Agent skill
review-plan
Review a proposed design or implementation plan before implementation
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/review-plan-daemn256-workspace-repo-templ
SKILL.md
Review Plan
Uses Reviewer. Evaluate a design document or implementation plan against ticket requirements and the Plan Quality Contract. Produce structured feedback and a verdict.
Prerequisites: Plan document path or content, ticket requirements and acceptance criteria available
Phase 1: Gather Context
Understand What Is Being Reviewed
- Locate the plan document (check
docs/notes/for*ticket-<N>*if path not provided) - Read the linked ticket — title, body, acceptance criteria, constraints
- Note the ticket scope: what is in scope vs. out of scope
Phase 2: Evaluate the Plan
Apply Plan Quality Contract
Evaluate the plan against each criterion:
The plan MUST contain:
- Problem statement — Is it clear what is being solved and why?
- Constraints — Are non-negotiable requirements listed?
- Scope — Is there an explicit list of files, sections, or components in scope?
- Ordered steps — Are steps numbered, specific, and actionable with file paths?
- AC mapping — Is each acceptance criterion traced to one or more steps?
- Verification steps — Can the Implementer confirm each step is done?
- Open assumptions — Are unresolved questions listed explicitly?
The plan MUST NOT:
- Use vague verbs ("update", "improve", "handle") without specifying exactly what
- Reference files without providing the path
- Leave multiple approaches open for the Implementer to choose
- Skip verification steps
- Omit acceptance criteria mapping
Completeness Assessment
Answer these questions:
- Is the plan detailed enough for an Implementer to execute without guessing?
- Are file locations, expected changes, and verification steps specified?
- Are there gaps, unstated assumptions, or overlooked risks?
Phase 3: Produce Feedback
Structure and Present
- Determine verdict (Approve, Request Changes)
- List blocking issues (gaps that would cause the Implementer to guess or fail)
- List suggestions (improvements that would increase clarity or coverage)
- Note positive observations (well-structured sections, thorough coverage)
Output
## Context Anchors
- **Reviewing:** <plan document path>
- **Type:** Design
- **Issue:** #<number> - <title>
## Summary
<One paragraph overall assessment of plan quality and readiness>
## Blocking Issues
1. **[Section] <Issue>**
- Problem: <what's missing or unclear>
- Suggestion: <what would fix it>
## Suggestions
1. **[Section] <Suggestion>**
- Current: <what it says now>
- Suggested: <what would be clearer>
## Positive Notes
- <well-structured or thorough sections>
## Verdict
APPROVE | REQUEST_CHANGES
## Next Step
<If REQUEST_CHANGES: "Address feedback and revise the plan">
<If APPROVE: "Plan is ready for implementation">
**Approval Required:** Yes
⛔ CHECKPOINT
STOP. Do not post review until verified:
- All Plan Quality Contract criteria reviewed
- Blockers are genuinely blocking (not style preferences)
- Feedback is specific and actionable
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
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.
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.
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.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
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?