メニュー
Validate implementation against plan, verify success criteria, identify issues. Use after implementing-plan to confirm execution, check success criteria, and generate validation reports.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Create detailed implementation plans through interactive research and iteration. Use when planning new features, designing changes, writing technical specs.
Implement technical plans from thoughts/shared/plans with verification. Use when executing approved implementation plans, resuming partially completed plans, or when the user mentions execute plan or resume plan.
End-to-end smoke test a ThoughtCabinet skill by deploying it to a target agent, running the agent non-interactively against a test project, capturing output, and evaluating results. Use when you want to verify a skill works correctly before shipping.
Onboard an AI agent to a new project by initializing ThoughtCabinet thoughts repo and bootstrapping agent memory. Use when starting work on a new repository, setting up a fresh project for AI-assisted development, or when the user asks to onboard, bootstrap, or initialize a project.
Write tests before implementation code using red-green-refactor. Use when implementing features, fixing bugs, or when the user mentions TDD, test-first, or test-driven.
Create, revise, or distill workflows into skills following best practices. Use when user asks to create a new skill, iterate on an existing skill, distill a session workflow into a reusable skill, or improve skill quality.
| name | validating-plan |
| description | Validate implementation against plan, verify success criteria, identify issues. Use after implementing-plan to confirm execution, check success criteria, and generate validation reports. |
Verify that implementation plans from thoughts/shared/plans/ were correctly executed, check success criteria, and identify deviations or issues.
If plan path provided, use it. Otherwise:
ls -lt thoughts/shared/plans/ | head
Ask user which plan to validate.
# Recent commits
git log --oneline -n 20
# Diff covering implementation commits
git diff HEAD~N..HEAD # Where N covers implementation commits
# Run verification
cd $(git rev-parse --show-toplevel) && make check test
Read the implementation plan completely and identify:
Use parallel research tasks if needed (via Task tool):
codebase-analyzer: Verify changes match plan specifications
thoughts-locator: Find related documentation or decisions
For each phase in the plan:
Check completion status
Run automated verification
Assess manual criteria
Analyze edge cases
## Validation Report: [Plan Name]
### Implementation Status
- Phase 1: [Name] - [Status]
- Phase 2: [Name] - [Status]
### Automated Verification Results
- Build: `make build` - [Pass/Fail]
- Tests: `make test` - [Pass/Fail]
- Lint: `make lint` - [Pass/Fail]
### Code Review Findings
**Matches Plan:**
- [Implementation detail with file:line]
**Deviations from Plan:**
- [Deviation with file:line and explanation]
**Potential Issues:**
- [Issue and impact]
### Manual Testing Required
- [ ] [Test step 1]
- [ ] [Test step 2]
### Recommendations
- [Action item]
If you participated in implementation:
Always verify:
Be Thorough: Run all automated checks; don't skip verification commands.
Document Everything: Both successes and issues.
Think Critically: Question if the implementation truly solves the problem.
Consider Maintenance: Will this be maintainable long-term?
Recommended workflow:
implementing-plan - Execute the implementation/commit - Create atomic commitsvalidating-plan - Verify implementation correctnessValidation works best after commits are made, enabling git history analysis.