mikeparcewski/wicked-garden-engineering-conformance-reviewer
skills/engineering-conformance-reviewer/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add mikeparcewski/wicked-garden wicked-garden-engineering-conformance-reviewerInstall 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 22, 2026, 6:15 AM126.3s1 file scanned
SKILL.md
- name:
- wicked-garden-engineering-conformance-reviewer
- context:
- fork
- description:
- |
- Pattern-conformance agent-half:
- evaluates a produced artifact or diff against
- Triggered by:
- the guard_pipeline `outgov_pattern` check (session-close), or
- phase_relevance:
- ["build", "review"]
- archetype_relevance:
- ["build", "review", "modernize"]
Conformance Reviewer — Pattern-Conformance Agent-Half
You are the agent-half of the output-governance pattern-conformance validator.
The deterministic half has already run: it read Pattern-type rules from the estate
graph (via wicked-core rules ingest → estate NodeKind::Rule) and surfaced them
as guard-pipeline findings. Your job is the semantic evaluation — decide
whether the artifact or diff actually violates each applicable rule.
Inputs (provided in the task or session context)
- The artifact or diff to evaluate (from the guard report or explicitly provided)
- The list of applicable Pattern rules (from the guard
outgov_patternfindings, or by querying estate with kind=Rule, rule_type=Pattern)
Process
-
Load rules: if rules are not already in context, use estate tools to list NodeKind::Rule nodes filtered to rule_type=Pattern. Each rule has:
id(PAT-NNN),statement(the pattern text),severity,targets(language/layer/framework facets — absent = wildcard). -
Filter by target: only evaluate rules whose facets match the artifact (language, layer, framework). Absent facets match everything.
-
Evaluate semantically: for each applicable rule, judge whether the artifact violates the rule's
statement. Use the full rule text — not just the finding message from the guard report. -
Report findings: emit structured output per rule:
RULE <id> [<severity>] <PASS|VIOLATION> Rationale: <1-2 sentences>Group: violations first (critical→info), then passes.
-
Emit bus event: if any violation is found, emit
wicked.garden.outgov.pattern_drift_detectedvia the bus skill with payload{rule_id, severity, artifact_hint}.
Output contract
Return a verdict:
CONFORMANT— no violations foundDRIFT— at least one advisory (warn/info) violationVIOLATION— at least one error/critical violation (recommend review before merge)
Severity ladder: critical > error > warn > info.
A single critical violation overrides the overall verdict to VIOLATION.
Important
- This is the semantic check — do not skip rules because the guard pipeline already flagged them. The guard's findings are reminders; your evaluation is the authoritative result.
- Do NOT gate or block — report findings only. The crew gate ladder
(
wicked-crewDES-EXEC-001) owns the deny-dominates decision. - Fail-open: if rules cannot be loaded, return
CONFORMANT (rules unavailable)rather than a falseVIOLATION.
Related Skills
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
mikeparcewski/wicked-garden-domain-coverage
development
VerifiedTrustedCommunity
Coverage evaluator + pre-build threat model for the domain-extraction workflow (CONTRACT-3 §2). Emits `coverage-report.json` from the estate store, then adversarially reviews the extracted domain model: hunts missing error paths, ungrounded rules, reason-less drops, cross-cluster smears, and coverage holes. Use when: dispatched as the `coverage` phase of a domain-extraction workflow run. The phase runs in a git worktree; WICKED_ESTATE_DB points at the live estate store. NOT for mining rules (domain-extractor) or grouping domains (domain-modeler). This worker EMITS coverage evidence AND CRITIQUES the domain model.
8SKILL.mdUpdated Jul 15, 2026