independent-review · minimax-ai — Claude Code skill: review and install
independent-review is a Claude Code skill that reviews changes from a clean context before merge. It compares the diff with the requirement and test output.
MIT ★ 741 updated 2026-11-11
/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stackWhat independent-review does
independent-review runs an outside-style review after an implementation, before merging, or when a second opinion is requested. The reviewer receives only the diff, the requirement, and real test output, leaving the author's conversation and reasoning out of scope.
It checks unchecked assumptions, requirement gaps, tests that pass without exercising the required behavior, and changes beyond the stated scope. Findings use a fixed shape: problem, location, reason, and severity. Without a requirement, the review can only check style; each finding is verified against the actual code and tests before a fix is applied.
What it helps with
- review a diff before merging
- compare an implementation with its requirement
- find unchecked null, empty-input, and error-path assumptions
- separate code defects from findings without a location or reason
- check whether passing tests exercise the requirement
Example prompts for the agent
- Review
git diff <base>...HEADagainst the requirement and the real test output, then report each finding with its location, reason, and severity. - Run an independent review of the staged changes before merge without using the author's conversation.
- Give a second opinion on this code change and check whether the tests cover the stated requirement.
How to install independent-review
1Plugin marketplace
/plugin marketplace add MiniMax-AI/mcode-stack/plugin install ronny@mcode-stackThis installs the whole ronny plugin with all its skills
2Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill independent-review -a claude-code3Manually: put the files in place
~/.claude/skills/independent-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/independent-review/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill independent-review -a codex2Manually: put the files in place
.agents/skills/independent-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill independent-review -a cursor2Manually: put the files in place
.cursor/skills/independent-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MiniMax-AI/mcode-stack stacks/ronny/skills/independent-review2Manually: put the files in place
.github/skills/independent-review/SKILL.md1Skills CLI (Vercel)
npx skills add MiniMax-AI/mcode-stack --skill independent-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/MiniMax-AI/mcode-stack --path stacks/ronny/skills/independent-reviewManually: put the files in place
.devin/skills/independent-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about independent-review
How do I install independent-review in Claude Code?
Add the marketplace with /plugin marketplace add MiniMax-AI/mcode-stack, then install the skill with /plugin install ronny@mcode-stack.
What does independent-review do?
It reviews a code change from a clean context. The review compares the diff with the requirement and test results, then reports findings with a location, reason, and severity.
What inputs does independent-review need?
It needs exactly three inputs: the diff, the requirement, and real output from the tests that were run, including failures and skipped tests. The author's conversation and self-assessment are left out.
Source text
SKILL.md · MIT
--- name: independent-review description: Review a code change from a clean context, the way an outside reviewer would. Use after the agent finishes an implementation, before merging, or when asked for an independent or second-opinion review of a diff. --- # Independent Review The agent that wrote the code has made many small decisions and convinced itself of each one. A reviewer that inherits that conversation tends to follow the same reasoning and miss the same things. This skill keeps the reviewer outside the author's context. Companion to MCode Engineering Notes 01, "More subagents isn't better". ## 1. Give the reviewer exactly three inputs Collect these, and nothing else: 1. **The diff.** For example `git diff <base>...HEAD`, or the staged changes. 2. **The requirement.** The issue, spec, task description or acceptance criteria the change is supposed to satisfy. 3. **Test results.** The commands that were run and their real output, including failures and skipped tests. Do **not** pass the author's conversation, plan, intermediate reasoning or self-assessment. The question the reviewer answers is "does this change meet the requirement?", not "does the author's reasoning hold up?". If the requirement is missing, stop and ask for it. A review without a requirement can only check style. ## 2. Run the review in a fresh context Prefer one of these, in order: - A subagent or task started with only the three inputs above. This is a black-box check with a clean boundary and a compact result, which is the kind of split that is worth a subagent. - A built-in review command or skill, if your agent has one, started in a new session. - A new session in which you paste the three inputs. Ask the reviewer to look in particular for: - Assumptions the code relies on but does not check (null or empty input, callers that "already validate", ordering, concurrency, error paths). - Requirement items that the diff does not cover. - Tests that pass without actually exercising the requirement. Tests written by the same agent share its blind spots, so check whether they cover the requirement, not only whether they pass. - Behaviour changes outside the stated scope. ## 3. Get findings back in a fixed structure Each finding must have: | Field | Content | | --- | --- | | Problem | What is wrong, in one or two sentences | | Location | File and line or function | | Reason | Why it is wrong, tied to the requirement or to concrete code | | Severity | blocking / should-fix / nit | Findings without a location or a reason are treated as opinions, not defects. ## 4. Verify before fixing Back in the main loop, do not apply findings wholesale. For each one: 1. Open the real code at the stated location. 2. Confirm the problem exists, ideally with a failing test or a concrete input. 3. Only then fix it, and rerun the relevant tests. 4. Record findings you rejected and why, so the next review does not raise them again. ## Output End with a short summary: findings confirmed and fixed, findings rejected (with the reason), and anything still open.
© Ronny (MiniMax Code team) · MIT · MiniMax-AI/mcode-stack
Similar skills
All skills for Code review and refactoring →independent-review by other authors comes first.