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
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
tools
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
development
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
tools
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).