القائمة
Intelligent code review agent — security (OWASP Top 10), best practices, test coverage, consistency. Auto-detects stack (Django/FastAPI/Node/Rust) and adapts checklists.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Code architecture design with web-informed debate between Architect and Reviewer agents — produces ASCII diagrams, justified stack, patterns (SOLID/DDD/CQRS), phased implementation plan.
Multi-turn brainstorming session with RAG, domain profiles (code/tech/btp/cyber/finance), Claude Opus or local Qwen3.5 backend.
CSV analysis via 2-pass SOTA orchestrator (score 54/55 on 7 CSVs). Statistics, data profiling, visualizations, insights.
Multi-perspective reasoning (advocate/critic/synthesizer). Three modes - general, --code for architecture decisions, --medical for EBM clinical analysis.
Deep reflection with web search — Brave/Perplexica pipeline fed into Qwen3.5-35B thinking mode for grounded, well-reasoned answers.
Threat intelligence analysis of IoCs (IPs, domains, hashes, URLs) via CyberBro (33 engines including Shodan/AbuseIPDB/VirusTotal) + Brave Search enrichment.
| name | review |
| description | Intelligent code review agent — security (OWASP Top 10), best practices, test coverage, consistency. Auto-detects stack (Django/FastAPI/Node/Rust) and adapts checklists. |
| trigger_patterns | ["review","code review","audit code","security review","owasp","audit projet"] |
| tools_required | ["exec","filesystem","llm_qwen35"] |
| examples | ["/path/to/project","/path/to/project --auto-fix","/path/to/project --categories security,best_practices"] |
| model | qwen3.5-35b-a3b |
| execution | {"command":"bash /home/remondiere/.openclaw/bin/code_reviewer_wrapper.sh review '$args'","timeout_ms":300000,"arg_mode":"raw"} |
Analyse adaptative d'un projet via Qwen3.5 avec thinking enabled. Détecte automatiquement le stack (Django, FastAPI, Node, Rust...) et adapte les checklists.
/path/to/project — review complet (security + best_practices + test_coverage + consistency)/path/to/project --auto-fix — review + correction automatique des patches/path/to/project --categories security,best_practices — catégories spécifiques| Category | Description |
|---|---|
| security | OWASP Top 10, secrets, auth, XSS, injection |
| best_practices | Anti-patterns framework-specifiques, N+1, race conditions |
| test_coverage | Gaps de tests, endpoints non-testés, edge cases |
| consistency | Cohérence spec↔code, deps inutilisées, code mort |
Rapport structuré avec findings par sévérité (critical/high/medium/low/info). Chaque finding inclut :
Avec --auto-fix, le skill applique les patches validés (high-confidence uniquement).
Les patches critiques sont toujours présentés pour validation manuelle.