audit-workflow
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.zipInstalls 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.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
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 :
- Securite — injection, auth, secrets, IDOR, CSRF, headers
- Performance — N+1, allocations, pagination, index
- Maintenabilite — SOLID, couplage, complexite cyclomatique, dead code
- Scalabilite — contention, parallelisme, caching, limites
- Persistance — migrations, contraintes FK, index, requetes non optimisees
- Architecture — coherence des couches, separation des responsabilites, drift
- Tests — couverture, qualite des assertions, zones sans filet
- 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-001aSEC-NNNpour la securitePERF-001aPERF-NNNpour la performanceMAINT-001aMAINT-NNNpour la maintenabiliteSCALE-001aSCALE-NNNpour la scalabiliteDB-001aDB-NNNpour la persistanceARCH-001aARCH-NNNpour l'architectureTEST-001aTEST-NNNpour les testsOBS-001aOBS-NNNpour l'observabilite
Reconciliation GitHub
Cycle de vie des issues
- Finding nouveau → creer une issue avec label
status: new - Finding toujours present → mettre a jour l'issue existante
- Finding disparu → fermer l'issue avec un commentaire
- 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-expertcharge ce skill en debut de mission@review-expertpeut referencer les findings d'audit dans ses reviews@devroute vers@audit-expertquand 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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| audit-workflow (this skill) | 0 | 3mo | No flags | Intermediate |
| beforemerge-fullstack-architecture-review | 0 | 4mo | No flags | Advanced |
| agent-v3-security-architect | 3 | 6mo | Review | Advanced |
| github-code-review | 13 | 2mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by FlorianDrevet
View all by FlorianDrevet →You might also like
beforemerge-fullstack-architecture-review
adrian-coronel
Code review rules for DRY/SOLID layered architecture in fullstack TypeScript applications. Covers dependency direction, service/repository patterns, factory injection, domain entities, security hardening, performance optimization, and code quality patterns. Use this skill when reviewing, writing, or
agent-v3-security-architect
ruvnet
Agent skill for v3-security-architect - invoke with $agent-v3-security-architect
github-code-review
ruvnet
Comprehensive GitHub code review with AI-powered swarm coordination
reviewing-nextjs-16-patterns
djankies
Review code for Next.js 16 compliance - security patterns, caching, breaking changes. Use when reviewing Next.js code, preparing for migration, or auditing for violations.
agent-code-analyzer
ruvnet
Agent skill for code-analyzer - invoke with $agent-code-analyzer
code-review-ai-ai-review
sickn33
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C