Convex Auth
CheckedConvex-auth securely authenticates users against Convex data sources using AI-powered risk assessment and adaptive authorization.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add igorwarzocha/opencode-workflows --skill convex-auth -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
igorwarzocha
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.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
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 undeclared network calls: passed
Makes no network calls.
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.
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 igorwarzocha/opencode-workflows at 6444ec4aac.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 6444ec4aac
- Scanned
- 1 file, 66 lines
About this skill
The convex-auth skill enables AI agents to manage authentication and authorization within Convex applications, a serverless backend platform. It allows agents to programmatically handle user sessions, verify credentials, and enforce access controls directly through code generation and execution.
When to use it
- Automating the setup of secure login flows for new Convex projects.
- Dynamically adjusting user permissions based on real-time application data.
- Integrating third-party identity providers (like Auth0 or Clerk) into existing Convex backends.
- Resolving access denied errors by correcting role assignments in the database schema.
Key capabilities
- Generates secure authentication middleware for Convex functions.
- Manages user session state and token validation logic.
- Enforces row-level security policies based on authenticated user roles.
- Integrates with external identity providers to extend login options.
Example prompts
- "Create a Convex function that requires a specific role before allowing a user to delete a project."
- "Set up authentication using Auth0 and configure the database schema to store user IDs securely."
- "Write code to automatically revoke a user's session when their account is flagged for suspicious activity."
Tips & gotchas
Ensure your Convex backend is properly configured with an identity provider before attempting to generate auth logic. This skill relies on specific Convex schema definitions; if the database structure is undefined, generated authentication code may fail to enforce correct access controls.