get-convex/convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
npx skills add https://github.com/get-convex/agent-skills/tree/main/skills/convex-performance-auditAudits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.
This repo contains 5 individual skills — each has its own dedicated page.
Routes general Convex requests to the right project skill. Use when the user asks which Convex skill to use or gives an underspecified Convex app task.
Builds reusable Convex components with isolated tables and app-facing APIs. Use for new components, reusable backend modules, integrations, or component boundary work.
Plans Convex schema and data migrations with widen-migrate-narrow and @convex-dev/migrations. Use for breaking schema changes, backfills, table reshaping, or zero-downtime rollouts.
Creates or adds Convex to an app. Use for new Convex projects, npm create convex@latest, frontend setup, env vars, or the first npx convex dev run.
Sets up Convex auth, identity mapping, and access control. Use for login, auth providers, users tables, protected functions, or roles in a Convex app.
Centralized Claude Skills library — edit once, symlink everywhere.
Rust runtime with TS/Python bindings for Claude Skills with progressive disclosure of skill metadata, full content and scripts/resources. Any agent can now own skills. Currently support Seatbelt and experimentally, WASM, sandboxing
Claude Code learning framework that runs reference-seeded coding lessons through MCP. Brings declarative probes + course/lesson authoring skills; pair with any content plugin (e.g. acc-deepbook-course) to teach a domain.
与吉伊卡哇世界的角色们对话！包含乌萨奇、小可爱、小八、小桃、铠甲人三兄弟、狮萨、海獭、栗子馒头共 10 位角色设定，单一入口按需加载，支持实时切换。适配任何 Markdown Skill/Prompt 格式的 AI Agent 系统。
Agent Skill that writes honest, structured READMEs — classifies your project type, audience & distribution model instead │ │ │ of filling templates. Works with Claude Code, Cursor, Codex, Gemini CLI and more AI agents.
Persona-distillation and AI ethics skill framework themed around idol-style compliance.