agentleFS
hegeldevhegeldev/hegel-rust/.claude/skills/self-review/SKILL.md

self-review

Skill400 starsChanged 35 days agoMITView on GitHub

Review your own changes before creating a pull request. Use this before running create-pr, or whenever you want to check that your changes are clean, correct, and well-tested. Trigger when: about to create a PR, finished a chunk of work, or asked to review changes.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use latex-formatting, novelty-assessment 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.
  • lingzhi227Skill

    latex-formatting

    Handle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage packages, and ensure venue-specific compliance. Use when the user needs to set up a paper template, fix LaTeX formatting, or prepare for submission.

    Also in 4 projects that use this

  • lingzhi227Skill

    novelty-assessment

    Assess research idea novelty through systematic literature search. Multi-round search-evaluate loops with harsh critic persona. Binary novel/not-novel decision with justification. Use before committing to a research direction.

    Also in 4 projects that use this

  • michaelboedingSkill

    slide-generation

    Use this skill to create presentation slides from structured content. Triggers: "create slides", "generate presentation", "make powerpoint", "create pptx", "build slides", "presentation from content", "slide deck", "slides for" Outputs: PPTX files, Markdown slides, or HTML presentations. Used by: pitch-deck-agent, market-researcher-agent, and other agents needing slides.

    Also in 4 projects that use this

  • FracteraSkill

    ask-element

    Work skill. The architect wants an element of this node to check or find out something and you to bring the answer («попроси template проверить …», «узнай у auth …»), or wants you to start or close an element's agent yourself. Also when «агент элемента … сообщил, что закончил (надзор …)» wakes you after such a task.

    Also in 3 projects that use this

  • FracteraSkill

    audit-broken-characters

    Scan the whole project for BROKEN / REPLACEMENT characters in localized text — a control byte (e.g. 0x13) or U+FFFD or mojibake left where an accented letter belonged, which renders as a box (e.g. "Documentación" showing "Documentaci□n"). Use when the owner reports a square / wrong glyph in the UI or content, says "broken character", "weird symbol", "mojibake", "validate encoding", or after authoring multilingual content and before closing a content step. It SHIPS SILENTLY (the file still parses), so run the audit to catch it. One project-root script, nothing external needed.

    Also in 3 projects that use this

  • +5 more from lingzhi227
  • +2 more from Fractera

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Run through these checks before creating a PR or declaring work complete.

    line 8
  2. Distinctive:

    Run all of these — they're fast and catch the most common issues:

    line 12
  3. Very specific:

    Run git diff origin/main...HEAD and read through it.

    line 22
  4. Very specific:

    If cargo-llvm-cov is available, run just check-coverage and review the output.

    line 33
  5. Distinctive:

    Ask yourself: if someone else wrote this diff, what would I flag in code review?

    line 37

“Common” is measured: kept by at least 6 in 10 of the 44 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

Self-Review

Run through these checks before creating a PR or declaring work complete. The goal is to catch the things a human reviewer would flag, before they have to.

Mechanical checks

Run all of these — they're fast and catch the most common issues:

just check   # formatting, lint, tests, docs

Fix any failures before proceeding. Don't skip checks because they passed locally last time — the code may have changed.

Review the diff

Run git diff origin/main...HEAD and read through it. Look for:

  • Dead code: unused imports, variables, functions that were left behind during refactoring.
  • Redundant test logic: tests that just mirror the implementation (e.g., a test with the same match arms as the code it's testing). Good tests validate against external reality or test behavior, not structure. If a test would still pass after introducing a bug in the code, it's not testing anything useful.
  • Network calls in tests: can any test that hits the network use file:// URLs or local fixtures instead? Keep at most one integration test that verifies the real network path works.
  • Hardcoded paths: /tmp/foo in tests should be tempfile::tempdir() for isolation and cleanup.
  • Missing error context: error messages should help the user fix the problem (e.g., include "Install X manually: <url>").
  • New // nocov annotations: each one needs explicit human permission. Your first instinct should be to write a test or refactor for testability instead.

Coverage check

If cargo-llvm-cov is available, run just check-coverage and review the output. If new code is uncovered, address it before the PR — don't rely on CI to catch it. See the coverage skill for how to approach coverage gaps.

Final gut check

Ask yourself: if someone else wrote this diff, what would I flag in code review? Common things to catch:

  • Functions that panic where they should return errors (or vice versa)
  • Thin wrapper functions that exist only for testability but aren't actually tested
  • Comments that describe what the code does rather than why

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.