Agent skill
phase-progress-auditor
Audits current project state for a given phase, detects completed, partial, or missing artifacts, fixes gaps via specs, and determines the correct next action.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/testing/phase-progress-auditor-ubaidraza1-ubaidraza1-todo-web-
SKILL.md
Phase Progress Auditor
Purpose
This skill ensures Claude never blindly regenerates work. It inspects the current project state before taking action.
Audit Before Action (MANDATORY)
Before executing any phase-level workflow:
- Check existing specs
- Check plans and tasks
- Check implementation files
- Check checklists / reviews
Possible States
- ✅ Complete
- 🟡 Partial
- ❌ Missing
- ⚠️ Inconsistent (spec ≠ code)
Behavior Rules
If Complete
- Do NOT regenerate
- Suggest next logical phase or enhancement
If Partial
- Identify exact gaps
- Generate ONLY missing specs or steps
- Never overwrite existing correct work
If Missing
- Run full phase workflow from scratch
If Inconsistent
- Propose spec fixes first
- Regenerate implementation ONLY after approval
Output Format
Always report:
- Current state
- Detected issues
- Proposed next actions
Never assume. Always verify.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?