agentleFS
y-miyazakiy-miyazaki/config/.claude/skills/go-review/SKILL.md

go-review

Skill1 starsChanged 3 days agoApache-2.0View on GitHub

Review Go code for security, correctness, and maintainability. Use when reviewing Go PRs requiring judgment beyond automated checks.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use typescript-review.

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.
  • samsam007bSkill

    typescript-review

    TypeScript & code quality audit: strict mode, explicit types, no-any, SOLID patterns, Clean Code naming. Sources: Martin Fowler, Google Engineering Practices, Microsoft TypeScript Handbook.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    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. Distinctive:

    Do not modify code files or approve/merge PRs

    line 27
  2. Very specific:

    run formatting/lint/test/vulnerability command pipelines (gofumpt, go vet, golangci-lint, go test, govulncheck)

    line 38
  3. Distinctive:

    Read PR context and change intent.

    line 63

“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

Input

  • Go files and PR context or file diffs (required); for ad-hoc file review without a PR, the Go files alone
  • Validation output from the companion go-validation report or CI (optional): used to skip tool-detectable checks

Output Specification

Return structured Markdown in accordance with references/common-output-format.md. That file is the source of truth for the output contract.

Each issue must include file path with line reference (<path>#L<line>), risk summary, and remediation guidance.

Execution Scope

  • Systematically apply review checklist from references/common-checklist.md
  • Focus on checks requiring human/AI judgment (design, concurrency, security patterns)
  • Do not modify code files or approve/merge PRs

USE FOR:

  • review Go PRs where .go files are in the changeset
  • assess design, security, and concurrency risks not covered by static checks
  • perform risk-focused review on multi-package changes
  • ad-hoc review of Go source files outside a PR context

DO NOT USE FOR:

  • run formatting/lint/test/vulnerability command pipelines (gofumpt, go vet, golangci-lint, go test, govulncheck)
  • implement code fixes directly
  • changesets containing only non-Go files (e.g., docs-only, CI config-only)

Reference Files Guide

  • common-checklist.md (always read)
  • common-output-format.md (always read)
  • common-troubleshooting.md (read on failure)
  • category-global.md (always read)
  • category-security.md (always read)
  • category-concurrency.md (always read)
  • category-error-handling.md (always read)
  • category-anti-patterns.md (always read)
  • category-architecture.md (always read)
  • category-code-standards.md (always read)
  • category-context.md (always read)
  • category-dependencies.md (always read)
  • category-documentation.md (always read)
  • category-function-design.md (always read)
  • category-testing.md (always read)
  • category-test-anti-patterns.md (always read)

Workflow

  1. Read PR context and change intent. If PR context is unavailable, review file diffs only and defer PR-context-dependent checks.
  2. Scope findings to changed files and hunks. Report violations in unchanged code outside the diff only under ## Expert Assessment, not ## Issues. For ad-hoc file review without a diff, treat the whole file as in scope.
  3. Exclude generated files and vendored third-party code (for example vendor/) from primary findings unless they introduce security-critical risk.
  4. For very large PRs (>50 changed Go files), prioritize security/correctness checks first and defer low-risk style checks if evidence is insufficient.
  5. When validation output (companion go-validation report or equivalent CI results) is supplied, do not re-report failures those tools detect: take the overlapping ItemID's status from the tool result, cite the tool, and spend the review on judgment checks. Category items with a validation Note: name the known overlaps.
  6. Apply the full review checklist and collect failed/deferred ItemIDs.
  7. Output required report sections per references/common-output-format.md. Prioritize SEC-* findings first.

Severity and Status Rules

StatusWhen to use
FailedFinding is confirmed from source code with concrete evidence (file + line)
DeferredCheck cannot be evaluated — file too large to fully analyze, or ambiguous without runtime context
PassedCheck evaluated and no issue found (counted in summary only)

Severity priority for Issues section ordering: SEC-* > CON-* > ERR-* > all others.

Error Handling

ConditionSeverityAction
common-checklist.md unavailableFatalStop, report missing dependency
common-output-format.md unavailableRecoverableNote missing file; emit ## Checks Summary, ## Checks (Failed/Deferred Only), and ## Issues only
PR contains only generated/vendor filesRecoverableReport "no reviewable Go source" and stop

Examples

  • Prompt: Review Go code changes for design and correctness
  • Result: Structured report per references/common-output-format.md; prioritize SEC-* findings.

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.