mikeparcewski/wicked-garden-product-requirements-navigate
skills/product/requirements-navigate/SKILL.md
Navigate, query, and maintain requirements graphs. Regenerates meta.md on demand, checks coverage, finds gaps, and lints the graph structure. Use when: navigating or querying a requirements graph, generating a coverage report, refreshing meta.md, or linting graph structure for gaps.
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden wicked-garden-product-requirements-navigateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 13, 2026, 8:01 AM80.0s2 files scanned
SKILL.md
- name:
- wicked-garden-product-requirements-navigate
- description:
- |
- Use when:
- navigating or querying a requirements graph, generating a coverage
- phase_relevance:
- ["clarify", "design", "review"]
- archetype_relevance:
- ["*"]
Requirements Navigate
Read, query, and maintain requirements graph structures. Generates and refreshes meta.md files. Checks coverage and finds gaps.
Commands
Navigate (read graph)
Read a requirements node or area with progressive depth:
Depth 0 — frontmatter only (~5 tokens per node):
# Read just the frontmatter of all ACs in a story
for f in requirements/auth/US-001/AC-*.md; do
head -20 "$f" # frontmatter block
done
Depth 1 — meta.md (summary + tables):
# Read the story summary
cat requirements/auth/US-001/meta.md
Depth 2 — full content of specific nodes:
# Read a specific AC
cat requirements/auth/US-001/AC-001-login-success.md
Always start at depth 1 (meta.md) unless you need specific AC content.
Refresh meta.md
Regenerate a meta.md from its children when stale:
- Read all sibling/child files in the directory
- Parse frontmatter from each
- Rebuild the summary table (counts, priorities, coverage stats)
- Write updated meta.md preserving the
idandtypefields
Staleness check: Compare generated_at in meta.md frontmatter against
stat() mtimes of children. If any child is newer, regenerate.
When to refresh:
- Before displaying requirements status to user
- Before crew gate evaluation
- After batch AC creation
- On explicit user request
Coverage Query
Check which ACs have trace links:
For each AC in requirements/**/*.md where type: acceptance-criterion:
- Has IMPLEMENTED_BY? → code coverage
- Has TESTED_BY? → test coverage
- Has VERIFIES? → verification coverage
Output format:
Coverage: auth
US-001: 3/3 ACs, 1/3 implemented, 0/3 tested
US-002: 2/2 ACs, 0/2 implemented, 0/2 tested
Total: 5 ACs, 1 implemented (20%), 0 tested (0%)
Gap Analysis
Find structural problems:
- Orphan ACs: AC files not referenced in parent story meta.md
- Empty stories: Story directories with meta.md but no AC files
- Missing traces: P0 ACs without IMPLEMENTED_BY or TESTED_BY
- Broken traces: Trace targets that don't exist on disk
- Stale meta.md: Generated timestamps older than children
- ID mismatches:
id:field doesn't match file path
Lint
Validate graph structure:
For each .md in requirements/**/:
1. Has valid YAML frontmatter with required fields
2. id: matches relative path from requirements/
3. type: is a valid node type
4. traces: targets exist (warn, don't fail — code may not exist yet)
5. ACs have: priority, category, story
6. Stories have: priority, complexity, persona, status
7. meta.md tables match actual children
Fix mode: --fix auto-corrects:
- Regenerate stale meta.md files
- Update
id:to match current path - Add missing AC references to parent meta.md
Integration with traceability.py
The navigate skill reads graph nodes directly. For cross-phase queries
that span beyond requirements (design, code, tests, evidence),
traceability.py provides BFS traversal.
Bridge: When navigate finds IMPLEMENTED_BY or TESTED_BY traces
in frontmatter, these are the authoritative links for the requirement
layer. traceability.py can read these as an additional data source
alongside its DomainStore links.
Integration with search
Requirements graph nodes are indexable by search:index:
/wicked-garden:search:index requirements/
Enables queries like:
- "All P0 ACs without TESTED_BY" (frontmatter + FTS5)
- "All ACs tagged 'authentication'" (tag search)
- "Which stories trace to src/auth/" (reverse trace)
Progressive Disclosure
- SKILL.md (this file): Commands, query patterns, integration
- refs/meta-templates.md: Copy-paste meta.md templates for each level
Related Skills
mikeparcewski/wicked-garden-engineering-conformance-reviewer
development
VerifiedTrustedCommunity
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.
8SKILL.mdUpdated Jul 22, 2026
mikeparcewski/wicked-garden-domain
tools
VerifiedTrustedCommunity
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.
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-modeler
development
VerifiedTrustedCommunity
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).
8SKILL.mdUpdated Jul 15, 2026
mikeparcewski/wicked-garden-domain-extractor
tools
VerifiedTrustedCommunity
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).
8SKILL.mdUpdated Jul 15, 2026