agentleFS
aman-bhandariaman-bhandari/claude-code-agent-skills-framework/.claude/skills/code-review/SKILL.md

code-reviewing

Skill0 starsChanged 7 months agoMITView on GitHub

Deep coach-style code review of code the student wrote. Triggers on /review or REVIEW prefix. Checks understanding first (why decisions were made), then correctness, then all standards (type hints, error handling, no print, meaningful names, docstrings, edge cases), then production thinking. Never rewrites code -- points to problems, the student fixes them.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-writing, infrastructure-setup and 2 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.
  • stepanenkoviktor0110-boopSkill

    code-writing

    Universal quality coding process: plan, TDD, reviews. Use whenever code needs to be written — ad-hoc or as part of a task.

    Also in 3 projects that use this

  • stepanenkoviktor0110-boopSkill

    infrastructure-setup

    Sets up dev infrastructure for new projects: framework init, folder structure, Docker, pre-commit hooks (gitleaks), testing infrastructure, .gitignore.

    Also in 3 projects that use this

  • nilecuiSkill

    documentation-writing

    Writing clear, discoverable software documentation following the Eight Rules and Diataxis framework. Use when creating README files, API docs, tutorials, how-to guides, or any project documentation. Automatically enforces docs/ location, linking requirements, and runnable examples.

    Also in 3 projects that use this

  • +1 more from stepanenkoviktor0110-boop

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not just correctness. Understanding, production-readiness, and growth.

    line 8
  2. Distinctive:

    After the student says they're done with an exercise

    line 13
  3. Distinctive:

    If the student can't explain their own code → stop.

    line 23
  4. Distinctive:

    Do tests cover happy path, edge case, and error case?

    line 27
  5. Distinctive:

    Do all tests pass?

    line 28
  6. Distinctive:

    If a concept or pattern emerged worth preserving → suggest brainstorm into wiki

    line 54
  7. Distinctive:

    Never rewrite code. Point to the problem, the student fixes it.

    line 58
  8. Distinctive:

    Ask WHY before saying WHAT's wrong.

    line 59
  9. Distinctive:

    If the same mistake appears twice across sessions, escalate: "This is a pattern.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 6 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 -- Coach Mode

Not just correctness. Understanding, production-readiness, and growth.

Trigger

  • /review or REVIEW: prefix
  • After the student says they're done with an exercise

Execution

  1. Read the file the student wants reviewed.
  2. Understanding check (always first -- before looking at code quality):
    • "Walk me through what this code does, line by line."
    • "Why did you choose [specific pattern]?"
    • "What happens if [edge case]?"
    • If the student can't explain their own code → stop. Understanding first, review second.
  3. TDD compliance:
    • Does test_*.py exist? Were tests written FIRST?
    • Do tests cover happy path, edge case, and error case?
    • Do all tests pass?
  4. Correctness:
    • Does it run? Expected output?
    • Edge cases handled?
    • Error paths covered?
  5. Standards compliance (ALL enforced, always):
    • Type hints on every function signature
    • Proper error handling (never bare except, catch specific exceptions)
    • No print() statements (use logging or structlog)
    • Meaningful variable names (not x, data, result, temp)
    • Docstrings on public functions
    • Edge cases considered and handled
  6. Production thinking:
    • "What breaks if the input is 10x larger?"
    • "What happens when the network/filesystem is unavailable?"
    • "How would you test this?"
    • "Where would you add monitoring?"
  7. Feedback format:
    • 1-2 things done well (specific, not generic praise)
    • 1-2 things to improve (specific line references)
    • 1 challenge question (pushes thinking deeper)
    • Concepts to add to spaced review deck
    • If a concept or pattern emerged worth preserving → suggest brainstorm into wiki

Rules

  • Never rewrite code. Point to the problem, the student fixes it.
  • Ask WHY before saying WHAT's wrong. Understanding > correctness.
  • If the same mistake appears twice across sessions, escalate: "This is a pattern. What's the root cause?"
  • Connect feedback to production and market: "An interviewer would flag this."

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.