agentleFS
Sign inStart free
openparallaxopenparallax/skills/developer/SKILL.md

developer

Skill0 starsChanged 7 months agoApache-2.0View on GitHub

Code review, debugging methodology, testing patterns, and PR workflow for software development tasks

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. github/gh-aw★ 5.6ksame name
    2. sgomez/developer-skills★ 8same name
    3. TeleginS/agent-orchestration★ 6same name
    4. KJ-devs/setupClaudeCode★ 2same name
    5. Satori28/free-skills★ 2same name
    6. nathan-vm/subforge-mcp★ 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

12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 10

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    When reviewing code, check in this order:

    line 8
  2. Distinctive:

    Follow this sequence. Do not skip steps.

    line 20
  3. Distinctive:

    Verify: Test the hypothesis with the minimum possible change.

    line 25
  4. Distinctive:

    Never guess. Read the error message.

    line 29
  5. Distinctive:

    Test behavior, not implementation.

    line 34
  6. Very specific:

    Use descriptive names: TestUserCreation_DuplicateEmail_ReturnsConflict not TestUser2.

    line 35
  7. Distinctive:

    Before opening a PR:

    line 44
  8. Distinctive:

    Run the full test suite. Fix failures before pushing.

    line 46
  9. Distinctive:

    Write a description that explains WHY, not WHAT.

    line 48
  10. Very specific:

    Commit messages: type: description (feat, fix, refactor, test, chore, docs).

    line 52
  11. Distinctive:

    When proposing architectural changes:

    line 56
  12. Distinctive:

    Keep it simple. Three similar lines beat a premature abstraction.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 3 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

Code Review

When reviewing code, check in this order:

  1. Correctness: Does it do what it claims? Edge cases handled?
  2. Security: Input validation, injection risks, secret exposure, OWASP top 10
  3. Performance: N+1 queries, unnecessary allocations, missing indexes, unbounded loops
  4. Readability: Clear naming, single-responsibility functions, no clever tricks
  5. Tests: Are new paths covered? Are assertions meaningful (not just assert true)?

Flag issues by severity: blocking (must fix), warning (should fix), nit (style preference).

Debugging Methodology

Follow this sequence. Do not skip steps.

  1. Reproduce: Get a reliable repro before touching code. Document exact steps.
  2. Isolate: Binary search the problem space. Comment out code, add logging, narrow scope.
  3. Hypothesize: Form a specific theory before changing code. "I think X causes Y because Z."
  4. Verify: Test the hypothesis with the minimum possible change.
  5. Fix: Apply the real fix. Do not leave debug artifacts (print statements, commented code).
  6. Regression test: Add a test that would have caught this bug.

Never guess. Read the error message. Read the stack trace. Read the docs.

Testing Patterns

Write tests that:

  • Test behavior, not implementation. If you refactor internals, tests should still pass.
  • Use descriptive names: TestUserCreation_DuplicateEmail_ReturnsConflict not TestUser2.
  • Set up their own state. No test should depend on another test's side effects.
  • Assert specific values. assert.Equal(t, 3, len(items)) not assert.True(t, len(items) > 0).
  • Cover the sad path. Error handling code has bugs too.

For integration tests: use real databases, real filesystems. Mocks hide bugs at boundaries.

PR Workflow

Before opening a PR:

  • Rebase on main. Resolve conflicts locally.
  • Run the full test suite. Fix failures before pushing.
  • Self-review the diff. Read every line as if someone else wrote it.
  • Write a description that explains WHY, not WHAT. The diff shows what changed.

PR size: Under 400 lines of meaningful changes. Split larger work into stacked PRs.

Commit messages: type: description (feat, fix, refactor, test, chore, docs). Present tense, no period. The message should complete the sentence "This commit will..."

Architecture Decisions

When proposing architectural changes:

  • State the problem clearly before proposing solutions
  • List alternatives you considered and why you rejected them
  • Identify the tradeoffs of your chosen approach
  • Define how you would reverse the decision if it turns out wrong
  • Keep it simple. Three similar lines beat a premature abstraction.

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.

Check your setup, free