AU

Conducts and reconciles technical audits across security, architecture, and performance domains.

Install

mkdir -p .claude/skills/audit-workflow && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14985" && unzip -o skill.zip -d .claude/skills/audit-workflow && rm skill.zip

Installs to .claude/skills/audit-workflow

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when: code audit, technical audit, security audit, performance audit, scalability audit, database audit, audit markdown, GitHub audit issues, findings reconciliation, labels sync.
183 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Generate technical audit reports in Markdown
  • Create GitHub issues for audit findings
  • Reconcile findings between successive audits
  • Sync GitHub labels for severity and category
  • Cover security, performance, and maintainability aspects
  • Define action plans for remediation phases

How it works

The skill structures audit findings into a Markdown report with specific identifiers and categorizes them for GitHub issue creation and reconciliation.

Inputs & outputs

You give it
Audit findings, code analysis, system configurations
You get back
Markdown audit report, GitHub issues with labels, reconciliation status

When to use audit-workflow

  • Perform a security audit of the authentication layer
  • Audit application performance for N+1 query issues
  • Create a technical audit report and action plan
  • Reconcile findings between two audit sessions

About this skill

Skill : audit-workflow — Audit technique et reconciliation

Charger ce skill pour toute tache d'audit technique, que ce soit la production du rapport, la creation d'issues GitHub, ou la reconciliation entre deux audits successifs.


Couverture d'audit

Un audit complet doit couvrir :

  1. Securite — injection, auth, secrets, IDOR, CSRF, headers
  2. Performance — N+1, allocations, pagination, index
  3. Maintenabilite — SOLID, couplage, complexite cyclomatique, dead code
  4. Scalabilite — contention, parallelisme, caching, limites
  5. Persistance — migrations, contraintes FK, index, requetes non optimisees
  6. Architecture — coherence des couches, separation des responsabilites, drift
  7. Tests — couverture, qualite des assertions, zones sans filet
  8. Observabilite — logging, tracing, health checks, metriques

Format du rapport

Emplacement : audits/audit-dd-MM-yyyy.md

Structure :

# Audit Technique — [DATE]

## Resume executif
- CRITICAL: X
- HIGH: Y
- MEDIUM: Z
- LOW: W

## Findings

### CRITICAL

#### SEC-001: [titre]
- **Localisation:** fichier(s) concernes
- **Description:** ce qui est problematique
- **Impact:** consequence si non corrige
- **Recommandation:** correction concrete
- **Effort:** S/M/L

### HIGH
...

### MEDIUM
...

### LOW
...

## Plan d'action
### Phase 1 — Critique (< 1 semaine)
### Phase 2 — Important (< 1 mois)
### Phase 3 — Amelioration continue

## Metriques cibles

Identifiants de findings

Chaque finding a un identifiant unique et stable :

  • SEC-001 a SEC-NNN pour la securite
  • PERF-001 a PERF-NNN pour la performance
  • MAINT-001 a MAINT-NNN pour la maintenabilite
  • SCALE-001 a SCALE-NNN pour la scalabilite
  • DB-001 a DB-NNN pour la persistance
  • ARCH-001 a ARCH-NNN pour l'architecture
  • TEST-001 a TEST-NNN pour les tests
  • OBS-001 a OBS-NNN pour l'observabilite

Reconciliation GitHub

Cycle de vie des issues

  1. Finding nouveau → creer une issue avec label status: new
  2. Finding toujours present → mettre a jour l'issue existante
  3. Finding disparu → fermer l'issue avec un commentaire
  4. Finding ferme qui reapparait → rouvrir l'issue

Labels d'audit

Les labels doivent etre organises en deux dimensions :

  • Severite : severity: critical, severity: high, severity: medium, severity: low
  • Categorie : category: security, category: performance, category: maintainability, etc.
  • Status : status: new, status: in-progress, status: fixed, status: wontfix

Integration avec les agents

  • @audit-expert charge ce skill en debut de mission
  • @review-expert peut referencer les findings d'audit dans ses reviews
  • @dev route vers @audit-expert quand une demande d'audit est detectee

When not to use it

  • The task is not related to technical audits
  • The task does not involve GitHub issues or Markdown reports

Limitations

  • The skill focuses on technical audits and their associated reporting and issue management.
  • The skill is limited to the specified audit coverage areas.
  • The skill expects a specific Markdown report format and GitHub label structure.

How it compares

This skill standardizes the audit reporting and issue management process by providing a predefined Markdown structure and GitHub label synchronization, which differs from a manual, unstructured approach.

Compared to similar skills

audit-workflow side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
audit-workflow (this skill)03moNo flagsIntermediate
beforemerge-fullstack-architecture-review04moNo flagsAdvanced
agent-v3-security-architect36moReviewAdvanced
github-code-review132moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry