architecture-compliance-review
Use this skill to review compliance contract portfolio health. Validates all 10 contracts exist and are ≤6 months old, triggers regeneration for missing/expired contracts, and generates an interactive playground for exploring concept gaps across all contracts to understand what needs to be addressed to reach the auto-approve threshold (≥8.0/10).
What this skill does
# Architecture Compliance Review Skill ## Purpose This skill acts as a **compliance portfolio health reviewer**. It validates that all 10 compliance contracts are present and fresh (≤6 months old), analyzes each contract's requirement gaps, and generates an interactive HTML playground for exploring the concept gaps across all contracts — helping you understand which areas of ARCHITECTURE.md fall short of the auto-approve threshold (≥8.0/10) and why. **Auto-Approve Threshold**: ≥8.0/10 per contract. **Maximum Contract Age**: 6 months. Any contract older than 6 months is considered EXPIRED and must be regenerated before review proceeds. --- ## When to Invoke This Skill - User asks to "review compliance contracts", "check compliance coverage", or "assess compliance health" - User wants to know what must be fixed to reach auto-approve across all contracts - User asks for a "compliance gap analysis", "compliance dashboard", or "compliance review" - User wants to explore which ARCHITECTURE.md concepts to update for compliance - User uses `/skill architecture-compliance-review` **Do NOT invoke for:** - Generating new compliance contracts → use `architecture-compliance` skill - **Recreating, regenerating, or rebuilding compliance contracts or the compliance manifest** → use `architecture-compliance` skill - Creating or editing ARCHITECTURE.md → use `architecture-docs` skill - Architecture quality peer review → use `architecture-peer-review` skill - Business requirements documentation → use `architecture-readiness` skill --- ## Files in This Skill | File | Purpose | |------|---------| | `SKILL.md` | This file — entry point and workflow | | `PLAYGROUND_TEMPLATE.md` | Playground template for the interactive compliance gap explorer HTML | --- ## The 10 Required Compliance Contracts | # | Contract Type | Identifier Prefix | |---|---------------|-------------------| | 1 | SRE Architecture | `SRE_ARCHITECTURE` | | 2 | Business Continuity | `BUSINESS_CONTINUITY` | | 3 | Cloud Architecture | `CLOUD_ARCHITECTURE` | | 4 | Data & AI Architecture | `DATA_AI_ARCHITECTURE` | | 5 | Development Architecture | `DEVELOPMENT_ARCHITECTURE` | | 6 | Process Transformation & Automation | `PROCESS_TRANSFORMATION` | | 7 | Security Architecture | `SECURITY_ARCHITECTURE` | | 8 | Platform & IT Infrastructure | `PLATFORM_INFRASTRUCTURE` | | 9 | Enterprise Architecture | `ENTERPRISE_ARCHITECTURE` | | 10 | Integration Architecture | `INTEGRATION_ARCHITECTURE` | --- ## Workflow ### Step 1 — Locate COMPLIANCE_MANIFEST.md Search for `compliance-docs/COMPLIANCE_MANIFEST.md` at the project root. If not found, abort with: > *"No COMPLIANCE_MANIFEST.md found. Run `/skill architecture-compliance` to generate compliance contracts first, then return here for the review."* --- ### Step 2 — Parse Manifest and Determine Coverage Read `compliance-docs/COMPLIANCE_MANIFEST.md`. Extract: - Project name - For each listed contract: contract type, filename, generation date, status, score **Get today's date** by running: `bun [plugin_dir]/scripts/today.ts` (cross-platform Bun helper; replaces `date +%Y-%m-%d` so the skill runs identically on Linux, macOS, Windows native, WSL, and Git Bash) **6-month cutoff rule**: A contract is VALID only if its generation date is within 6 calendar months of today. Compute the cutoff date = today minus 6 months (e.g., if today is 2026-03-22, the cutoff is 2025-09-22). **For each of the 10 required contract types**, determine: - **present**: Is the contract listed in the manifest? Confirm the file exists in `compliance-docs/` using Glob. - **fresh**: Is the generation date on or after the 6-month cutoff? - **contract_status**: `valid` | `missing` | `expired` Build a coverage summary table and display it to the user: ``` | # | Contract Type | Status | Generation Date | Age | Score | |---|-------------------------------|-----------|-----------------|----------|---------| | 1 | SRE Architecture | ✅ Valid | 2025-12-27 | 2.8 mo | 7.69/10 | | 2 | Business Continuity | ❌ Missing | — | — | — | | 3 | Security Architecture | ⚠️ Expired | 2025-01-15 | 14.2 mo | 6.5/10 | | … | … | … | … | … | … | ``` --- ### Step 3 — Handle Missing and Expired Contracts If **all 10 contracts are valid**, skip to Step 4. If any contracts are `missing` or `expired`, present the user with a choice: > **N contract(s) are missing or expired and cannot be included in this review.** > > **[A] Regenerate now** — invoke the `architecture-compliance` skill for the affected contracts, then continue the review > **[B] Proceed with valid contracts only** — review covers only the valid contracts; missing/expired will be marked as NOT REVIEWED > **[C] Cancel** — stop here and regenerate contracts manually with `/skill architecture-compliance` - **Option A**: Invoke the `architecture-compliance` skill specifying only the affected contract types. Wait for completion. Re-read the manifest. Proceed to Step 4. - **Option B**: Proceed to Step 4 with the available valid contracts. Track missing/expired contracts separately as NOT REVIEWED items in the playground data. - **Option C**: Abort with guidance to use `/skill architecture-compliance`. --- ### Step 4 — Read Contract Files for Gap Extraction For each contract with `contract_status = valid`, read the actual file from `compliance-docs/`. From each contract file, extract the following data: #### 4a. Score and Requirement Breakdown Locate the Document Control section (table with `| Field | Value |` format) or the score summary. Extract: - Current score (e.g., `7.69/10`) - Projected score after resolving all Unknown gaps (if stated) Locate the requirement breakdown section. Extract counts for: - Blocker requirements: total, compliant, not applicable, unknown, non-compliant - Desired requirements: total, compliant, not applicable, unknown, non-compliant #### 4b. Gap Rows from Compliance Summary Table Locate the **Compliance Summary Table** — a 6-column table with headers: `| Code | Requirement | Category | Status | Source Section | Responsible Role |` Extract every row where `Status` = `Non-Compliant` OR `Status` = `Unknown`. For each gap row, capture: - `code`: requirement code (e.g., `SRE-B-023`) - `requirement`: full requirement text - `category`: compliance category - `status`: `Non-Compliant` or `Unknown` - `sourceSection`: ARCHITECTURE.md source section reference - `priority`: determine whether this is a **Blocker** or **Desired** requirement by checking which section heading precedes the row (e.g., "Blocker Requirements" or "Desired Requirements") **Assign concept tags** to each gap based on requirement text keywords: - Load testing, stress testing, performance testing → `["load-testing", "performance"]` - Chaos engineering, fault injection → `["chaos-engineering", "resilience"]` - RTO, RPO, DR, disaster recovery → `["dr-rto-rpo", "business-continuity"]` - IAM, RBAC, authentication, authorization → `["iam", "access-control"]` - Monitoring, observability, alerting, SLO, SLA → `["observability", "monitoring"]` - Data retention, data classification, data governance → `["data-governance"]` - CI/CD, pipeline, deployment automation → `["cicd", "deployment"]` - API documentation, API contracts, OpenAPI → `["api-docs", "integration"]` - Encryption, TLS, mTLS, certificates → `["encryption", "security"]` - Incident management, runbooks, SOPs, on-call → `["incident-management", "operations"]` - Capacity planning, scaling, auto-scaling → `["capacity-planning", "scalability"]` - Compliance framework, audit, GDPR, SOC2 → `["regulatory-compliance"]` --- ### Step 5 — Compute Gap Analysis #### 5a. Per-Contract Auto-Approve Gap For each valid contract, compute: - `aboveThreshold`: score ≥ 8.0 - `gapToThreshold`: max(0, 8.0 − score) - Estimated score if all Unknown gaps resolved t
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.