agentleFS
malinskibeniaminmalinskibeniamin/skills/golang-review/SKILL.md

golang-review

Skill4 starsChanged 5 days agoMITView on GitHub

Review Go against evidence-backed rules for bounds, APIs, concurrency, errors, security, tests, and rollout. Use for Go diffs, PRs, branches, modules, or backend protos.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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
  1. Very specific:

    Run standalone or inline as the golang hat in /review.

    line 8
  2. Very specific:

    Only diff-introduced, user-impacting, actionable, PR-ready findings: What, catalog/contract-backed Why, Suggested fix, One-shot prompt.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Review one axis: whether a Go diff follows RULES.md and applicable language contracts. Catalog rules carry aggregate support; version findings cite /golang official contracts, not taste.

Run standalone or inline as the golang hat in /review. Reviewer lanes still require explicit delegation or /swarm.

Exclude

  • Anything target golangci-lint config already enforces.
  • Generic style without catalog/version-contract backing.
  • Frontend, vendored, and generated *.pb.go, *_pb.go, *.connect.go, @generated/DO NOT EDIT.
  • Catalog debate; submit feedback rather than invert a rule.

Procedure

  1. Scope: diff fixed point to HEAD. Inspect Go/proto plus go.mod/go.work when toolchain may change. Read .golangci.yml; exclude enabled lint rules.
  2. Classify: proto/API, public SDK/library, handlers, Temporal, controllers, tests, config/rollout, tenant security, concurrency/lifecycle.
  3. Load: matching RULES.md and /golang domain files: PROTO-API, CONCURRENCY, ERRORS, TESTING, TEMPORAL, SECURITY, ROLLOUT, STRUCTURE, CONTROLLERS. For Go 1.27 generic methods, compatibility, or leak profiling, load GO-1.27.md. Apply in-scope S/A rules, clear B violations, and only plain C/D violations; gate release contracts by module version/surface.
  4. Check tensions: positive bool versus fail-closed, enum subset, keepalive, filters. Context decides.
  5. Report: rule/contract id, file:line, behavior, required change, priority. Hat limit 400 words; standalone stays concise and sourced.

Severity

  • P0: fail-open security, unsafe tenant egress, plaintext secret, progress before durable processing, unversioned live-Temporal break.
  • P1: other S/A violation: unbounded tenant growth, raw public errors, missing staged removal, mocked integration claim, or Go 1.27 syntax above supported floor.
  • P2: B violation; judgment-call S/A; generic-method interface/reflection conflict; clean leak profile claimed as proof.
  • P3: C/D wording/polish.

Confirmed bugs remain P0/P1 regardless of effort.

Output

Only diff-introduced, user-impacting, actionable, PR-ready findings: What, catalog/contract-backed Why, Suggested fix, One-shot prompt. If clean: APPROVED -- <domains checked>, no catalog or version-contract violations.

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.