Convex Auth Setup
Guides an agent through adding login, user identity mapping, and access control to a Convex app.
- Repository
- openclaw/clawhub
- Stars
- 9,546
- Licence
- MIT
- Files
- 6 files
What it does
When installed, the agent follows a structured process for adding authentication to a Convex backend app. It first asks which auth provider to use (Convex Auth, Clerk, WorkOS AuthKit, Auth0, or a custom JWT provider) or infers it from the repository, then reads the matching reference file and official docs to wire up packages, environment variables, and config. It also steers the agent toward verifying identity on the server inside backend functions rather than trusting client-supplied user IDs.
Great for
- Developers starting a new Convex app who need login and protected backend functions
- Teams already using Clerk, Auth0, or WorkOS with Convex who want guided integration
- Developers adding role or ownership checks to existing Convex queries and mutations
Skip it if
- Projects using a non-Convex backend, since the guidance is specific to Convex functions and config
- Anyone expecting fully automatic setup: the skill intentionally pauses for provider choices and for human steps like dashboard or deployment configuration
Try asking
- “Set up Clerk authentication in my Convex React app and protect my query functions”
- “Add login to this Convex project using Convex Auth, and check that protected functions reject signed-out users”
- “Make my getMyProfile function use the logged-in user's identity instead of a userId argument”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 6 original files, the MIT licence and an attribution note.
convex-setup-auth.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip convex-setup-auth.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip convex-setup-auth.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Name your auth provider up front, or let the agent detect it from existing dependencies and files like convex/auth.config.ts
- Say whether you want local-only or production-ready setup, since the skill asks about this early
- Review any generated auth config and env var changes yourself before deploying, especially for production
What's inside
- agents/openai.yaml
- references/auth0.md
- references/clerk.md
- references/convex-auth.md
- references/workos-authkit.md
- SKILL.md
Redistributed unmodified from openclaw/clawhub under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.