tk
Git-backed ticket management for AI agents
Browse AI and ML workflow skills for model integration, prompt engineering, evaluations, and LLM automation across major IDEs.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
Git-backed ticket management for AI agents
pr-creator is an open-source AI agent that streamlines Pull Request creation. It guides you through branch management and commit best practices.
Un serveur MCP est un environnement de développement qui utilise TypeScript et les outils Lightdash pour ajouter des ressources et des promtps de manière efficace
Les compétences THOR sont un ensemble de compétences pour les LLM qui permettent de router les demandes et d'appliquer des règles globales
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: AI SDK, Vercel AI SDK, generateText, streamText, add AI to my app, build an agent, tool calling, structured output, useChat.
Write, critique, and iterate prompts for OpenAI GPT-5 series models. Use for tasks like: (1) turning vague requirements into high-signal instructions, (2) selecting between quick vs deep reasoning behaviors, (3) creating robust structured-output prompts (JSON schemas, tool calls), (4) designing evaluation prompts and rubrics, and (5) debugging prompt failures (hallucinations, format drift, tool misuse). Trigger when the user mentions GPT-5, prompt engineering, system/developer messages, structured outputs, agent prompts, or wants best-practice templates.
Converts markdown plans into beads (tasks with dependencies) and polishes them until implementation-ready. The bridge between planning and agent team execution. Use when converting a plan to beads, polishing bead descriptions, adding test coverage beads, reviewing bead dependencies, or preparing tasks for parallel agent team execution.
Un agent de Claudecode est un objet JSON qui définit une série de commandes et d'actions pour automatiser des tâches dans la CLI de Claudecode.
🚀 39+ battle-tested Claude Code skills & 9 specialized agents for professional software development. The most comprehensive skill library for Claude Code.
Thirdweb v5 SDK usage in AutoClaw. Use when working with wallet connection, social login, SIWE authentication, or thirdweb client/provider setup. Triggers on: thirdweb, wallet connect, inAppWallet, social login, SIWE, ConnectButton, thirdweb auth, thirdweb provider.
Use the Atlassian MCP Server to interact with JIRA from coding agents (Cursor, Claude Code). This skill documents how to use the official Atlassian MCP server for JIRA and Confluence operations. Enable this MCP server in your Cursor/Claude Code settings for JIRA access.
View call logs for the Vocal Bridge voice agent. Can list recent calls or show details of a specific session including transcript.