From rodlc-toolkit
Quality review — any system (code, config, business, organization)
How this skill is triggered — by the user, by Claude, or both
Slash command
/rodlc-toolkit:auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<audit-command>
Scope (priority): $ARGUMENTS → active plan → git diff HEAD~3 --name-only → error if none.
Domain auto-detect:
| Domain | Signals |
|---|---|
| Code | .py .ts .rb .go extensions, imports, functions |
| Config | .json .yaml .toml .md in .claude/, rules/, hooks |
| Business | plan, strategy, budget, OKR in description |
| Organization | directories, naming, structure in description |
"{domain} {pattern} best practices 2026" — skip if failStructure → Complementarity · Coherence · Simplicity
Interaction → Discoverability · Feedback · Integrity
Adaptation → Completeness · Resilience · Evolvability
Finding format: [severity] [dimension] location — description → suggestion
🔴 Critical → 🟠 Major → 🟡 Minor → 💡 Suggest
Deduplicate root causes. Cap at 15 findings total.
╔══════════════════════════════════════════════════════════╗
║ AUDIT {scope} │ 🔴 {n} 🟠 {n} 🟡 {n} 💡 {n} ║
╠══════════════════════════════════════════════════════════╣
║ Domain: {detected} │ Scope: {source} ║
╚══════════════════════════════════════════════════════════╝
🔴 Critical
────────────────────────────────────────────────────────────
1. [Dimension] location — description → suggestion
🟠 Major
────────────────────────────────────────────────────────────
2. [Dimension] location — description → suggestion
📊 Dimensions 🌐 Web applied
Structure ├── "query" → #N
├── Coherence ██░ └── "query" → #N
0 findings → "✓ No findings — system looks sound."
AskUserQuestion: Fix selected → EnterPlanMode | Export to plan | Done
npx claudepluginhub rodlc/claude-workshop-plugins --plugin rodlc-toolkitOrchestrates extensible code quality audits: discovers dimensions, builds DAG for phased parallel execution via subagents, each in isolated context window.
Audits a codebase as a senior advisor and produces prioritized, self-contained implementation plans for other models/agents to execute. Read-only — never implements or fixes code itself.
Runs codebase audits (health, evaluation, documentation) with parallel agents, producing intake docs for a pipeline run.