Skip to content
TrustedSkillsbeta
Back to all skills

Clerk Backend Api

Official
clerk·vlatest·security

Official clerk skill covering backend development, API for developing backend services and APIs.

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 clerk/skills --skill clerk-backend-api -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

clerk

Matched to the vendor's own GitHub organisation.

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 2 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 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: api.clerk.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

    api.clerk.comundeclaredraw.githubusercontent.comsource hostapi.github.comsource host

    What it found (3 of 10)

    • skills/core/clerk-backend-api/SKILL.md:43contacts api.clerk.com
      ORG=$(curl -s -X POST "https://api.clerk.com/v1/organizations" \
    • skills/core/clerk-backend-api/SKILL.md:53contacts api.clerk.com
      curl -s -X POST "https://api.clerk.com/v1/organizations/${ORG_ID}/invitations" \
    • skills/core/clerk-backend-api/SKILL.md:97contacts api.clerk.com
      curl -s -X PATCH "https://api.clerk.com/v1/users/${USER_ID}" \

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 7 places.

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

    What it found (3 of 7)

    • skills/core/clerk-backend-api/SKILL.md:354remote script piped into an interpreter
      curl -s https://raw.githubusercontent.com/clerk/openapi-specs/main/bapi/${version_name} | node scripts/extract-tags.js
    • skills/core/clerk-backend-api/SKILL.md:368remote script piped into a shell
      curl -s https://raw.githubusercontent.com/clerk/openapi-specs/main/bapi/${version_name} | bash scripts/extract-tag-endpoints.sh "${tag_name}"
    • skills/core/clerk-backend-api/SKILL.md:385remote script piped into a shell
      curl -s https://raw.githubusercontent.com/clerk/openapi-specs/main/bapi/${version_name} | bash scripts/extract-endpoint-detail.sh "${path}" "${method}"

  • 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.

  • Pinned to a commit: passed

    Scanned clerk/skills at 863ff165de.

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

Commit
863ff165de
Manifest
skills/core/clerk-backend-api/SKILL.md
Scanned
7 files, 973 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 a backend API interface specifically designed to integrate Clerk's authentication and user management features into custom AI agent workflows. It enables agents to securely handle identity verification, session management, and user data retrieval without exposing sensitive credentials directly in the agent's logic.

When to use it

  • Secure Authentication: When an AI agent needs to verify a user's identity before granting access to private data or actions.
  • Session Persistence: For maintaining logged-in states across multiple interactions within a backend service.
  • User Context Retrieval: To fetch specific user attributes (like email or role) required for personalized responses.
  • Multi-Tenant Applications: When building platforms where different users need isolated access controls managed by Clerk.

Key capabilities

  • Handles OAuth2 and magic link authentication flows via API endpoints.
  • Manages user sessions and tokens securely on the server side.
  • Provides structured JSON responses for user profiles and permissions.
  • Supports integration with custom backend frameworks (Node.js, Python, etc.).

Example prompts

  • "Integrate the clerk-backend-api skill to authenticate a user via magic link before allowing them to upload documents."
  • "Use this API to retrieve the current user's role from Clerk and adjust the AI agent's response permissions accordingly."
  • "Configure the backend handler to validate session tokens for every incoming request to the data retrieval endpoint."

Tips & gotchas

Ensure your backend server environment is properly configured with the necessary Clerk API keys before attempting to install or invoke this skill. This skill operates strictly on the server side; do not attempt to call it directly from a client-side AI agent interface without a secure proxy.