meddev-ai-assisted-development-governance
Define governance for AI/LLM-assisted software development (e.g., Cursor, Copilot, Claude): human review expectations, evidence that generated code is covered by requirements-based tests, tool validation for GxP-adjacent workflows, and alignment with Computer Software Assurance (CSA) principles (risk-based, critical thinking) without replacing your SOPs. Use when working on ai assisted development governance in medical device software.
AminAlam · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add AminAlam/meddev-agent-skills --skill meddev-ai-assisted-development-governance技能说明
name: meddev-ai-assisted-development-governance description: 'Define governance for AI/LLM-assisted software development (e.g., Cursor, Copilot, Claude): human review expectations, evidence that generated code is covered by requirements-based tests, tool validation for GxP-adjacent workflows, and alignment with Computer Software Assurance (CSA) principles (risk-based, critical thinking) without replacing your SOPs. Use when working on ai assisted development governance in medical device software.' license: MIT metadata: skill_id: DOC-AI-GOV version: 1.0.1 last_updated: '2026-05-21' applies_to: Class A, Class B, Class C jurisdiction: Global prerequisites: REG-IEC62304, REG-ISO14971, DOC-TRACEABILITY category: documentation
AI-Assisted Development Governance (LLM Coding Agents)
Purpose
Define governance for AI/LLM-assisted software development (e.g., Cursor, Copilot, Claude): human review expectations, evidence that generated code is covered by requirements-based tests, tool validation for GxP-adjacent workflows, and alignment with Computer Software Assurance (CSA) principles (risk-based, critical thinking) without replacing your SOPs.
When to Apply
- Teams using LLMs for code generation, refactor, or test synthesis in regulated projects.
- Establishing AI usage policies for design history / audit trail.
- Qualifying IDE plugins or CI bots that touch production or QMS repositories.
Requirements (testable)
- Policy: Document where LLM assistance is allowed (e.g., scaffolding vs safety-critical modules) and required human review gates per risk class. Rationale: controlled process.
- Traceability: Every merged change must retain author/reviewer identity; LLM assistance disclosed in commit or PR template when policy requires. Rationale: audit trail.
- Independent Review: For Class B/C changes, second-person review of generated patches focusing on requirements coverage, failure modes, and misinterpreted specs. Rationale: defect detection beyond automation.
- Test Evidence: No merge without tests (or justified analysis) demonstrating REQ→TEST linkage for new behavior; forbid “LLM says it works” as evidence. Rationale: verification independence from generator.
- Prompt & Context Hygiene: No PHI/PII/proprietary trial data in prompts; use sanitized snippets; pin skill/context versions (e.g.,
SKILL.mdhashes) when claims depend on agent guidance. Rationale: confidentiality and reproducibility. 5a. IEC 62304 Skills by Class: LoadREG-IEC62304and child skills appropriate to safety class (e.g.DOC-SW-REQ,REG-IEC62304-SWRMfor B/C, detailed design for C); record skill IDs/versions in change records. Rationale: proportional lifecycle guidance. - Tool Validation (GxP): For tools affecting GMP/quality records, apply FDA CSA approach: risk assessment, intended use, testing records, and change control when models or plugins update. Rationale: 21 CFR Part 11 / 820 alignment for QMS software.
- Regression & Flakes: Treat LLM-generated tests like any other code — deterministic CI, seed control where needed, flake triage. Rationale: valid CI as design verification aid.
- Record Retention: Store PR descriptions, review comments, and test reports as part of DHF/evidence; avoid relying on vendor chat logs as SOLE records. Rationale: durable evidence.
Recommended Practices
- Use a PR checklist:
[ ] REQ IDs,[ ] tests added,[ ] reviewer not sole prompt author,[ ] no secrets in diff. - Snapshot agent skill versions in release notes when agent guidance materially influenced design.
Patterns
PR template excerpt (markdown):
## AI assistance
- [ ] No PHI/secrets in prompts or logs
- [ ] Assistant tools: Cursor 2.x + skills @ commit `abc1234`
- [ ] Reviewer verified REQ/TEST mapping for generated code
Commit message:
fix: debounce door sensor per REQ-62304-088
AI: scaffolded by LLM; reviewed by @jdoe; TEST-412 added
Anti-Patterns (risks)
- Blind merge of generated safety-critical code — risk: latent defects and audit failure.
- Pasting production credentials into chat — risk: data breach and Part 11 issues.
- Skipping review because “coverage is high” — risk: wrong tests for the right requirement.
Verification Checklist
- AI use policy acknowledged for the repo/product line.
- PRs show human reviewer distinct from sole prompt author where required.
- Requirements and tests updated for all generated behavior changes.
- No sensitive data in prompts or CI logs (spot audit).
- Tool/plugin major updates assessed under change control if GxP applies.
Traceability
- Link
REQ-*/TEST-*/ PR URLs in change records; optional tagAI-GENon commits for metrics (internal only).
References
- FDA Guidance: “Computer Software Assurance for Production and Quality System Software” (2022).
- IEC 62304:2006+A1:2015 — software development process (human processes still apply).
- Internal QMS SOPs for design control and records (primary authority).
Changelog
- 1.0.1 (2026-05-21): Require class-appropriate IEC 62304 child skills and version pinning in change records.
- 1.0.0 (2026-03-20): Initial skill for LLM-assisted dev governance, review, and CSA alignment.