GraphQL Schema Generator skill for Claude and Codex
Your written-out type, query, and mutation specifications turned into a valid, saveable .graphql file: correct SDL syntax, declared scalars and directives…
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 types, queries, and mutations are already written out in notes and need transcribing into a syntactically valid schema.graphql file without design changes. Do not use for designing the schema from a domain description, or auditing a schema that already exists. Related topics: coding, graphql.
What it will ask you for
- Types (longer free text)
- Queries (longer free text)
- Mutations (longer free text)
- Scalars (choose any: Date, DateTime, JSON, URL, UUID, Email, Long)
- Directives (choose any: @auth, @deprecated, @cache, @upper, @rateLimit)
- File name (free text, e.g. "schema.graphql")
How it works
- Transcribe every type, field, argument, and return type from the inputs with its given name, so the SDL contains exactly what was specified.
- Normalise syntax only: list and non-null markers, consistent casing with each rename noted, and no invented fields.
- Declare each selected scalar and directive with its locations before first use.
- Order the file as scalars, directives, enums, interfaces, object types, inputs, then Query and Mutation.
- Check that every referenced type is defined, no field is duplicated, and every mutation returns a type, then output the file with any assumptions listed.
What you get
The file name on one line, the complete SDL in one fenced graphql block, and a short Assumptions list for any ambiguity resolved in the inputs.
What it watches out for
- Adding helpful fields or pagination the specification never mentioned, which turns a transcription into a redesign.
- Using a custom scalar or directive in a field without declaring it, which fails schema load on the first run.
- Silently changing a field's casing without listing the rename, so resolvers written against the notes no longer match.
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.