data-audit
Skill0 starsChanged 7 months agoMITView on GitHub
Audit complet de qualite data sur les 9 dimensions ISO 8000-8. Utiliser pour verifier la fiabilite des donnees d'un projet, d'une table, ou d'un SIREN specifique.
Files
/data-audit — Audit Qualite Data
Objectif
Evaluer systematiquement la qualite des donnees sur les 9 dimensions ISO 8000-8 et produire un rapport actionnable.
Arguments
$ARGUMENTS: projet, table, ou SIREN a auditer (optionnel, defaut = projet courant)
Workflow
Phase 1 — Decouverte
- Identifier le schema de donnees (Prisma, Zod, interfaces TypeScript)
- Lister les sources de donnees externes (crawlers, imports, APIs)
- Identifier les tables/collections contenant des donnees
Phase 2 — Evaluation des 9 dimensions
Pour chaque source/table identifiee :
Dimension 1 — Validite
- Grep les schemas Zod dans
src/core/entities/etsrc/api/validation.ts - Verifier que chaque champ a un type et un domaine de valeurs
Dimension 2 — Exactitude
- Verifier les formats cles : SIREN (9 digits), RNA (W+9), NAF (4 digits + lettre)
- Cross-ref : champs verifiables contre source officielle
Dimension 3 — Fiabilite
- Classifier chaque source (Tier A/B/C) depuis
src/config/sources.ts - Verifier le
confidence_scorepar source
Dimension 4 — Fraicheur
- Verifier la presence de
source_updated_atvsingested_at - Calculer l'age moyen des donnees par source
Dimension 5 — Completude
- Identifier les champs obligatoires
- Estimer le taux de null sur les champs critiques
Dimension 6 — Coherence
- Detecter les contradictions (deadline < date_ouverture, etc.)
- Verifier la coherence inter-tables (FK, memes SIREN = memes noms)
Dimension 7 — Unicite
- Verifier les doublons sur cles primaires (SIREN, RNA, externalId)
Dimension 8 — Structure
- Verifier encodage UTF-8, dates ISO, normalisation
Dimension 9 — Tracabilite
- Verifier la presence des champs DataProvenance
- Verifier
enrichmentSourcesJSONB - Verifier
lineage_run_id
Phase 3 — Rapport
Generer un rapport Markdown avec :
- Score global et par dimension
- Violations classees P0/P1/P2
- Recommandations concretes avec fichiers/lignes
- Comparaison avec les SLOs (Gold/Silver/Bronze)
Reference
Voir references/iso8000-dimensions.md pour les definitions completes.
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- lianxhcn/PXa2026a★ 4same name
- 26zl/universal-agent-skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository172 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/skills/vercel-composition-patterns/AGENTS.mdAGENTS.md
- .claude/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- .claude/skills/vercel-react-native-skills/AGENTS.mdAGENTS.md
- address-sanitizerSkill
- aflppSkill
- agentic-actions-auditorSkill
- agentic-workspaceSkill
- agent-patternsSkill
- aides-finderSkill
- algorand-vulnerability-scannerSkill
- algorithmic-artSkill
- apexSkill
- ask-questions-if-underspecifiedSkill
- atherisSkill
- audit-context-buildingSkill
- audit-flash-cyberSkill
- audit-prep-assistantSkill
- audit-quickSkill
- bodacc-watchSkill
- brand-guidelinesSkill
- burpsuite-project-parserSkill
- cairo-vulnerability-scannerSkill
- canvas-designSkill
- capitalizeSkill
- cargo-fuzzSkill
- claude-in-chrome-troubleshootingSkill
- claude-memorySkill
- cnil-scannerSkill
- code-maturity-assessorSkill
- codeqlSkill
- code-review-agentSkill
- commitSkill
- competitive-intelSkill
- constant-time-analysisSkill
- constant-time-testingSkill
- content-machineSkill
- context-engineeringSkill
- cosmos-vulnerability-scannerSkill
- coverage-analysisSkill
- create-prSkill
- daily-briefingSkill
- data-cleanerSkill
- data-contractSkill
- data-freshness-checkSkill
- data-scienceSkill
- debug-buttercupSkill
- deep-researchSkill
- deploy-to-vercelSkill
- designing-workflow-skillsSkill
- devcontainer-setupSkill
- devops-agentSkill
- differential-reviewSkill
- dl-capitalizeSkill
- dl-costSkill
- dl-crawlSkill
- dl-importSkill
- dl-mcpSkill
- dl-scaffoldSkill
- dl-schemaSkill
- The first 60 shown.
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.

