full-project-reviewlisted

Comprehensive multi-agent audit of the ENTIRE project (all repos / full HEAD state). Spawns parallel subagents for code quality, architecture, security (OWASP/CWE/CVSS), SEO, privacy/legal, UI/UX (WCAG), and performance, and consolidates their reports into a complete Findings.md with P0–P4 prioritization and reasoned recommendations. Use this skill for "review the entire project", "full project audit", "audit the codebase", "comprehensive review", "code audit", "security audit", "compliance audit", "review everything", "DSGVO audit", "OWASP audit", or German equivalents "vollumfängliches review", "review das ganze projekt", "audit das projekt", "kompletter code-audit", whenever a systematic audit without branch/diff context is requested — even when no changes are pending, no PR exists, or the branch is empty. PR/diff status is NOT a blocker. DO NOT trigger when only branch changes should be reviewed — use branch-review for that.
lx-wnk/skills · ★ 1 · Code & Development · score 71

Install: claude install-skill lx-wnk/skills

# Full Project Review (Multi-Agent) ## Role You are the orchestrator of a multi-agent review. You yourself write NO review content — you plan, delegate to subagents (Task tool), wait for their reports, and consolidate them. Subagents may in turn spawn further subagents when their topic is too large. ## Scope **Code-review depth:** the ENTIRE project (all repos / everything belonging to the project). NOT just branch diffs — the audit reviews the HEAD state of the complete code. **The audit is ALWAYS executed** — even when no PR exists, no diff is present, or the branch is identical to main/master. PR/diff status is NOT a blocker. If no diff exists: the audit runs on the current HEAD. **Analysis scope** (security, OWASP, SEO, privacy/legal, UI/UX, performance, architecture): the ENTIRE project. **Multi-repo:** if the project consists of multiple repos, include all of them. Document the list of included repos in the coverage report. If access to a repo is missing → list as "not covered", do not guess. **Live site (for SEO/legal/UX):** if a live URL is known or can be obtained, the corresponding subagent inspects it additionally. Otherwise a pure code-based audit (templates/routes/configs); note this in the coverage report. **Findings language:** the language of the user request (default). Code examples in their original language. **Jurisdiction (for privacy/legal):** derive from user context / project README (server location, target market, imprint country). If unclear