openapi-summarizer
Skill50 starsChanged 21 days agoMITView on GitHub
Summarizes an OpenAPI 3 or Swagger 2 JSON file into title, servers, endpoint counts per tag, unsecured operations, deprecated operations and a compact endpoint list. Use when the user shares an API spec and asks what it contains, wants an overview before integrating, or needs to find endpoints without authentication.
In this repository26 other files it gives its agents.
- api-endpoint-testerSkill
- changelog-generatorSkill
- commit-message-writerSkill
- cron-explainerSkill
- csv-profilerSkill
- docker-compose-reviewerSkill
- dockerfile-linterSkill
- env-file-auditorSkill
- git-conflict-resolverSkill
- incident-postmortem-writerSkill
- json-diffSkill
- jwt-inspectorSkill
- log-analyzerSkill
- markdown-link-checkerSkill
- meeting-notes-to-actionsSkill
- pr-description-writerSkill
- python-code-smellsSkill
- readme-doctorSkill
- regex-explainerSkill
- release-checklistSkill
- requirements-auditorSkill
- secure-code-reviewSkill
- skill-authorSkill
- sql-query-reviewerSkill
- todo-extractorSkill
- unit-test-writerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Before writing a client, to see how big the API is and how it is organized.
- Distinctive: line 43
Start with the title, version and the size (operations and schemas).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenAPI summarizer
Turns a large spec into a short, structured overview that an agent can reason about.
When to use
- The user pastes or points to an
openapi.jsonorswagger.json. - Before writing a client, to see how big the API is and how it is organized.
- During a review, to list the operations that have no security requirement.
How to run
python scripts/summarize_openapi.py openapi.jsonYAML specs must be converted to JSON first.
Output
JSON with:
title,version(the API version) andspec(the OpenAPI or Swagger version).servers: server URLs (for Swagger 2, built fromschemes,hostandbasePath).operations,deprecated,unsecured: counts. An operation is secured when it has its ownsecuritylist, or when it has none and the document defines a globalsecuritylist. An empty list means no security.by_tag: operations per tag (untaggedwhen missing).schemas: number of schema definitions.endpoints: a list of{"method", "path", "summary", "tags", "secured", "deprecated"}.
Reading the result
- Start with the title, version and the size (operations and schemas).
- Name the biggest tags and what they seem to cover.
- Point out
unsecuredoperations and ask whether they are meant to be public. - Mention deprecated operations so they are not used in new code.
Errors
A missing file exits with code 2. Invalid JSON, or a document that is not OpenAPI or Swagger, exits with code 3.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

