GraphQL Schema Documenter skill for Claude and Codex
A docs-folder-ready reference for a GraphQL API: table of contents, every selected type and operation with field-level descriptions and arguments, example…
Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.
Download the skill (.zip) · View SKILL.md
When it is used
Use when a GraphQL schema needs an API reference document with operations, types, arguments, example queries, and deprecations laid out for developers to read. Do not use for auditing schema quality, or generating the schema itself. Related topics: coding, graphql.
What it will ask you for
- Schema SDL (longer free text)
- Sections to include (choose any: Types, Queries, Mutations, Subscriptions, Enums, Interfaces, Scalars, Input types)
- Include example queries (choose one: Yes, No)
- Output style (choose one: Plain markdown, GitHub-flavored markdown, HTML)
- Deprecation notes (choose one: Include, Omit)
- Audience (choose one: Internal frontend team, External API consumers, Both)
How it works
- Write the introduction and a table of contents linking every included section.
- Document each query, mutation, and subscription with its arguments table, return type, errors, and visible auth requirement.
- Produce a field table per type, enum, interface, and input type, turning SDL descriptions into full sentences and marking missing ones with a TODO.
- Write one runnable example query per operation with its response shape, when examples are on.
- Add deprecation callouts when enabled and the pagination and error conventions section for external consumers, then format for the chosen output style.
What you get
A single document in the chosen format with an introduction, table of contents, Operations section, Types section (one table per type), Examples when enabled, and Deprecations when enabled.
What it watches out for
- Documenting types before operations, so readers scroll past twenty object types to find the one query they need.
- Writing example queries from memory that request fields the schema does not define.
- Inventing descriptions for undocumented fields instead of flagging them, which bakes guesses into the docs.
How to install
Claude.ai and the Claude desktop app
- Download the skill .zip.
- Open Settings, then Capabilities, and find Skills.
- Choose Upload skill and select the .zip.
- Ask Claude for help with the task. It loads the skill when your request matches.
Claude Code
- Download the skill .zip.
- Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
- Start a new session. Claude Code loads the skill when your request matches.
Codex
- Download the skill .zip.
- Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
- Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.
Cursor
- Download the Cursor rule (.mdc).
- Save it in .cursor/rules/ inside your project.
- Cursor's agent applies the rule when your request matches its description.
AGENTS.md (Codex, Cursor, and other coding agents)
- Copy the AGENTS.md section.
- Paste it into AGENTS.md at the root of your repository, creating the file if needed.
- Coding agents that read AGENTS.md follow it when your request fits.