cc-skills-golang: Agent Skills for Production-Ready Go
A curated, human-reviewed collection of Golang agentic skills covering code style, testing, security, performance, and more, ready for any compatible AI coding assistant.
- Source repo
- samber/cc-skills-golang
- Stars
- ★ 3.5k
- Last updated
- 17d ago
- License
- MIT
- Primary language
- Go
- FA score
- 35/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformChatGPT · Codex · Claude Code
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A Go developer using Claude Code needs to ensure new code follows idiomatic style and error-handling conventions; the assistant loads golang-code-style and golang-error-handling skills.
- Not a fit if
- Teams with their own Go conventions unwilling to maintain override skills
- Non-Go developers needing git, CI/CD or PR-review workflow skills
- Source review
- 35/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
cc-skills-golang is a repository of AI agent skills specifically for Go development. It includes around 30 atomic skills grouped into categories like Code Quality, Architecture & Design, QA & Performance, Project Setup, APIs, Dependency Injection, Frameworks, samber/* libraries, and Testing. Each skill consists of a SKILL.md file with a YAML frontmatter description for triggering, plus secondary markdown files for deeper references, all designed for lazy loading to conserve context. The author emphasizes human editing and testing, claiming significant error-rate reductions. Installation is supported across multiple assistants: Claude Code, Gemini CLI, Cursor, Copilot, OpenCode, Codex, Antigravity, and via the universal skills CLI. It also provides evaluation data in EVALUATIONS.md and guidance for using skills in CI for AI-driven reviews. Licensed under MIT.
The repository provides reusable skill definitions that AI assistants load on demand. Each skill is a directory with a SKILL.md file; the description field in frontmatter helps trigger the skill based on user requests. For example, the golang-testing skill includes table-driven testing, fuzzing, and goroutine leak detection. Installation is done via commands like npx skills add https://github.com/samber/cc-skills-golang --all or via plugin commands for specific tools. Once installed, the AI assistant automatically references these skills when relevant, guiding code generation, review, or refactoring. The skills can be overridden by company-specific skills, and techniques for tuning triggers are documented.
- A Go developer using Claude Code needs to ensure new code follows idiomatic style and error-handling conventions; the assistant loads golang-code-style and golang-error-handling skills.
- A team sets up AI-powered code review in CI using GitHub Actions; the agent applies golang-security and golang-observability skills to catch issues beyond linters.
- A developer is refactoring a large legacy Go codebase and uses golang-refactoring skill to apply safe, tool-driven transformations such as gopls Rename and Extract.
- A developer using Gemini CLI wants to generate a new CLI application; they install the skill and ask for a Cobra-based CLI, getting guidance from golang-spf13-cobra.
- A team adopting samber/lo for functional programming wants the AI to write idiomatic code; the golang-samber-lo skill provides detailed usage.
- A developer wants to add structured logging and metrics to a Go service; the golang-observability skill guides the implementation with slog and Prometheus.
How do you install or deploy this agent?
Universal CLI installation:
npx skills add https://github.com/samber/cc-skills-golang --allFor single skill:
npx skills add https://github.com/samber/cc-skills-golang --skill golang-performanceFor specific tools:
- Claude Code: In Claude Code, run /plugin marketplace add samber/cc then /plugin install cc-skills-golang@samber.
- Gemini CLI: gemini extensions install https://github.com/samber/cc-skills-golang and update with gemini extensions update cc-skills-golang.
- Cursor/OpenClaw/OpenCode/Codex/Antigravity: clone repo to the appropriate skills directory, e.g., git clone https://github.com/samber/cc-skills-golang.git ~/.cursor/skills/cc-skills-golang.
How do you use this agent?
After installation, the AI assistant will automatically leverage the skills based on context. For example, when you ask your assistant to "write tests for this function", it will load the golang-testing skill and produce table-driven tests. You can also explicitly request guidance on specific topics like "recommend a high-performance HTTP router" to trigger golang-popular-libraries. For CI review, configure a GitHub Action that uses an AI agent with these skills installed to comment on PRs. Refer to GOLANG-AI-DRIVEN-REVIEW.md for detailed setup.
What are this agent's strengths and limitations?
- Comprehensive coverage of Go development: 30+ skills, each with clear scope and detailed instructions, tested and reviewed by humans.
- Quantified impact: evaluation shows overall score jumps from 56% to 98% with skills, and per-skill error rate gaps range from -5% to -81%.
- Works with multiple coding assistants and a universal installer, reducing lock-in to a single tool.
- Efficient context usage: only skill descriptions (~1,100 tokens for recommended set) are loaded upfront; full content is lazy-loaded.
- Skills reflect the author's personal Go conventions; teams with different standards must create override skills, adding maintenance overhead.
- Some overlap with linters (e.g., golang-naming, golang-code-style) may cause redundant checks or require disabling conflicting rules.
- Not all skills are equally mature; some are marked as work in progress or have missing evaluation data (e.g., golang-stay-updated).
- Repository relies on external tools like npx and gopls; offline or restricted network environments may face installation hurdles.
How does this agent compare with similar options?
For generic skills, the author provides samber/cc-skills, which focuses on dev workflow conventions like git and CI. This repository specifically covers Go-language skills. No other competitor tools are mentioned in the source.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| cc-skills-golang: Agent Skills for Production-Ready Go This agent | 35 · Major gaps | Agent plugin / skillFree + model costs | ★ 3.5k | 17d ago | Go | ChatGPT · Codex · Claude Code |
| EOC — Everything OpenAI Codex Workflow OS | 75 · Good | Agent plugin / skillFree + model costs | ★ 86 | 4mo ago | JavaScript | Codex |
| Code Abyss: Persona and Engineering Skills for Coding Agents | 66 · Some gaps | CLI | ★ 244 | 3mo ago | JavaScript | Codex · Claude Code |
| Runtm | 63 · Some gaps | CLIFreemium | ★ 302 | 2d ago | Python | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows the repository contains only skill documentation and CI configuration, with no executable code or permission declarations. Therefore, least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, and source attribution have no supporting evidence, scoring 0. No malicious behavior found, but no security mechanisms either.
Self-consistency: Skills reference each other, README explains cross-referencing design, but no actual content verification, score 2. Dependency availability: Depends on external tools like skills CLI, gopls, godig, but no version pinning or availability guarantees, score 1. Failure messages: No documentation of error handling or failure messages, score 0.
Audience and scenarios: README clearly targets Go developers, lists multiple use cases, score 2. Capability boundaries: Skill list is clear, but specific boundaries of each skill not defined, score 2. Trigger precision: Provides description field and tuning guide, but no actual trigger tests, score 2. Environment fit: Provides installation for multiple clients, but not all environments, score 2.
Information architecture: README structure clear, skill categorization reasonable, score 2. Install notes: Multiple installation methods provided, score 2. Naming stability: Skill naming consistent, but no version history, score 2. Examples and FAQ: Examples and evaluation data provided, but FAQ missing, score 2. Known limitations: Mentions overlap and incomplete skills, but not comprehensive, score 1. License: MIT license clear, score 2. Versioning and changelog: No version numbers or changelog, score 0. Maintenance responsibility: No clear maintainer or contribution guidelines, score 1.
Output usability: Skill content well-organized, but no actual output examples, score 2. Marginal value: Provides error rate reduction data, but no independent verification, score 2. Cost benefit: Provides token budget suggestions, but no actual cost analysis, score 1.
Claim traceability: Error rate reduction claims in README lack specific test methodology, score 1. Cross-source corroboration: No external verification, score 0. Fact-inference separation: Some content distinguishes facts and inferences, but not clearly, score 1.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- Repository contains only skill documentation, no actual code, so actual effectiveness cannot be verified.
- Error rate reduction data lacks test methodology, may be overstated.
- Depends on external tools without version pinning, may affect reproducibility.
- No versioning or changelog, making updates hard to track.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Cross-harness compatibility v2.0.0 makes this skill collection cross-harness by default: Codex, Gemini CLI, Cursor, Copilot CLI, OpenCode, Antigravity, and Mistral Vibe, not just Claude Code. Skills now describe capabilities in prose rather than hardcoding tool names, and any generated config file includes real per-harness variants instead of a vague "adapt this yourself" note. What's Changed * fix(golang-lint): enable goimports formatter by @yebei199 in https://github.com/samber/cc-skills-golang/pull/85 …View on GitHub ↗ -
Release notes excerpt
What's Changed * docs(golang-benchmark): correct rationale for separate _bench_test.go files by @samber in https://github.com/samber/cc-skills-golang/pull/83 Full Changelog: https://github.com/samber/cc-skills-golang/compare/v1.9.0...v1.9.1View on GitHub ↗ -
Release notes excerpt
What's Changed * Clarify godig/gopls/Context7/govulncheck tool boundaries across skills by @samber in https://github.com/samber/cc-skills-golang/pull/72 * feat(skills): add isolated-worktree workflow to 5 skills by @samber in https://github.com/samber/cc-skills-golang/pull/73 * feat(skills): add ultracode orchestration directive to fan-out skills by @samber in https://github.com/samber/cc-skills-golang/pull/74 * feat(skills): add golang-gopls skill by @samber in https://github.com/samber/cc-skills-golang/pull/75 …View on GitHub ↗