mcpbeat Sign in

Go Documentation Agent Skill

by cxuu

Use when writing or reviewing documentation for Go packages, types, functions, or methods. Also use proactively when creating new exported types, functions, or packages, even if the user doesn't explicitly ask about documentation. Does not cover code comments for non-exported symbols (see go-style-core).

7k tokens
context cost
the whole folder, loaded on every use
7
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
136
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/cxuu/golang-skills --skill go-documentation

The instruction itself

12 sections, as written by the author

Go Documentation

Resource Routing

  • scripts/check-docs.sh - Run when checking exported functions, types, methods, constants, and packages for missing doc comments.
  • scripts/check-docs-ast.go - Implementation helper invoked by check-docs.sh; patch this when changing documentation analysis behavior.
  • assets/doc-template.go - Use when starting a documented package or exported API.
  • references/CONVENTIONS.md - Read when documenting parameters, context behavior, concurrency safety, cleanup, errors, or named results.
  • references/EXAMPLES.md - Read when adding runnable examples or package examples.
  • references/FORMATTING.md - Read when formatting Godoc lists, paragraphs, links, and code blocks.

Doc Comments

> Normative: All top-level exported names must have doc comments.

Basic Rules

  • Begin with the name of the object being described
  • An article ("a", "an", "the") may precede the name
  • Use full sentences (capitalized, punctuated)
// A Request represents a request to run a command.
type Request struct { ...

// Encode writes the JSON encoding of req to w.
func Encode(w io.Writer, req *Request) { ...

Unexported types/functions with unobvious behavior should also have doc comments.

> Validation: After adding doc comments, run bash scripts/check-docs.sh to verify no exported symbols are missing documentation. Fix any gaps before proceeding.


Comment Sentences

> Normative: Documentation comments must be complete sentences.

  • Capitalize the first word, end with punctuation
  • Exception: may begin with uncapitalized identifier if clear
  • End-of-line comments for struct fields can be phrases

Comment Line Length

> Advisory: Aim for ~80 columns, but no hard limit.

Break based on punctuation. Don't split long URLs.


Struct Documentation

Group fields with section comments. Mark optional fields with defaults:

type Options struct {
    // General setup:
    Name  string
    Group *FooGroup

    // Customization:
    LargeGroupThreshold int // optional; default: 10
}

Package Comments

> Normative: Every package must have exactly one package comment.

// Package math provides basic constants and mathematical functions.
package math
  • For main packages, use the binary name: // The seed_generator command ...
  • For long package comments, use a doc.go file

What to Document

> Advisory: Document non-obvious behavior, not obvious behavior.

| Topic | Document when... | Skip when... |

|-------|-----------------|--------------|

| Parameters | Non-obvious behavior, edge cases | Restates the type signature |

| Contexts | Behavior differs from standard cancellation | Standard ctx.Err() return |

| Concurrency | Ambiguous thread safety (e.g., read that mutates) | Read-only is safe, mutation is unsafe |

| Cleanup | Always document resource release | — |

| Errors | Sentinel values, error types (use *PathError) | — |

| Named results | Multiple params of same type, action-oriented names | Type alone is clear enough |

Key principles:

  • Context cancellation returning ctx.Err() is implied — don't restate it
  • Read-only ops are assumed thread-safe; mutations assumed unsafe — don't restate
  • Always document cleanup requirements (e.g., Call Stop to release resources)
  • Use pointer in error type docs (*PathError) for correct errors.Is/errors.As
  • Don't name results just to enable naked returns — clarity > brevity

Runnable Examples

> Advisory: Provide runnable examples in test files (*_test.go).

func ExampleConfig_WriteTo() {
    cfg := &Config{Name: "example"}
    cfg.WriteTo(os.Stdout)
    // Output:
    // {"name": "example"}
}

Examples appear in Godoc attached to the documented element.


Quick Reference

| Topic | Key Rule |

|-------|----------|

| Doc comments | Start with name, use full sentences |

| Line length | ~80 chars, prioritize readability |

| Package comments | One per package, above package clause |

| Parameters | Document non-obvious behavior only |

| Contexts | Document exceptions to implied behavior |

| Concurrency | Document ambiguous thread safety |

| Cleanup | Always document resource release |

| Errors | Document sentinels and types (note pointer) |

| Examples | Use runnable examples in test files |

| Formatting | Blank lines for paragraphs, indent for code |


  • Naming conventions: See go-naming when choosing names for the identifiers your doc comments describe
  • Testing examples: See go-testing when writing runnable Example test functions that appear in godoc
  • Linting enforcement: See go-linting when using revive or other linters to enforce doc comment presence
  • Style principles: See go-style-core when balancing documentation verbosity against clarity and concision

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take cxuu/go-documentation from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.