agentleFS
ArangoGutierrezArangoGutierrez/claude-toolkit/.claude/skills/go-review/SKILL.md

go-review

Skill4 starsChanged 3 months agoMITView on GitHub

Go-specific code review — errors, concurrency, performance, idioms. Triggered by "review Go code", "Go best practices", or /go-review

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When invoked by the pr-review dispatcher, the reviewer reads references/go-review-checklist.md, reviews ONLY the changed lines in the PR …

    line 35
  2. Distinctive:

    Don't flag style that gofmt/golangci-lint handles

    line 49
  3. Distinctive:

    Don't suggest premature optimization

    line 50
  4. Distinctive:

    Don't redesign architecture during review

    line 51

“Common” is measured: kept by at least 6 in 10 of the 4 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

Go Review

Systematic Go code review. Only flags correctness, performance, and maintainability — not style.

Process

  1. Static analysis:

    golangci-lint run --new-from-rev=HEAD~1 ./...
  2. Walk checklist (see references/go-review-checklist.md):
    • Error handling, concurrency, performance, interfaces
  3. Report findings:
    • file:line for each issue
    • Category: correctness / performance / maintainability
    • Severity: must-fix / should-fix / consider
    • Suggested fix (code snippet)

Dispatched mode (pr-review integration)

When invoked by the pr-review dispatcher, the reviewer reads references/go-review-checklist.md, reviews ONLY the changed lines in the PR diff, and returns a findings list where each finding has: file (repo-relative path), line (NEW-file/RIGHT-side line number), a 1–2 sentence description, category (correctness / performance / maintainability), severity (must-fix / should-fix / consider), and reason (which checklist item flagged it). Take no external action of any kind in dispatched mode — findings are returned as data.

Scope

Changed files only unless explicitly asked for full package review.

Gotchas

  • Don't flag style that gofmt/golangci-lint handles
  • Don't suggest premature optimization
  • Don't redesign architecture during review
  • Respect existing patterns

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.