agentleFS
Sign inStart free
axomiyaindieaxomiyaindie/agent-skills-playbook/skills/code-review-hawk/SKILL.md

code-review-hawk

Skill0 starsChanged 5 days agoMITView on GitHub

Version: 0.1.0 Applies to: Coding agents Trigger: Load when the agent is asked to review a diff, pull request, or code snippet.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the full diff before commenting.

    line 12
  2. Distinctive:

    Never comment on formatting that a linter handles.

    line 20
  3. Distinctive:

    Never suggest a rewrite when a targeted fix works.

    line 21
  4. Distinctive:

    Do not approve code with unresolved High issues.

    line 22
  5. Distinctive:

    Do not invent issues to appear thorough.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Code Review Hawk

Version: 0.1.0 Applies to: Coding agents Trigger: Load when the agent is asked to review a diff, pull request, or code snippet.

Goal

Produce a structured, severity-ranked review that catches real issues without nitpicking style.

Instructions

  1. Read the full diff before commenting.
  2. Classify each issue by severity: High (bug, security, data loss), Medium (performance, maintainability), Low (style, naming).
  3. For each High issue, include the failure scenario: what input causes what failure.
  4. For each issue, include a concrete fix, not a vague suggestion.
  5. Skip pure style issues unless they affect readability of complex logic.
  6. Summarize: count of High, Medium, Low, and a one-line verdict.

Constraints

  • Never comment on formatting that a linter handles.
  • Never suggest a rewrite when a targeted fix works.
  • Do not approve code with unresolved High issues.
  • Do not invent issues to appear thorough.

Expected Output

  • Verdict: approve / request changes.
  • High: list with failure scenario and fix.
  • Medium: list with fix.
  • Low: list, optional.
  • Summary: counts and one-line verdict.

Example

Input: A diff adding a database query with a string-concatenated filter. Behavior: The agent flags High (SQL injection), gives the failure scenario, and suggests a parameterized query. Output: Verdict request changes, one High with scenario and fix.

Notes

Pair with the security-pass skill for security-sensitive diffs.

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