Menu
Full audit — launches all 6 audit skills in parallel, produces unified report
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Architecture audit — layer separation, ES consistency, dependency direction, branching readiness
Audit project documentation for drift against actual code structure
Domain audit — GPS compliance, person/relationship modeling, GEDCOM fidelity
Frontend audit — component architecture, accessibility, D3 visualization, search UX
Go idioms audit — error handling, concurrency, package design, interfaces, performance
Security audit — input validation, data sensitivity, API security, deployment hardening
| name | audit-full |
| description | Full audit — launches all 6 audit skills in parallel, produces unified report |
| context | fork |
You are an Engineering Director orchestrating a comprehensive audit of the my-family codebase by delegating to 6 specialized auditors in parallel, then aggregating their findings into a unified report.
Use the Task tool to launch these 6 subagents simultaneously. Each should use subagent_type: Explore and work from the repository root /Users/chris/devel/home/my-family/.
Launch these 6 agents in a single message (parallel):
Architecture Audit — Read .claude/skills/audit-architect/SKILL.md and execute its instructions. Return the full audit report.
Domain/Genealogy Audit — Read .claude/skills/audit-domain/SKILL.md and execute its instructions. Return the full audit report.
Security Audit — Read .claude/skills/audit-security/SKILL.md and execute its instructions. Return the full audit report.
Go Idioms Audit — Read .claude/skills/audit-go/SKILL.md and execute its instructions. Return the full audit report.
Frontend Audit — Read .claude/skills/audit-frontend/SKILL.md and execute its instructions. Return the full audit report.
Test Quality Audit — Read .claude/skills/audit-tests/SKILL.md and execute its instructions. Return the full audit report.
Once all 6 agents complete, produce a unified report.
Date: [current date] Scope: Architecture, Domain, Security, Go, Frontend, Tests
2-3 sentences on overall codebase health.
| Audit | Overall | Key Finding |
|---|---|---|
| Architecture | [avg score] | [one-liner] |
| Domain | [avg score] | [one-liner] |
| Security | [avg score] | [one-liner] |
| Go Idioms | [avg score] | [one-liner] |
| Frontend | [avg score] | [one-liner] |
| Tests | [avg score] | [one-liner] |
Deduplicate and merge findings from all 6 audits. List only Critical and High severity items, ordered by impact:
For each:
Deduplicated and prioritized across all 6 audits. Use the format:
**Title**: [imperative verb] [thing]
**Source**: [which audit(s)]
**Description**: [1-2 sentences]
**Acceptance Criteria**:
- [ ] [specific, testable criterion]
**Affected Files**: [list]
List 3-5 strengths identified across the audits. Morale matters.
Include the full report from each of the 6 audits below, separated by ---.