Reviewing Plans
Core mindset: You're not checking whether the plan sounds smart. You're checking whether a diligent but literal executor can follow it step by step and arrive at exactly what you wanted — nothing more, nothing less.
Announce at start: "I'm using the reviewing-plans skill to review this plan."
1. Problem & Scope
- Does it restate and solve the actual problem, not a nearby easier one?
- Is this the simplest approach that solves it, or is there an obvious simpler alternative?
- No extra features or refactors you didn't ask for. No vague hand-waving ("handle edge cases") on the hard parts.
- If you can't tie a step to your original request in one sentence, cut it.
2. Step Quality
Each step must be specific (exact files/functions), atomic (one thing), ordered (no forward dependencies), and verifiable (clear "done" condition).
Red flags: vague steps ("clean up the code"), bundled mega-steps, assumed knowledge not in the plan.
3. Dependencies & Risk
- Steps in the right order? Hidden dependencies called out?
- What's the blast radius? Destructive actions (deletions, migrations) isolated and done last?
- If step N fails, are steps 1–(N-1) still usable?
4. Verification
- Does it start from a known state and end with a verified one?
- Every meaningful step has a concrete check ("run suite X, expect green" not just "run tests").
- Final end-to-end verification exists, not just step-by-step.
- Existing behavior is confirmed preserved.
5. What's Missing
- Failure handling (network errors, invalid input, partial state)
- Existing tests — will they still pass?
- Boundaries (empty states, first run, large datasets)
- Cleanup (dead code, imports, deprecations)
6. Exit Criteria
"Done" is clearly defined, independently verifiable, and ends with a concrete deliverable — not "continue improving."
7. Red Flags Cheat Sheet
| You see |
It means |
| "Refactor/update as needed" |
No plan, will improvise |
| "For completeness" / "While we're here" |
Scope creep |
| Steps with no verification |
Will claim success unchecked |
| New abstractions for one use case |
Over-engineering |
| Touching unrelated files |
Scope creep or misunderstanding |
| "Should be straightforward" |
Hasn't thought it through |
| No mention of existing tests |
Will break things silently |
| "We'll handle that later" |
Deferring the hard part |
| "Similar to how we did X" |
Assuming without verifying |
| Plan starts with code changes, not verification |
Guessing, not diagnosing |
1---2name: reviewing-plans3description: Use when reviewing an AI-generated implementation plan before execution, when handed a plan to approve, or when checking if a plan is ready to act on4metadata:5 source: https://skillmd.com/skills/ogu8/reviewing-plans6---78# Reviewing Plans910**Core mindset:** You're not checking whether the plan sounds smart. You're checking whether a diligent but literal executor can follow it step by step and arrive at exactly what you wanted — nothing more, nothing less.1112**Announce at start:** "I'm using the reviewing-plans skill to review this plan."1314---1516## 1. Problem & Scope1718- Does it restate and solve the *actual* problem, not a nearby easier one?19- Is this the simplest approach that solves it, or is there an obvious simpler alternative?20- No extra features or refactors you didn't ask for. No vague hand-waving ("handle edge cases") on the hard parts.21- If you can't tie a step to your original request in one sentence, cut it.2223## 2. Step Quality2425Each step must be **specific** (exact files/functions), **atomic** (one thing), **ordered** (no forward dependencies), and **verifiable** (clear "done" condition).2627Red flags: vague steps ("clean up the code"), bundled mega-steps, assumed knowledge not in the plan.2829## 3. Dependencies & Risk3031- Steps in the right order? Hidden dependencies called out?32- What's the blast radius? Destructive actions (deletions, migrations) isolated and done last?33- If step N fails, are steps 1–(N-1) still usable?3435## 4. Verification3637- Does it start from a known state and end with a verified one?38- Every meaningful step has a *concrete* check ("run suite X, expect green" not just "run tests").39- Final end-to-end verification exists, not just step-by-step.40- Existing behavior is confirmed preserved.4142## 5. What's Missing4344- Failure handling (network errors, invalid input, partial state)45- Existing tests — will they still pass?46- Boundaries (empty states, first run, large datasets)47- Cleanup (dead code, imports, deprecations)4849## 6. Exit Criteria5051"Done" is clearly defined, independently verifiable, and ends with a concrete deliverable — not "continue improving."5253## 7. Red Flags Cheat Sheet5455| You see | It means |56|-|-|57| "Refactor/update as needed" | No plan, will improvise |58| "For completeness" / "While we're here" | Scope creep |59| Steps with no verification | Will claim success unchecked |60| New abstractions for one use case | Over-engineering |61| Touching unrelated files | Scope creep or misunderstanding |62| "Should be straightforward" | Hasn't thought it through |63| No mention of existing tests | Will break things silently |64| "We'll handle that later" | Deferring the hard part |65| "Similar to how we did X" | Assuming without verifying |66| Plan starts with code changes, not verification | Guessing, not diagnosing |