soc2-audit-prep
$
npx mdskill add alirezarezvani/claude-skills/soc2-audit-prepConducts SOC 2 Type II readiness interrogation with six critical questions
- Evaluates SOC 2 Type II compliance readiness during observation periods
- Uses AICPA TSC criteria and audit standards for questioning
- Focuses on scope definition, control consistency, and incident history
- Delivers structured output for audit preparation and remediation planning
SKILL.md
.github/skills/soc2-audit-prepView on GitHub ↗
--- name: "soc2-audit-prep" description: "/cs:soc2-audit-prep <scope> — SOC 2 Type II readiness 6-question forcing interrogation. Observation-period focused. Use before Type II observation begins, mid-period checkpoint, or pre-field-test month-10 readiness." --- # /cs:soc2-audit-prep — SOC 2 Type II Forcing Questions **Command:** `/cs:soc2-audit-prep <scope>` The SOC 2 Type II auditor pressure-tests any SOC 2 work. Six observation-period-disciplined questions before any Type II cycle. ## When to Run - Pre-observation period (months 1-2 of cycle) - Mid-observation period (month 6 checkpoint) - Pre-field-test (month 10) - Post-report (planning next cycle) - After scope change (adding TSC category) - After major incident during observation period ## The Six SOC 2 Type II Questions ### 1. What's the scope, and which TSC categories are in? **Security always required; others elective based on customer ask.** - Common Criteria (CC1-CC9) under Security always - Availability (A1): for SaaS with SLA commitments - Processing Integrity (PI1): for systems processing transactional / financial data - Confidentiality (C1): for systems handling proprietary / confidential data - Privacy (P1-P8): for systems handling personal data (overlap with GDPR if applicable) - AICPA AT-C 205 description of system: complete + accurate + boundaries clear ### 2. Did any control skip a cycle during observation period? **Type II requires consistent operation — single skipped cycle = likely exception.** - Quarterly controls (e.g., access reviews): all 4 quarters covered - Monthly controls (e.g., vulnerability scans): all months covered - Continuous controls (e.g., logging): no gaps during period - Annual controls (e.g., BCP exercises, training): completed within period ### 3. Show me the change-management evidence for any control implemented mid-period. **Mid-period changes = high audit risk.** - New controls implemented during observation: documented with change-management - Modified controls: rationale + effective date + impact on prior samples - Removed controls: rationale + customer impact assessment - Strategy: avoid mid-period changes; defer to next cycle ### 4. Where's the exception log, and what's the materiality assessment? **Real-time exception logging — not retroactive.** - Each exception logged when discovered, not at audit time - Per exception: what / when / impact / remediation / owner - Materiality assessment: does the exception affect overall control operation? - Audit firm threshold: typically 1-2 exceptions per control acceptable; 3+ = finding ### 5. Show me sample evidence from each TSC criterion in the FIRST month of observation. **Not the last week — the first month.** - Audit firm samples across the observation period - Front-loaded evidence demonstrates operational discipline - Back-loaded evidence (last 30 days) = "scrambling" signal - Sample IDs should be reproducible from operational systems ### 6. What's the cross-walk to ISO 27001, and which evidence reuses? **75% control overlap — the canonical pair.** - Run `cross_framework_mapper.py` for HIGH-confidence overlap themes - Each shared artefact cited by both audits (one collection, two reports) - Coordinate audit calendar with cs-ciso-iso27001 - Avoid producing duplicate evidence files for same control ## Workflow ```bash # 1. Scoping + gap analysis (pre-observation) python ra-qm-team/skills/soc2-compliance/scripts/gap_analyzer.py current_state.json # 2. Control matrix with ISO 27001 cross-walk python ra-qm-team/skills/soc2-compliance/scripts/control_matrix_builder.py program.json # 3. Continuous evidence tracking (during observation) python ra-qm-team/skills/soc2-compliance/scripts/evidence_tracker.py evidence_log.json # 4. Mock audit (pre-field-test month 10) python ../../skills/compliance-os/scripts/audit_simulator.py soc2_scope.json ``` ## Output Format ```markdown # SOC 2 Type II Audit Prep: <scope> **Date:** YYYY-MM-DD **Observation Period:** YYYY-MM-DD to YYYY-MM-DD ## The Decision Being Made [scoping | pre-observation | observation-status | pre-field | report-response] ## TSC Scope - Security: included - Availability: <yes/no> - Processing Integrity: <yes/no> - Confidentiality: <yes/no> - Privacy: <yes/no> ## Observation Period Status - Months elapsed: N / 12 - Controls operated consistently: % of total - Cycle skips identified: <list> - Mid-period control changes: N (each documented with change-mgmt: yes/no) ## Exception Log - Total exceptions logged: N - Per-control max exceptions: M (audit firm tolerance: typically 1-2) - Material exceptions (overall control affected): <list> - Remediation status per exception: complete/in-progress ## Sample Evidence Coverage - Month 1-3 evidence: complete/gaps - Month 4-6 evidence: complete/gaps - Month 7-9 evidence: complete/gaps - Month 10-12 evidence: complete/gaps (only for pre-report status) ## ISO 27001 Cross-Walk Reuse - HIGH-confidence overlap themes: N - Shared artefacts in evidence pool: <count> - Duplicate evidence collection avoided: % savings ## Audit Firm Readiness - Scoping discussion: complete/pending - Description of system per AT-C 205: complete/pending - Walkthrough rehearsal: complete/pending - Sample preparation: complete/pending ## Verdict 🟢 ON-TRACK | 🟡 NEEDS-ATTENTION | 🔴 MATERIAL-RISK ## Top 3 Actions [3 concrete next steps with owner + observation-period timing] ``` ## Routing - `/cs:compliance-readiness` — for multi-framework view - `/cs:iso27001-audit-prep` — for ISO 27001 cross-walk pair (75% overlap) - `/cs:gdpr-audit-prep` — for Privacy TSC overlap - `/cs:ciso-review` — for executive cybersecurity strategy ## Related - Agent: [`cs-soc2-auditor`](../../agents/cs-soc2-auditor.md) - Skill: [`soc2-compliance`](../../../ra-qm-team/skills/soc2-compliance/SKILL.md) - Playbook: [soc2_audit_playbook.md](../../../ra-qm-team/skills/soc2-compliance/references/soc2_audit_playbook.md) - Adjacent: `../iso27001-audit-prep/`, `../gdpr-audit-prep/`, `../compliance-readiness/` --- **Version:** 1.0.0
More from alirezarezvani/claude-skills
- a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
- ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
- ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
- adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
- aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
- agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
- agent-protocolInter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.
- agent-workflow-designerDesign production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.
- agenthubMulti-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
- agile-product-ownerAgile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use when writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing the backlog.