agentleFS
ValueMelodyValueMelody/melody-auth/.claude/skills/review-feature/SKILL.md

review-feature

Skill649 starsChanged 8 months agoMITView on GitHub

Use this skill whenever the user asks for a feature-focused review of the current in-progress work, uncommitted changes, staged diff, or worktree. Trigger on requests like "review this feature", "review the current diff", "what is missing feature-wise", "is anything missing before this ships", or "check the uncommitted changes and only focus on feature behavior". Do not use this skill for style, refactoring, performance, or test review.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. parthsidpara/lazyskills★ 1same name
    2. 0xdeafcafe/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the changed files and any nearby code needed to understand the intended behavior.

    line 25
  2. Distinctive:

    If the user provided extra context, use it to infer the expected feature scope.

    line 26
  3. Distinctive:

    If there are no uncommitted changes, say so clearly and stop.

    line 27
  4. Distinctive:

    Start with findings only, ordered by severity

    line 39
  5. Distinctive:

    Never mention tests, missing tests, or test quality

    line 41
  6. Very specific:

    If no feature-level gaps are found, say exactly: No feature-level gaps found in the current uncommitted changes.

    line 42
  7. Very specific:

    Add a short Open questions section only if needed

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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 Feature

Review the current uncommitted changes as a feature review.

Scope

  • Focus only on feature completeness and product behavior.
  • Ignore tests and test quality completely.
  • Ignore style, formatting, naming, refactoring, and performance unless they directly break the feature.

Step 1: Inspect the current work

  1. Run git status --short.
  2. Review both staged and unstaged diffs.
  3. Read the changed files and any nearby code needed to understand the intended behavior.
  4. If the user provided extra context, use it to infer the expected feature scope.
  5. If there are no uncommitted changes, say so clearly and stop.

What to look for

  • Missing frontend, backend, API, or data wiring
  • Missing validation, authorization, persistence, schema, or route updates
  • Missing loading, empty, success, or error states that break the feature flow
  • Missing translations, generated artifacts, or docs only when they are required for the feature to ship
  • Edge cases or regressions that make the feature incomplete for real users

Response format

  • Start with findings only, ordered by severity
  • For each finding, explain why it matters for feature behavior and cite file paths with line numbers
  • Never mention tests, missing tests, or test quality
  • If no feature-level gaps are found, say exactly: No feature-level gaps found in the current uncommitted changes.
  • Add a short Open questions section only if needed

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.