Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access."..." for exact phrases · Try typography, debugging or spreadsheetSet up backend API projects using FastAPI templates. Covers asynchronous application patterns, dependency injection, and comprehensive error handling.
Adds authentication using passkeys or OAuth to an existing Convex app. Includes wiring auth.config.ts.
Specializes in code within convex/ directories, including schemas, indexes, queries, mutations, actions, HTTP endpoints, crons, storage, and authentication. Covers function syntax, validators, resource limits, and component installation.
Performs schema migrations and data backfills on deployed Convex applications using @convex-dev/migrations.
Identifies the installed Convex version and retrieves corresponding documentation as Markdown or checks local package types. Uses a freshness hierarchy to avoid relying on stale API knowledge.
Scans Convex apps for identity impersonation, missing document ownership checks, queries exposing data through client-supplied IDs, and unauthorized container writes. Applies requireIdentity and requireOwner checks and verifies with TypeScript.
Checks pull request implementations against approved or repository specification context in spec_context.md. Adds material discrepancies to review.json during PR review.
Audits functions and other code in a convex/ directory before release. Checks security, authentication, validators, performance, and implementation patterns.
Applies an Adlerian psychology framework to barriers to action. Intended for situations where users know what to do but delay, repeatedly procrastinate, or stop making progress.
Reviews an existing Convex application and applies optimizations across security, scale, upgrades, and observability.
Builds reactive, type-safe Convex backends covering schemas, indexes, queries, mutations, actions, authentication, storage, and scheduling. Also covers multiplayer, mobile backends, and LLM or agent workflows.
Classifies and announces the target deployment before commands that affect it. Requires fresh explicit consent for production actions and supports a session read-only mode.
A growing collection of real, public skills. Descriptions and instructions indexed 24 Sept 2026.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name