Quality Checklist
Testing & Qualityquality-checklistQuality Checklist is an Agent Skill for testing & quality published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/methodologies/spec-kit/skills/quality-checklist/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/quality-checklist, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
- When validating code quality against constitution standards
- When verifying specification requirement coverage
- When running custom project-specific quality checks
Key Principle
Quality validation must be objective, reproducible, and multi-dimensional. Failed items must have actionable remediation recommendations. The checklist supports convergence loops -- re-validate after fixes until quality threshold is met.
Process
- Validate code quality - Check against constitution coding standards
- Verify test coverage - Ensure coverage meets constitution thresholds
- Check spec satisfaction - Verify all requirements are implemented
- Assess performance - Validate against constitution benchmarks
- Verify security - Check compliance with constitution security constraints
- Execute custom checks - Run any project-specific quality checks
- Score overall quality - Weighted average across categories (0-100)
- Produce recommendations - Actionable fixes for failed items
- Remediation loop - Re-validate after fixes (up to 3 iterations)
Tool Use
Invoke via babysitter process: methodologies/spec-kit/spec-kit-implementation (quality checklist phase)
Full pipeline: methodologies/spec-kit/spec-kit-orchestrator