacion para completar la tarea
- outdated: informacion desactualizada que causo error
- wrong: informacion incorrecta
Almacenamiento
public-docs-feedback/{doc-name-sanitized}.jsonl — una linea JSON por rating.
Ejemplo: public-docs-feedback/skills--codebase-map--SKILL.jsonl
Aggregacion
/docs-quality-audit lee todos los JSONL y produce:
- Score por doc: % ratings positivos (clear) vs negativos (confusing+incomplete+outdated+wrong)
- Docs con >30% ratings negativos → flagged para reescritura
- Tendencia: ¿mejoran o empeoran los docs con el tiempo?
- Top 5 docs mas usados (por numero de ratings)
- Top 5 docs peor puntuados (candidatos a
/skill-optimize)
Protocolo de emision
Los agentes NO estan obligados a emitir rating en cada ejecucion. El rating es voluntario y se emite cuando el agente detecta una de las condiciones:
- Tuvo que re-interpretar una instruccion ambigua → confusing
- No encontro informacion que necesitaba → incomplete
- Encontro informacion incorrecta → wrong/outdated
- Todo funciono sin friccion → clear (emitir 1 de cada 5 veces para no saturar)
Formato del JSONL
{"doc":"path","agent":"name","rating":"clear|confusing|incomplete|outdated|wrong","note":"...","ts":"ISO"}
Integracion
- skill-auto-activation: docs con rating bajo pierden prioridad de sugerencia
- skill-optimize: docs con rating bajo son candidatos prioritarios
- hub-audit: cruzar ratings con hub score para priorizar reescrituras
- session-init: si hay docs criticos (>50% negativo), alertar al PM
Related Skills
gonzalezpazmonica/skill-creator
testing
VerifiedTrustedCommunity
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.
40SKILL.mdUpdated May 24, 2026
gonzalezpazmonica/mcp-builder
tools
VerifiedTrustedCommunity
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).
40SKILL.mdUpdated May 24, 2026
gonzalezpazmonica/wellbeing-guardian
tools
VerifiedTrustedCommunity
Sistema proactivo de bienestar individual
33SKILL.mdUpdated Apr 17, 2026
gonzalezpazmonica/web-research
development
VerifiedTrustedCommunity
Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.
33SKILL.mdUpdated Apr 17, 2026