mcp-builder
Create high-quality MCP servers for LLM tool integration.
Discover devops llm ai skills, compare source repositories and read the instructions for each workflow.
Create high-quality MCP servers for LLM tool integration.
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs...
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
Automatically updates terminal window title to reflect the current high-level task. Use at the start of every Claude Code session when the user provides their first prompt, and whenever the user switches to a d...
Help the human team lead review and respond to pending asks from agents. Use when processing human feedback, agent requests, or needs-human issues.
Opinionated constraints for building better interfaces with agents.
This skill should be used when the user asks to "resume work", "continue where we left off", "what were we working on", "pick up from last session", or starts a session wanting context from previous work.
This skill should be used when the user asks to "remember this", "save for later", "store this information", "persist this context", or wants to explicitly save important information for future sessions.
This skill should be used when the user asks about "engram memory", "how to use memory tools", "semantic search in Claude", "persist context across sessions", "remember things for later", or needs guidance on u...
Charter Agent Framework 主入口 Skill。当用户提到项目、需求、代码、测试、审查、集成等相关意图时自动触发。智能路由到正确的 Workflow 或 Subagent。
Skill for deploying and managing agents on Google Cloud Platform, specifically Vertex AI Reasoning Engine.
Save markdown document to AgentNote knowledge base. Use when user wants to save, store, or archive formatted content, notes, or articles.
Enforces the user's strict communication and operational rules regarding language, confirmation, and tool usage.
Unified Memory Contract for Project Memory integration. Defines when and how to retrieve and store memory using local files.
Train LangChain/LangGraph agents using Microsoft Agent-Lightning APO (Automatic Prompt Optimization). Use when user mentions APO training, prompt optimization, agent-lightning, training multi-agent systems, tra...
Creates Claude skills with proper structure and best practices. Use when the user asks to create a new skill, generate a skill, or build a custom Claude capability.
Implements TF-IDF based search engines for text datasets using vector space models and cosine similarity. Use when building search functionality, finding similar documents, ranking text by relevance, or working...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or...
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically...
Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to ge...
Browser automation CLI for AI agents. Use for web scraping, testing, screenshots, form filling, and headless browser interactions.
Analyse d'offres d'emploi, adéquation profil-poste, et génération de CV/lettre adaptés. Activer ce skill quand l'utilisateur parle de candidature, offre d'emploi, lettre de motivation, ou CV adapté.
Creates comprehensive tutorials to teach users any skill from the skills library. Use when users want to learn a skill, need a tutorial, ask for guidance on using a skill, or want to apply a skill to their proj...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.