How do I install the Review Change skill?

Run npx skillmds@latest add kunalsuri/review-change-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Review Change safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Change?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Change free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Review Change?

kunalsuri (@kunalsuri) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Change by kunalsuri — Agent Skill

Name: Review Change
Author: kunalsuri

Review Change

Review a completed change against its authorizing spec in fresh context — evidence-based checks, severity-ranked findings, and a written verdict for the human's merge decision. Use when a diff needs reviewing before merge, or when add-feature / fix-bug / implement-spec reaches its review gate.

kunalsuri Updated Sep 17, 2026

File contents

Review a change

The contract: review in a session that did NOT write the change; check with evidence, not assertions; re-run the suites yourself; the written verdict is the deliverable — the human merges, not you.

1. Fresh-context gate

A reviewer sharing the implementer's context inherits the implementer's blind spots. If this session wrote the change, stop and hand the review to a fresh session that did not implement it.

2. Pin the scope

Identify the exact diff (commits / branch / files) and the spec or bugfix doc in ai/lab/specs/ that authorized it. No spec ⇒ that is finding #1, severity blocker: unspecced work.

3. Open the review

Copy ai/lab/reviews/REVIEW_TEMPLATE.md → ai/lab/reviews/REVIEW_<work-id>.md.

4. Check with evidence

For each check in the template — spec conformance, surgical diff, Stability respected, tests, conventions, knowledge updated, provenance clean — record where you looked and what you saw. Delegate the suite re-run to test-runner: run the suites the spec names yourself; do not trust the implementer's report.

5. File findings by severity

Any blocker or major ⇒ verdict request-changes; hand the list back to the implementer. Minor / nit findings can ship with notes.

6. Verdict and hand-off

Fill "what the human should double-check" — the judgement calls a mechanical check cannot make. The review itself is [inferred]; the human's merge decision is the real approval, and this document is its evidence.

7. Record

Link the review from the work's row in ai/lab/WORKLOG.md (Review column) and set that row's Status to in-review.

---name: review-change-2description: Review a completed change against its authorizing spec in fresh context — evidence-based checks, severity-ranked findings, and a written verdict for the human's merge decision. Use when a diff needs reviewing before merge, or when add-feature / fix-bug / implement-spec reaches its review gate.---# Review a changeThe contract: **review in a session that did NOT write the change; check withevidence, not assertions; re-run the suites yourself; the written verdict is thedeliverable — the human merges, not you.**## 1. Fresh-context gateA reviewer sharing the implementer's context inherits the implementer's blindspots. If this session wrote the change, stop and hand the review to a freshsession that did not implement it.## 2. Pin the scopeIdentify the exact diff (commits / branch / files) and the spec or bugfix doc in`ai/lab/specs/` that authorized it. No spec ⇒ that is finding #1, severity blocker:unspecced work.## 3. Open the reviewCopy `ai/lab/reviews/REVIEW_TEMPLATE.md` → `ai/lab/reviews/REVIEW_<work-id>.md`.## 4. Check with evidenceFor each check in the template — spec conformance, surgical diff, Stabilityrespected, tests, conventions, knowledge updated, provenance clean — record whereyou looked and what you saw. Delegate the suite re-run to `test-runner`: run thesuites the spec names yourself; do not trust the implementer's report.## 5. File findings by severityAny blocker or major ⇒ verdict `request-changes`; hand the list back to theimplementer. Minor / nit findings can ship with notes.## 6. Verdict and hand-offFill "what the human should double-check" — the judgement calls a mechanical checkcannot make. The review itself is `[inferred]`; the human's merge decision is thereal approval, and this document is its evidence.## 7. RecordLink the review from the work's row in `ai/lab/WORKLOG.md` (Review column) and setthat row's Status to `in-review`.

Frequently asked questions