Skip to content
TrustedSkillsbeta
Back to all skills

Api Expert

Listed
martinholovsky·vlatest·backend·Unlicense

Provides API guidance and assistance for agent workflows.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add martinholovsky/claude-skills-generator --skill api-expert -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

martinholovsky

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 2 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: 169.254.169.254, www.google.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    www.google.comundeclared169.254.169.254undeclaredinternal-admin.company.locallocal

    What it found

    • skills/api-expert/references/security-examples.md:518contacts www.google.com
      const response = await fetch('https://www.google.com/recaptcha/api/siteverify', {
    • skills/api-expert/references/security-examples.md:597contacts 169.254.169.254
      // http://169.254.169.254/latest/meta-data/ (AWS metadata)

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned martinholovsky/claude-skills-generator at 1086ef2567.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
1086ef2567
Manifest
skills/api-expert/SKILL.md
Scanned
4 files, 2,725 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill provides expert guidance on API design and architecture for AI agent workflows. It ensures API implementations adhere to industry standards, avoids common pitfalls (hallucinations), and prioritizes security. The skill leverages available tools like code searches and web access to verify specifications before generating or implementing any API-related code. It's designed to help agents create secure, scalable, consistent, and developer-friendly APIs.

When to use it

  • When designing new REST APIs or integrating with existing ones.
  • When needing assistance with authentication protocols like OAuth2 and JWT.
  • To ensure API implementations comply with the OWASP API Security Top 10 (2023).
  • When implementing pagination strategies (offset, cursor-based, keyset) for large datasets.
  • To verify HTTP status code meanings or OpenAPI schema options before implementation.

Key capabilities

  • Expertise in REST API design principles: resource modeling, HTTP methods, status codes, HATEOAS, Richardson Maturity Model.
  • Knowledge of API standards including OpenAPI 3.1, JSON:API, HAL, and Problem Details (RFC 7807).
  • Familiarity with various API paradigms: REST, GraphQL, gRPC, WebSocket, Server-Sent Events.
  • Understanding of authentication methods like OAuth2, JWT, API keys, mTLS, and OIDC.
  • Ability to verify HTTP status codes (RFC 7231), OpenAPI schema fields against the 3.1 specification, and OWASP categories.
  • Access to tools for code searching, web searches, and fetching official RFC documents.

Example prompts

  • "What is the correct HTTP status code for a successful resource creation?"
  • "Verify the current OAuth2 grant types."
  • "Show me examples of cursor-based pagination in OpenAPI 3.1."
  • "Check the OWASP API Security Top 10 (2023) guidance on input validation."

Tips & gotchas

  • Mandatory Verification: Always verify any API specification, header, or standard before implementing code. If certainty is below 80%, STOP and verify.
  • Hallucination Risk: This skill deals with a high-risk area (API security). Be extremely cautious about "invented" specifications or patterns – they can lead to integration failures and security vulnerabilities.
  • Documentation Required: When providing API code, always cite the official specification used for verification.