Agent skill

Google Style Code Docs

Applies Google Style documentation to Python docstrings, Go comments and Terraform descriptions, for writing new docs or reviewing existing ones.

MITAuto-check passedDevelopment

Install Google Style Code Docs

skills CLI

$ npx skills add jjmartres/opencode --skill code-docs -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install jjmartres/opencode code-docs --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/jjmartres/opencode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/opencode/skills/code-docs .claude/skills/code-docs && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "code-docs" agent skill from https://github.com/jjmartres/opencode/tree/main/opencode/skills/code-docs into .claude/skills/code-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-docs", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/jjmartres/opencode/tree/main/opencode/skills/code-docs

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add jjmartres/opencode --skill code-docs -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install jjmartres/opencode code-docs --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jjmartres/opencode.git skills-src && mkdir -p .agents/skills && cp -r skills-src/opencode/skills/code-docs .agents/skills/code-docs && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "code-docs" agent skill from https://github.com/jjmartres/opencode/tree/main/opencode/skills/code-docs into .agents/skills/code-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-docs", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add jjmartres/opencode --skill code-docs -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install jjmartres/opencode code-docs --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jjmartres/opencode.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/opencode/skills/code-docs .cursor/skills/code-docs && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "code-docs" agent skill from https://github.com/jjmartres/opencode/tree/main/opencode/skills/code-docs into .cursor/skills/code-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-docs", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/jjmartres/opencode.git --path opencode/skills/code-docs

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add jjmartres/opencode --skill code-docs -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install jjmartres/opencode code-docs --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jjmartres/opencode.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/opencode/skills/code-docs .gemini/skills/code-docs && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "code-docs" agent skill from https://github.com/jjmartres/opencode/tree/main/opencode/skills/code-docs into .gemini/skills/code-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-docs", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install jjmartres/opencode code-docs

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add jjmartres/opencode --skill code-docs -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/jjmartres/opencode.git skills-src && mkdir -p .github/skills && cp -r skills-src/opencode/skills/code-docs .github/skills/code-docs && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "code-docs" agent skill from https://github.com/jjmartres/opencode/tree/main/opencode/skills/code-docs into .github/skills/code-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-docs", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add jjmartres/opencode --skill code-docs -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install jjmartres/opencode code-docs --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/jjmartres/opencode.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/opencode/skills/code-docs .opencode/skills/code-docs && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "code-docs" agent skill from https://github.com/jjmartres/opencode/tree/main/opencode/skills/code-docs into .opencode/skills/code-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-docs", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: code-docs
GitHub stars: 133
Token cost: ~1.9k tokens
SKILL.md length: 684 words
Files: 4 (incl. references)
Skills in repo: 11
Repo updated: Apr 20, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Applies Google Style documentation to Python docstrings, Go comments and Terraform descriptions, for writing new docs or reviewing existing ones.

Works in 5 steps: Detect Language → Apply Appropriate Standard → Document Code Elements → …
Adding docstrings to Python modules and classes
SKILL.md covers When to Apply This Skill, Core Principles, Workflow and Documentation Coverage, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The agent detects the language from file extensions and keywords, reads the matching reference file for Python, Go or Terraform, and documents the appropriate elements: modules, classes and functions for Python, package, type and function comments for Go, and variable, output, resource and module descriptions for Terraform.

Five principles guide the work: clarity, completeness for all public APIs with parameters, returns and exceptions, consistency with each language's Google Style conventions, conciseness without redundancy, and usage examples for complex functionality. Before finishing, the agent checks that public APIs are documented, formatting follows the style exactly, and no obvious or redundant text remains.

In review mode, the skill points out missing documentation, suggests improvements to existing text, supplies corrected examples and explains why the documentation matters. It applies when writing new functions, classes or packages, refactoring undocumented code, or when you mention Google Style or ask to document code.

When your agent uses it

Adding docstrings to Python modules and classes
Writing Go package, type and function comments
Reviewing Terraform variable and output descriptions

Example prompts

“Add Google Style docstrings to every public function in utils/dates.py.”
“Document the Terraform variables and outputs in modules/network.”
“Review this Go package for missing or unclear comments.”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Detect Language
Apply Appropriate Standard
Document Code Elements
Quality Checks
Provide Feedback

What it can do on your machine

Read from SKILL.md and the folder at commit 28dc323. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and go).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Google Style Code Docs loads about 1.9k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 684 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~105
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jjmartres/opencode at commit 28dc323, republished under its MIT licence (© jjmartres). 684 words, ~1,948 tokens.

Download SKILL.mdSave it as .claude/skills/code-docs/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: code-docs
description: Apply Google Style documentation standards to Python, Go, and Terraform code. Use when writing or reviewing code that needs docstrings/comments, when asked to "document this code", "add docstrings", "follow Google Style", or when improving code documentation quality. Supports Python docstrings, Go comments, and Terraform variable/output descriptions. Enforces consistent, professional documentation standards.

Code Documentation Standards

Apply Google Style documentation standards to Python (docstrings), Go (comments), and Terraform (descriptions). Ensures consistent, professional, and comprehensive code documentation across multiple languages.

When to Apply This Skill

Use this skill when:

Writing new functions, classes, or packages
Reviewing code for documentation quality
User requests "document this code" or "add docstrings"
User mentions "Google Style" or documentation standards
Refactoring code that lacks proper documentation
Creating code examples that should be well-documented

Core Principles

Clarity: Documentation should be immediately understandable
Completeness: Document all public APIs, parameters, returns, exceptions
Consistency: Follow language-specific Google Style conventions
Conciseness: Be thorough but avoid redundancy
Examples: Include usage examples for complex functionality

Workflow

1. Detect Language

Identify the programming language:

Python: Look for .py files, def, class keywords, type hints
Go: Look for .go files, func, type, package keywords
Terraform: Look for .tf files, resource, variable, module keywords

2. Apply Appropriate Standard

Read the corresponding reference file:

Python: Read references/python_google_style.md for complete docstring standards
Go: Read references/go_google_style.md for complete comment standards
Terraform: Read references/terraform_style.md for complete description standards

3. Document Code Elements

Apply documentation to all appropriate code elements:

Python:

Module-level docstrings
Class docstrings
Method/function docstrings
Important variables/constants

Go:

Package comments
Type comments
Function comments
Important constants/variables

Terraform:

Variable descriptions
Output descriptions
Resource comments
Module descriptions

4. Quality Checks

Before finalizing, verify:

All public APIs are documented
Parameters and returns are described
Exceptions/errors are documented
Examples are provided for complex functions
Formatting follows Google Style exactly
No redundant or obvious documentation

5. Provide Feedback

When reviewing code:

Point out missing documentation
Suggest improvements to existing docs
Provide corrected examples
Explain why certain documentation is important

Documentation Coverage

Python - What to Document

Always Document:

Public modules (module-level docstring)
Public classes (class docstring)
Public methods and functions (method docstring)
__init__ methods (explain parameters)

Consider Documenting:

Complex private functions (with leading underscore)
Non-obvious class attributes
Module-level constants

Don't Document:

Self-explanatory code (e.g., simple getters/setters)
Override methods that just call super() without changes
Trivial one-liner functions with obvious behavior

Go - What to Document

Always Document:

Package (package comment before package declaration)
Exported types (structs, interfaces)
Exported functions and methods
Exported constants and variables

Consider Documenting:

Complex unexported functions
Non-obvious implementation details
Important internal structures

Don't Document:

Trivial getters/setters
Self-explanatory code
Override methods without new behavior

Terraform - What to Document

Always Document:

All variables (description field)
All outputs (description field)
Module purpose (README.md)
Complex resources (inline comments)

Consider Documenting:

Data sources with complex filters
Non-obvious resource dependencies
Conditional resource creation logic

Don't Document:

Self-explanatory variable names
Simple pass-through outputs
Standard resource configurations

Show full SKILL.md (255 more words)Show less

Special Cases

Python Type Hints

When using type hints, docstrings can be more concise:

python

def add(a: int, b: int) -> int:
    """Add two integers.

    Args:
        a: First integer.
        b: Second integer.

    Returns:
        The sum of a and b.
    """
    return a + b

Type information is already in the signature, so Args and Returns can be brief.

Go Error Returns

Always document what errors a function can return:

// ReadConfig reads and parses the configuration file.
//
// Returns an error if the file cannot be read or contains invalid YAML.
func ReadConfig(path string) (*Config, error) {
    // implementation
}

Complex Algorithms

For complex logic, add inline comments AND comprehensive function documentation:

python

def dijkstra(graph: Graph, start: Node) -> dict[Node, float]:
    """Find shortest paths using Dijkstra's algorithm.

    Implements Dijkstra's single-source shortest path algorithm
    using a priority queue for O((V + E) log V) complexity.

    Args:
        graph: Weighted graph with non-negative edge weights.
        start: Starting node for path calculations.

    Returns:
        Dictionary mapping each node to its shortest distance from start.
        Unreachable nodes are not included in the result.

    Raises:
        ValueError: If graph contains negative edge weights.

    Example:
        >>> graph = Graph()
        >>> graph.add_edge("A", "B", 4)
        >>> graph.add_edge("A", "C", 2)
        >>> distances = dijkstra(graph, "A")
        >>> distances["B"]
        4
    """
    # Implementation with inline comments for complex parts

Output Format

When adding documentation to code:

Present the documented code with proper formatting
Explain what was added if the changes are significant
Highlight any decisions made about what to document or not document

Avoid

Generic or placeholder documentation ("This function does stuff")
Redundant documentation that just repeats the code ("This adds a and b")
Over-documentation of obvious code
Inconsistent formatting within the same file
Missing critical information (parameters, exceptions, edge cases)
Documentation that becomes outdated as code changes

references/terraform_style.md

Complete Terraform documentation standard with:

Variable description format
Output description format
Module documentation structure
Inline comments for complex resources
Examples for common patterns
terraform-docs integration

Resources

references/python_google_style.md

Complete Python docstring standard with:

Module, class, and function docstring formats
Args, Returns, Raises, Yields sections
Type hint integration
Examples for common patterns
Edge cases and best practices

references/go_google_style.md

Complete Go comment standard with:

Package comment format
Function and method comment format
Type comment format
Documentation for errors
Examples for common patterns
godoc integration notes

Quality Standards

All code documentation must:

Start with a concise one-line summary
Use proper grammar and punctuation
Follow language-specific formatting (indentation, delimiters)
Include examples for non-trivial public APIs
Document all parameters, returns, and errors/exceptions
Be maintained when code changes

Files

SKILL.md and 3 other files (references) in opencode/skills/code-docs of jjmartres/opencode.

SKILL.md
references/go_google_style.md
references/python_google_style.md
references/terraform_style.md

Open the folder on GitHubat commit 28dc323

Compare with similar skills

Google Style Code Docs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Google Style Code Docs compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Google Style Code Docs this skilljjmartres/opencode	133	—	~1.9k	Automated safety check: Pass	MIT	5 mo ago
Clean Commentsertugrul-dmr/clean-code-skills	195	—	~422	Automated safety check: Pass	MIT	5 mo ago
Kitaru Docszenml-io/kitaru	300	—	~936	Automated safety check: Pass	Apache-2.0	today
Flowfile Config and Flags CatalogEdwardvaneechoud/Flowfile	370	—	~12k	Automated safety check: Notes	MIT	yesterday
Genie API Service Docsqualcomm/qai-appbuilder	246	—	~840	Automated safety check: Pass	Custom licence	today
Draw.io Diagram StudioAgents365-ai/drawio-skill	10k	—	~2.4k	Automated safety check: Notes	MIT	5 days ago

Similar skills

Clean Comments
ertugrul-dmr/clean-code-skills
A skill your agent uses when writing, fixing, editing, or reviewing Python comments and docstrings.
195 GitHub stars~422 tokensUpdated 5 mo ago
DevelopmentAuto-check passed
Kitaru Docs
zenml-io/kitaru
Kitaru documentation surfaces, link rules, and accuracy rules.
300 GitHub stars~936 tokensUpdated today
DevelopmentAuto-check passed
Flowfile Config and Flags Catalog
Edwardvaneechoud/Flowfile
Catalog of Flowfile's environment variables and runtime flags: what each does, where the code reads it, its default, and where the docs disagree with the code.
370 GitHub stars~12k tokensUpdated yesterday
DevelopmentAuto-check: notes
Genie API Service Docs
qualcomm/qai-appbuilder
GenieAPIService technical documentation retrieval. An agent skill from qualcomm/qai-appbuilder.
246 GitHub stars~840 tokensUpdated today
DevelopmentAuto-check passed
Draw.io Diagram Studio
Agents365-ai/drawio-skill
Creates and edits editable draw.io diagrams from descriptions, code, infrastructure files, SQL and API schemas, with sync, review, test and export tools.
10k GitHub stars~2.4k tokensUpdated 5 days ago
DevelopmentAuto-check: notes
Dignified Python Standards
docling-project/docling
Applies opinionated production Python conventions chosen by the project's Python version: modern type syntax, pathlib, explicit checks and interface guidance.
68k GitHub stars~1.5k tokensUpdated yesterday
DevelopmentAuto-check passed

Questions about Google Style Code Docs

What does Google Style Code Docs do?

Applies Google Style documentation to Python docstrings, Go comments and Terraform descriptions, for writing new docs or reviewing existing ones. The agent detects the language from file extensions and keywords, reads the matching reference file for Python, Go or Terraform, and documents the appropriate elements: modules, classes and functions for Python, package, type and function comments for Go, and variable, output, resource and module descriptions for Terraform.

When should I use Google Style Code Docs?

Google Style Code Docs fits situations like: adding docstrings to Python modules and classes; writing Go package, type and function comments; reviewing Terraform variable and output descriptions.

How do I install Google Style Code Docs in Claude Code?

Run `npx skills add jjmartres/opencode --skill code-docs -a claude-code`. Or copy the skill folder (opencode/skills/code-docs in jjmartres/opencode) into .claude/skills/code-docs in your project. Claude Code loads it when a task matches its description.

How do I install Google Style Code Docs in Codex?

Run `npx skills add jjmartres/opencode --skill code-docs -a codex`. Or copy the skill folder (opencode/skills/code-docs in jjmartres/opencode) into .agents/skills/code-docs in your project. Codex loads it when a task matches its description.

Can I use Google Style Code Docs in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jjmartres/opencode --skill code-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-docs, .gemini/skills/code-docs, .github/skills/code-docs and .opencode/skills/code-docs in your project.

What does Google Style Code Docs need to run?

SKILL.md names no scripts, command-line tools or credentials: Google Style Code Docs is instructions for the agent only.

Does Google Style Code Docs access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Google Style Code Docs safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Google Style Code Docs use?

Google Style Code Docs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Google Style Code Docs use?

About 1.9k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.

What are the alternatives to Google Style Code Docs?

Skills that share tags, products or a category with Google Style Code Docs: Clean Comments (ertugrul-dmr/clean-code-skills, 195 stars), Kitaru Docs (zenml-io/kitaru, 300 stars), Flowfile Config and Flags Catalog (Edwardvaneechoud/Flowfile, 370 stars) and Genie API Service Docs (qualcomm/qai-appbuilder, 246 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Google Style Code Docs?

jjmartres (a GitHub user) maintains it in jjmartres/opencode, which has 133 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on April 20, 2026.

Source: jjmartres/opencode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Google Style Code Docs

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Code Documentation Standards

When to Apply This Skill

Core Principles

Workflow

1. Detect Language

2. Apply Appropriate Standard

3. Document Code Elements

4. Quality Checks

5. Provide Feedback

Documentation Coverage

Python - What to Document

Go - What to Document

Terraform - What to Document

Special Cases

Python Type Hints

Go Error Returns

Complex Algorithms

Output Format

Avoid

references/terraform_style.md

Resources

references/python_google_style.md

references/go_google_style.md

Quality Standards

Files

Compare with similar skills

Similar skills

More from jjmartres/opencode

Related

Questions about Google Style Code Docs