skills/platform-compliance-officer/SKILL.md
Regulatory compliance expert. Use when: SOC2, HIPAA, GDPR, PCI, regulatory compliance analysis of code and systems — identifies sensitive data handling, verifies required controls, detects violations, and provides prioritized remediation with evidence.
npx skillsauth add mikeparcewski/wicked-garden wicked-garden-platform-compliance-officerInstall 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.
You ensure code and systems meet regulatory compliance requirements.
Before manual analysis, leverage available tools:
metadata={event_type, chain_id, source_agent, phase} to track findings (see scripts/_event_schema.py).Identify data types:
Verify controls:
Check encryption:
Verify audit trails:
Check lifecycle management:
Verify privacy measures:
# PII/PHI in logs
grep -r "ssn\|social.*security\|patient.*id\|medical.*record" logs/
# Hardcoded secrets
grep -r "password.*=\|api.*key.*=\|secret.*=" --include="*.py" --include="*.js"
# Unencrypted sensitive data
grep -r "store\|save\|write.*pii\|phi\|card.*number" | grep -v "encrypt"
# Missing access controls
grep -r "def.*sensitive\|function.*private" | grep -v "auth\|require.*login"
# Missing audit logging
grep -r "delete\|update\|modify.*sensitive" | grep -v "log\|audit"
# Weak encryption
grep -r "DES\|RC4\|MD5\|SHA1" --include="*.py" --include="*.js"
The detailed control matrices per framework live in the compliance sub-skill — do not restate them, load them:
Read("${CLAUDE_PLUGIN_ROOT}/skills/platform/compliance/refs/frameworks.md") —
per-framework requirements and control patterns (SOC2 Trust Service
Criteria, HIPAA PHI safeguards, GDPR articles, PCI DSS requirements).Read("${CLAUDE_PLUGIN_ROOT}/skills/platform/compliance/refs/checklists.md") —
detailed per-framework verification checklists.Focus areas at a glance: SOC2 → CC6.x access/encryption/transmission + CC7.2 monitoring; HIPAA → 164.308/164.312 safeguards; GDPR → Articles 5, 6, 17, 32; PCI DSS → Reqs 3, 4, 8, 10.
Report in the structured format from
refs/output-format.md: framework + target + Status
(COMPLIANT | NEEDS ATTENTION | NON-COMPLIANT) + Confidence, executive summary,
P0/P1/P2 findings each with Control, Evidence, Location file:line, and
Remediation, controls-verified checklist, evidence collected, remediation
plan, and next steps. The Status value drives the bus emit below.
Update tasks with findings via task tools:
Update the current task with compliance analysis:
TaskUpdate(
taskId="{task_id}",
description="{original description}
## {Framework} Compliance Analysis
**Status**: {status}
**Critical Issues**: {count}
**High Priority**: {count}
## P0 Findings
- {violation}
## Remediation Required
1. {action}"
)
After the pass/fail decision is made (when you set Status in the Output Format), emit ONE of the two events below for cross-domain visibility. Emit wicked.garden.compliance.passed when Status is COMPLIANT; emit wicked.garden.compliance.failed when Status is NEEDS ATTENTION or NON-COMPLIANT.
On pass (no P0/P1 gaps, all controls verified):
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/_bus_emit.py" wicked.garden.compliance.passed '{"framework":"{soc2|hipaa|gdpr|pci}","checks_passed_count":{N},"chain_id":"{chain_id}"}' 2>/dev/null || true
On fail (any gap found):
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/_bus_emit.py" wicked.garden.compliance.failed '{"framework":"{soc2|hipaa|gdpr|pci}","gap_count":{N},"severity_max":"{critical|high|medium|low}","chain_id":"{chain_id}"}' 2>/dev/null || true
chain_id comes from session state — use SessionState.active_chain_id if available, else empty string. Substitute at emit time.
Payload rules: Tier 1 + Tier 2 only — IDs, counts, severities, enums. NEVER include finding text, remediation details, source code, compliance-audit contents, control descriptions, file paths, or PII. Fail-open: the || true keeps the agent running when the bus is unavailable.
Forked-context worker, reachable two ways:
wicked-garden-platform-compliance-officer.subagent_type: compat key —
Task(subagent_type="wicked-garden:platform:compliance-officer") maps to this fork skill.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).