documentary-audit
Skill1 starsChanged 5 months agoMITView on GitHub
Audita metadata, consistencia y vocabulario de los documentos controlados del laboratorio AgentOps. Úsala antes de aprobar cualquier documento o tras editar docs/.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-behaviour-testSkill
- implementation-strategySkill
- knowledge-base-intakeSkill
- source-consolidationSkill
- validation-reportSkill
The file
Files
Skill: documentary-audit
Propósito (estrecho)
Verificar que los documentos controlados del laboratorio cumplen el contrato de
metadata, el vocabulario controlado y la política de datos definidos en
docs/00_CONTROL_DOCUMENTAL/LAB_SOURCE_000_FUENTE_UNICA_CONTROL_v0.1.0.md (LAB-SRC-000).
Trigger
- El usuario pide "auditar documentación" / "revisar metadata".
- Antes de mover un documento a
IN_REVIEWoAPPROVED_LAB. - Después de crear o editar archivos en
docs/.
Acciones permitidas
- Leer documentos en
docs/. - Ejecutar
python3 scripts/check_metadata.py,check_duplicate_ids.py,check_status_values.py. - Listar hallazgos con ruta y campo afectado.
- Proponer correcciones (sin aplicarlas si tocan canon o autorización).
Acciones prohibidas
- Declarar canon o cambiar
canon_statusa algo distinto deNOT_CANON. - Cambiar cualquier bandera de autorización a
true. - Modificar código Next.js o tocar el proyecto principal.
- Inventar datos reales o sustituir fixtures demo.
Salida esperada
- Un reporte breve (apto para
docs/02_REPORTES/) con: lista de hallazgos, severidad (info/warn/error) y veredicto PASS/FAIL. - Si hay error, indicar exactamente qué campo/documento corregir.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

