agentleFS
timohaatimohaa/scopewalker-mcp/.claude/skills/review-changes/SKILL.md

review-changes

Skill1 starsChanged 52 days agoMITView on GitHub

Review uncommitted changes and fail on unresolved Scopewalker findings or repository checks. Pass `full` for a whole-source audit.

36 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use explore-codebase, debug-issue and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • srclightSkill

    explore-codebase

    This skill should be used when the user asks to "explore this codebase", "understand this project", "give me an overview", "how does this work", "onboard me", "walk me through the architecture", "map the codebase", or any request to understand a codebase's structure, architecture, or design.

    Also in 4 projects that use this

  • NVIDIASkill

    debug-issue

    Use when the user asks to debug, investigate, or fix a GitHub issue or supplies a repository bug report.

    Also in 4 projects that use this

  • srclightSkill

    refactor-safely

    This skill should be used when the user asks to "refactor", "rename", "move", "change a function signature", "extract a method", "delete unused code", "clean up", or any modification that could break callers or dependents. Provides a pre-change safety checklist using srclight's graph tools to assess blast radius before touching code.

    Also in 4 projects that use this

  • JetBrainsSkill

    fix-bug

    End-to-end bug fix workflow for the Exposed project. Accepts a GitHub issue (#NUMBER), YouTrack issue (EXPOSED-NUMBER), or YouTrack URL (https://youtrack.jetbrains.com/issue/EXPOSED-NUMBER). Fetches the issue, creates a failing reproducer test, commits on a new branch, implements the fix, validates, and opens a PR. Use this skill whenever the user wants to fix a bug from an issue tracker, mentions a EXPOSED issue number, or references a GitHub issue to fix.

    Also in 3 projects that use this

  • SentrySkill

    write-tests

    Write tests following project conventions. Use when adding new tests or modifying existing ones.

    Also in 3 projects that use this

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read docs/code-quality.md for required scans, limits, finding dispositions, and verdicts.

    line 8
  2. Very specific:

    Use these non-fixing scripts because npm run check runs lint:fix.

    line 35
  3. Very specific:

    Run the shared Scopewalker checks for the selected scope.

    line 36
  4. Very specific:

    Search all changed source/test files in one command for unjustified eslint-disable, @ts-ignore, and console.log.

    line 45
  5. Very specific:

    Verify behavior changes have appropriate tests and tool changes update TOOLS.md and docs/.

    line 47
  6. Distinctive:

    Keep optional design suggestions separate from failures.

    line 51
  7. Distinctive:

    Do not recommend committing while required checks or actionable findings remain unresolved.

    line 58

“Common” is measured: kept by at least 6 in 10 of the 35 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review Changes

Read docs/code-quality.md for required scans, limits, finding dispositions, and verdicts. Review and report; do not refactor as part of a review.

1. Establish Scope

git status --porcelain
git diff
git diff --cached

Include staged, unstaged, and untracked files. Read new files, since diffs omit their contents. With full, audit all of src/ and run the whole-repository checks below. An empty default scope is N/A, not a whole-repository pass.

2. Run Checks

For source/test changes or full:

npm run check:versions
npm run lint
npm run typecheck
npx prettier --check src
npm run test

Use these non-fixing scripts because npm run check runs lint:fix. Run the shared Scopewalker checks for the selected scope. Inspect all in-scope findings; cross-file scans must cover src/ even when only a few files changed.

For changed Markdown, run one npx markdownlint-cli <all changed Markdown files> command and verify affected links, tool arguments, and workflow references. In full mode, include all tracked Markdown. Documentation-only changes need no source tests or code scans.

3. Review What Automation Misses

Search all changed source/test files in one command for unjustified eslint-disable, @ts-ignore, and console.log. Inspect the diff for commented-out dead code. Verify behavior changes have appropriate tests and tool changes update TOOLS.md and docs/.

Classify every Scopewalker finding using the shared dispositions. Confirmed violations are must fix, including pre-existing violations inside the selected scope. Keep optional design suggestions separate from failures.

4. Report

Give one result per check, the scope covered, and file:line details for failures. Include observed values versus limits, evidence for non-actionable findings, and explicit exceptions. End with PASS, FAIL, or BLOCKED under the shared rules. Do not recommend committing while required checks or actionable findings remain unresolved.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.