From openapi-tools
This skill should be used when the user wants to explore an endpoint, show endpoint details, view endpoint schema, inspect an endpoint, understand what an endpoint accepts, or see endpoint input and output.
How this skill is triggered — by the user, by Claude, or both
Slash command
/openapi-tools:openapi-inspectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Fetch and display full details for a specific API endpoint from a running service's OpenAPI spec.
Fetch and display full details for a specific API endpoint from a running service's OpenAPI spec.
Use {host} as the base URL. Default to http://localhost:8000 if the user does not specify a host.
Pull the endpoint entry from the OpenAPI spec using jq:
curl -s {host}/openapi.json | jq '.paths["/path/to/endpoint"]'
Replace "/path/to/endpoint" with the actual path the user asked about.
Scan the output for any "$ref": "#/components/schemas/SchemaName" entries. Collect every unique schema name.
For each $ref, query its schema and recursively resolve nested $ref entries until all schemas are fully expanded:
curl -s {host}/openapi.json | jq '.components.schemas.SchemaName'
Replace SchemaName with the name extracted from the $ref.
Display to the user:
$ref)Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub alex-kopylov/zweihander --plugin openapi-tools