comply
Use for compliance-shaped reviews — SOC2, HIPAA, GDPR, PCI-DSS, or org-specific control sets. Maps the codebase against named controls, surfaces gaps, produces an evidence-based report.
What this skill does
# comply
Control-mapped compliance review. Pick the framework; map the code; surface gaps with evidence.
## Frameworks supported
- **SOC2 Type 2** — Common Criteria (CC) controls
- **HIPAA** — Privacy, Security, Breach Notification rules
- **GDPR** — data subject rights, lawful basis, processor obligations
- **PCI-DSS v4** — for payment-card-handling code
- **Industry clouds** (Salesforce: Health Cloud / Financial Services Cloud / Public Sector Solutions) — see `/siftcoder:salesforce-comply`
User picks framework; or detect from project metadata if obvious.
## Method
1. **Pick framework + scope.** Which controls apply? (e.g. SOC2: CC6 Logical Access; CC7 System Operations.)
2. **Per control, map code:**
- What evidence demonstrates the control?
- Where does the evidence live (code, config, log, doc, test)?
- Is the evidence current? Auditable? Tamper-evident?
3. **Gap analysis** for each control:
- Has evidence and is current → ✅
- Has evidence but stale → ⚠️
- No evidence → ❌
4. **Severity** for each gap. Compliance frameworks usually rank for you (e.g. SOC2 has Implementation status); use that.
5. **Remediation plan** with effort estimate.
## Output shape
```
Framework: <e.g. SOC2 Type 2>
Scope: <e.g. Common Criteria 6.1 — 6.8>
Evidence period: <date range>
Control mapping:
CC6.1 — Logical access controls
Evidence: src/auth/middleware.ts:14-58, audit-log table
Status: ✅ implemented, evidence current
Tests: tests/auth/access-control.test.ts (12 tests)
CC6.2 — Privileged access management
Evidence: <none found>
Status: ❌ gap
Risk: high — admin actions not logged
Remediation: instrument privileged ops in src/admin/*; ~2 days
CC7.1 — System monitoring
Evidence: monitors/memory-daemon-health.mjs, OpsGenie config
Status: ⚠️ partial — daemon health monitored; user-facing latency not
Risk: med
Remediation: add p95 latency alert; ~4 hours
Summary:
✅ 8 controls fully evidenced
⚠️ 3 controls partial
❌ 2 controls gap
Total remediation effort: ~3-5 days
```
## Rules
- **Cite evidence by file:line / table / config key.** No claim without a citation.
- **Frameworks have official wording.** Use it. Don't paraphrase controls.
- **Stale evidence is a gap.** Last-touched > 12 months on a code-based control = ⚠️.
- **Don't auto-fix.** Compliance changes need human review of the framework mapping. Output recommendations only.
## Anti-patterns
- Generic "you should have logging" without naming the control it satisfies
- Citing a control without showing the code that implements it
- Treating "we have a policy doc" as evidence (frameworks want operational evidence)
- Mapping controls to imagined code (cite real paths)
## When NOT to use
- General code quality — `/empathy`, `/review`
- Pre-audit dry-run — actually use it; this is its purpose
- Ad-hoc security review — `/security` skill (lighter touch)
## Subagent dispatch
- `Explore` for evidence collection
- Built-in `/security-review` overlaps; combine outputs
- `general-purpose` for the control mapping
- `salesforce-architect` agent for SF-specific compliance (Health, FS, Public Sector)
## Value over native CC
CC will discuss compliance topics if asked. CC won't naturally produce a control-by-control mapping with evidence citations and stale-evidence detection. The framework-shaped output IS the value — feeds directly into audit prep.
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.