golang-skills
AGENTS.md7 starsChanged 9 days agoApache-2.0View on GitHub
This repository packages Go-focused Agent Skills; it is not a Go application and has no root go.mod. Run these from the repository root: The first command is the CI structural suite, including the Agent Skills frontmatter check in TestStructure; the others validate shell syntax and the pinned lint configuration. Model-driven runs are opt-in and costly: cd evals && go run ./cmd/evalrun -set validation -kind all -j 2 -out evals-results.json. Write decision-oriented Markdown. Keep each SKILL.md at 400 lines or fewer…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- go-code-refactorSkill
- go-code-reviewSkill
- go-codeSkill
- go-concurrencySkill
- go-contextSkill
- go-databaseSkill
- go-data-structuresSkill
- go-defensiveSkill
- go-documentationSkill
- go-error-handlingSkill
- go-functionsSkill
- go-genericsSkill
- go-httpSkill
- go-interfacesSkill
- go-lintingSkill
- go-loggingSkill
- go-namingSkill
- go-packagesSkill
- go-performanceSkill
- go-resilienceSkill
- go-securitySkill
- go-style-coreSkill
- go-testingSkill
- go-troubleshootingSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 14
Run these from the repository root:
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.
Files
Repository Guidelines
Project Structure & Module Organization
This repository packages Go-focused Agent Skills; it is not a Go application and has no root go.mod.
skills/go-*/: runtime skills. Keep eachSKILL.mdwith its optionalreferences/,scripts/, andassets/.evals/: the only Go module; contains structural tests, fixtures, golden cases, and theevalrun/abrunrunners.hooks/andagents/: Claude Code routing, post-edit hooks, and the optionalgo-verifyagent.docs/: authoring, ownership, script-contract, and release policy.source/contains licensed upstream snapshots and is not edited.
Build, Test, and Development Commands
Run these from the repository root:
(cd evals && go test -count=1 -race -shuffle=on ./...)
bash -n hooks/*.sh
golangci-lint config verify --config skills/go-linting/assets/golangci.ymlThe first command is the CI structural suite, including the Agent Skills frontmatter check in TestStructure; the others validate shell syntax and the pinned lint configuration. Model-driven runs are opt-in and costly: cd evals && go run ./cmd/evalrun -set validation -kind all -j 2 -out evals-results.json.
Coding Style & Naming Conventions
Write decision-oriented Markdown. Keep each SKILL.md at 400 lines or fewer and references at 300 or fewer. Route every bundled resource in ## Resource Routing, use relative links, and assign each rule one owner in docs/RULE_OWNERSHIP.md. Go examples must be formatted and compilable; target Go 1.27 with 1.26 and 1.27 supported. Use gofmt for Go and portable Bash for hooks and scripts.
Testing Guidelines
Put structural tests in evals/*_test.go with descriptive Test... names. Update fixtures and golden cases when changing scripts, hooks, routing, manifest counts, or example behavior. Run a focused subtest while iterating, then the full race-enabled suite before opening a PR. Keep model-run reports and traces outside the repository.
Commit & Pull Request Guidelines
Use the history’s scoped conventional style, such as feat(go-http): ..., fix(hooks): ..., docs: ..., or release: 1.21.2. Keep commits focused. PRs should explain intent, list affected files, record validation commands and baseline failures, update CHANGELOG.md under ## [Unreleased] for user-visible changes, and update README/manifests when resource counts or versions change. For releases, follow docs/RELEASE_CHECKLIST.md; do not bump versions for ordinary PRs.
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
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.