Guide · Agent skill
How to use the API Request Checker agent skill (api-analyzer)
Updated · written with AI from the project's own documentation and checked against our catalogue data
The api-analyzer skill is an agent skill that reviews an API request you paste into your AI assistant and flags obvious structural problems, such as a missing Authorization header or a wrong Content-Type. It is aimed at developers who want a quick sanity check before running a curl command or endpoint call. This guide explains what an agent skill is, how to install this one, how to trigger it, and what it cannot tell you.
API Request Checkersickn33/agentic-awesome-skills · MIT Download the skill Quick start
- 1Download the ZIP. Download the api-analyzer skill ZIP from this page and unzip it.
- 2Place the folder. Move the unzipped api-analyzer folder into ~/.claude/skills/ for personal use, or into .claude/skills/ in your project.
- 3Or upload it in the apps. In the Claude apps, go to Settings → Capabilities → Skills and upload the ZIP.
- 4Paste your request. Paste the method, URL, headers and body, or a curl command, into the conversation and ask for it to be checked.
- 5Read the verdict. Check whether the skill returns a correct line, an error with a fix, or one clarifying question, and answer the question if asked.
- 6Run the real test. Send the request with your own tooling or test suite, since the skill does not execute it or verify credentials.
What an agent skill is and what this one does
An agent skill is a folder containing a SKILL.md file that gives an AI agent specific instructions for a task. When the task matches the skill's description, the agent follows those instructions.
The api-analyzer skill validates whether an API request is correct based on the inputs you provide: method, URL, headers, body, auth and query parameters. It checks the method, URL, headers, body, query parameters and authentication against the contract you supply.
- Checks the HTTP method against the documented operation
- Checks that the URL is well formed, has no obvious typos and has path parameters filled in
- Checks that Content-Type matches the body format and that Authorization is present on likely-protected endpoints
- Checks that the body is valid for its Content-Type and that required fields are present if a schema is known
- Checks that required query parameters are present and correctly encoded
- Checks that the token or key format looks right for the scheme (Bearer, Basic, API key)
Install the api-analyzer skill
Download the skill ZIP from this page and unzip it. For a personal install, place the unzipped skill folder in ~/.claude/skills/. For a single project, place it in that project's .claude/skills/ folder.
If you use the Claude apps instead, upload the ZIP under Settings → Capabilities → Skills.
- Personal install: ~/.claude/skills/api-analyzer/
- Project install: .claude/skills/api-analyzer/ inside your project
- Claude apps: Settings → Capabilities → Skills, then upload the ZIP
Trigger the skill with a natural request
You do not need a special command. Paste the request into the conversation and ask for it to be checked, for example in the form of a method, URL, headers and body, or a curl command.
The skill replies in one line. If the request is correct, it says it is syntactically consistent with the supplied contract and was not executed. If something is wrong, it states the error and a one-line fix. If the skill cannot decide without one missing detail, it asks a single targeted question.
- Example input: GET /users/123 with header Authorization: Bearer abc123
- Example input: POST /orders with Content-Type: application/json and body {"item":"shoe"}
- Example input: POST /checkout with no body and no headers
Read the kinds of answers you will get
The skill uses three response types. A check mark means the request looks correct. A cross means there is an error, with a fix. A warning sign means it needs one clarifying question before it can judge the request.
The skill is designed to ask only when the answer would change its verdict. It will not ask about optional headers or environment details.
- Correct: the request is syntactically consistent with the contract and was not executed
- Incorrect: for example, a missing Authorization header, with a suggested header to add
- Ambiguous: a single question such as whether a POST request has a body, or whether the body is JSON or form data
What the skill does not do
The skill does not send the request. It does not check whether your credentials work or whether a live server would accept the call. Its verdicts are based only on the text you paste and the contract you provide.
Because of this, a correct verdict is not a promise that the API will respond successfully. Use it to catch structural mistakes early, then run your real API tests.
Safety and requirements
The skill lists no requirements. According to its listing, it does not run scripts and does not use the network. Its source file is SKILL.md only.
The skill's own limitations say to use it only when the task matches its upstream source and local project context. Verify commands, generated code, credentials and external service behaviour before applying changes. Do not treat its examples as a substitute for environment-specific tests, security review, or approval for destructive or costly actions.
The skill is licensed under MIT.
- Requires: nothing listed
- Runs scripts: no
- Uses network: no
- Do not paste live secrets you would not share with your AI tool
What people use it for
- Finding a missing Authorization header before calling a protected endpoint with curl
- Catching a Content-Type that does not match a JSON or form body
- Spotting a malformed URL or unfilled path parameter in an endpoint call
- Checking that a POST or PATCH request includes a body when the contract needs one
- Getting a quick structural review of a request against a contract you provide
Frequently asked questions
Is the api-analyzer skill free to use?
The skill is licensed under MIT, according to its listing and source file. The source does not mention pricing, so check the license file linked from the skill's source for the terms.
What do I need to install the api-analyzer skill?
The listing states no requirements. You download the ZIP from this page, unzip it, and place it in ~/.claude/skills/ or a project's .claude/skills/ folder, or upload it under Settings → Capabilities → Skills in the Claude apps.
Does the api-analyzer skill send my API request?
No. The skill explicitly does not execute requests or verify credentials. It only reviews the text you paste for structural problems.
Can api-analyzer tell me if my API key is valid?
No. It checks whether a token or key format looks right for the auth scheme, but it does not confirm the credential works against a live server.
Does api-analyzer replace API testing or schema validation?
No. It inspects text only and gives no guarantee that the server will accept the call. Keep running your real API tests, schema validation and security review.
What are alternatives to api-analyzer for checking API requests?
The source does not compare this skill with other tools, so this guide cannot make a comparison. For actual responses, you would need to send the request with your own tooling and tests, which this skill does not do.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Use this skill if you are a developer or a team that wants a fast one-line structural check on a curl command or endpoint call before running it. Skip it if you need to know whether a live API accepts a request or a credential is valid, or if you need real API tests, schema validation or a security review.
Download the skill