skills/engineering/docs-audit/SKILL.md
Audit documentation coverage and quality. Find undocumented code, assess completeness, and provide coverage metrics. Use when: "audit docs", "doc coverage report", "find undocumented code", "documentation gaps", "what's missing docs", "doc completeness"
npx skillsauth add mikeparcewski/wicked-garden docs-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Assess documentation coverage and quality across the codebase.
Evaluate documentation health:
| Command | Purpose |
|---------|---------|
| /wicked-garden:engineering:docs-audit [path] | Audit documentation coverage |
| /wicked-garden:engineering:docs-audit --full | Comprehensive audit with quality scoring |
| /wicked-garden:engineering:docs-audit --report | Generate coverage report |
# Basic coverage audit
/wicked-garden:engineering:docs-audit src/
# Full audit with quality assessment
/wicked-garden:engineering:docs-audit src/ --full
# Generate report
/wicked-garden:engineering:docs-audit --report docs/coverage-report.md
Discover all documentable items:
For each item, verify:
Coverage Percentage:
Coverage = (Documented Items / Total Items) × 100
Quality Score (0-100):
Prioritize undocumented items:
Check each function/class/API for documentation. Calculate coverage percentage and quality score. Identify undocumented (✗), partial (⚠), and documented (✓) items.
Rate documentation quality (0-100):
# Documentation Coverage Report
Generated: {timestamp}
## Summary
| Category | Total | Documented | Coverage |
|----------|-------|------------|----------|
| Functions | 145 | 98 | 67.6% |
| Classes | 23 | 21 | 91.3% |
| APIs | 28 | 28 | 100% |
| **Overall** | **196** | **147** | **75.0%** |
## Quality Distribution
| Quality | Count | Percentage |
|---------|-------|------------|
| Excellent (76-100) | 45 | 30.6% |
| Good (51-75) | 89 | 60.5% |
| Basic (26-50) | 13 | 8.9% |
**Average Quality Score:** 65.2/100
## Top Issues
### Undocumented Public Functions (12)
**High Priority:**
- `src/api/auth.ts::authenticate` - Core auth function
- `src/api/users.ts::deleteUser` - Destructive operation
- `src/utils/validation.ts::validateInput` - Public API
### Missing Examples (67)
Functions without usage examples
## Recommendations
1. Document 12 high-priority public functions
2. Add examples to 67 functions
3. Complete parameter docs for 23 functions
Use wicked-garden:search to find code to audit.
Native TaskCreate (with metadata.event_type="task") tracks documentation tasks for gaps.
product reviews documentation quality.
[docs:coverage:info] - Coverage metrics calculated[docs:missing:warning] - Undocumented code found[docs:quality:info] - Quality assessment completedaudit:
min_coverage: 80 # Target coverage percentage
min_quality: 60 # Target quality score
scope:
include_private: false # Audit private members
include_tests: false # Audit test files
quality:
require_description: true # Description required
require_parameters: true # Parameter docs required
require_examples: true # Examples required
development
--- name: large-scale-migration description: How to execute a LARGE MECHANICAL change across any codebase with LEVERAGE instead of an agent-grind or hand-edits — a cross-cutting migration, refactor, rename, dialect/framework/DB port, library adoption, or bulk transform. The map→transform→gate pattern: a deterministic transform driven by a source-of-truth map, proven by a differential-equivalence gate. Use when the work is "migrate all X to Y", "rename Z everywhere", "port to a new DB/dialect/fra
testing
v11 LLM-based work-shape classifier. Replaces the regex archetype detector with the model's own reasoning. Reads the user's prompt, picks the right archetype(s) from the catalog, identifies signals (blast_radius, novelty, reversibility, etc.), and persists to SessionState so subsequent turns steer correctly. Use when: the prompt_submit hook emitted a `<wg classify-due />` directive, OR explicitly invoked at session start, OR when re-classifying after the user changes scope mid-session.
tools
v11 work-shape archetype runner. When a prompt has been routed to one of the 9 archetypes (triage, explore, specify, decide, ship, review, incident, build, migrate), this skill is the entry point. It picks the right per-archetype playbook from refs/ and executes the phase shape declared in `.claude-plugin/archetypes.json`. Use when: a `<wg archetype="X">` or `<wg archetypes>` system-reminder tag appears, an explicit "let's run the X archetype" request, or when one of the per-archetype slash commands resolves to this skill.
development
Show or set the session intent variable. Intent gates how loud the framework is — simple-edit (silent), feature/research (synthesis directive), rigor (full crew context). Auto-detected on turn 1; this skill overrides explicitly. Sticky for the session. Use when: "set intent", "intent override", "/wicked-garden:intent", "make the framework quiet", "force rigor", "what's my intent".