Review code fix

Skill cloverink/shipwright/skills/review-code-fix

Automated code review → fix → re-review loop. Runs until score >9 or max 3 rounds. Fixes Critical/Major/Warnings only — Suggestions are deferred.From its SKILL.md

Install

npx -y skills add cloverink/shipwright --skill review-code-fix

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.5 KB, 597 tokens by cl100k_base, as published. Nobody here has run it

/review-code-fix

Iterative review-fix loop that keeps going until your code passes the quality bar.

When to use: Code-only review when you want to skip auto-scope-detection (backend-only PR, library code). Use /review-full instead if: your diff has frontend changes — it'll dispatch to UX review too. Called by: /review-full (auto-dispatched on code diffs — /ship Phase R reaches this transitively).

How it works

Round 1: Review → list issues → fix Critical/Major/Warning → re-review
Round 2: Review again → fix remaining → re-review
Round 3: Final attempt → fix → final review
         If still failing → report to user with remaining issues

Score Gate

The pass threshold is strictly greater than 9:

Score	Result
10	Pass
9.5	Pass
9.0	Fail
8.5	Fail

A 9.0 means at least one Major issue or two Warnings remain. That's not ship-ready.

Severity Levels

Severity	Score impact	Auto-fixed?
Critical (-3)	Security, data loss, broken build	Yes
Major (-1)	Bug, perf regression, missing tests	Yes
Warning (-0.5, max -2)	Convention violations	Yes
Suggestion (0)	Style preference, naming nits	No

Fix Strategy

Fixes are applied by scope to avoid conflicts:

Group issues by file/directory
Fix each group
Run lint + typecheck after each batch
Re-review only after all fixes pass

Review Focus

Type safety — no any, proper null handling, explicit returns
Security — no secrets, input validation, injection prevention
Performance — N+1 queries, missing indexes, bundle size
Testing — coverage on changed code paths
Conventions — naming, imports, file organization

Output Format

Summary: 1-3 sentences
Issues:
  - [Critical] [file:line] description
  - [Major] [file:line] description
  - [Warning] [file:line] description
  - [Suggestion] [file:line] description (not auto-fixed)
Score: X/10

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most code review skills give in 597 tokens

Counted across 668 of the 814 authors here whose files we hold, read 2026-09-06

Provide technical reasoning when pushing backin 84 of 668, across 70 files
Fix critical issues immediatelyin 77 of 668, across 60 files
Dispatch a code reviewer subagentin 76 of 668, across 59 files
Fix important issues before proceedingin 73 of 668, across 56 files
Ask for clarification on unclear itemsin 68 of 668, across 56 files
Verify feedback against codebase before implementationin 66 of 668, across 55 files
Implement fixes one at a timein 64 of 668, across 53 files
Test each fix individuallyin 62 of 668, across 51 files
Restate technical requirements in own wordsin 57 of 668, across 46 files
Reply to inline comments in the specific threadin 51 of 668, across 40 files
Note minor issues for laterin 49 of 668, across 34 files
Group findings by severityin 48 of 668, across 47 files

Said here and by no other author read

Review code for type safety and security
Group issues by file or directory
Fix Critical Major and Warning issues
Run lint and typecheck after each batch
Re-review code after all fixes
Repeat loop until score exceeds nine

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.