Loading...
Loading...
Found 3,437 Skills
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, or memory benchmarks (LoCoMo, LongMemEval).
Build autonomous RAG agents that reason, plan, and use tools for complex retrieval tasks. Use this skill when simple retrieve-and-generate isn't enough. Activate when: agentic RAG, RAG agent, multi-step retrieval, tool-using RAG, autonomous retrieval, query decomposition.
Create new agent skills with best-practice templates. Guides through skill level selection (L0 pure prompt, L0+ with helper scripts, L1 with business scripts), environment strategy (stdlib/uv/venv), and generates ready-to-edit project files following runtime UX best practices. This skill should be used when creating a new skill, scaffolding a skill project, initializing skill templates, or when the user says 'help me build a skill', 'create a skill', '创建技能', '新建 skill'.
Package a agent skill into a complete GitHub repository ready for distribution via skills.sh. Generates README, LICENSE, plugin.json, marketplace.json, .gitignore, and the proper directory structure. Optionally initializes a git repo and creates a GitHub repository. This skill should be used when publishing a skill, packaging a skill for distribution, preparing a skill repo, or when the user says 'publish skill', 'package skill', 'release skill', '发布技能', '打包 skill'.
N coordinated agents on shared task list (compatibility facade over team)
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).
Instruments Python and TypeScript code with MLflow Tracing for observability. Triggers on questions about adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, or tracing specific frameworks (LangGraph, LangChain, OpenAI, DSPy, CrewAI, AutoGen). Examples - "How do I add tracing?", "How to instrument my agent?", "How to trace my LangChain app?", "Getting started with MLflow tracing", "Trace my TypeScript app"
Structured checkpoint format for requesting human input. When an agent needs a decision, it must stop, present context, show options, and wait. Activate when delegating to subagents, running background tasks, or hitting any decision point that requires human judgment.
Set up a full AI ensemble/mob programming team for any software project. Creates team member profiles (.team/), coordinator instructions (.team/coordinator-instructions.md), project owner constraints (PROJECT.md), team conventions (AGENTS.md), architectural decisions (docs/ARCHITECTURE.md), domain glossary, and supporting docs. Use when: (1) starting a new project and wanting a full expert agent team, (2) the user asks to "set up a team", "create a mob team", "set up ensemble programming", or "create agent profiles", (3) converting an existing project to the driver-reviewer mob model, (4) the user wants AI agents to work as a coordinated product team with retrospectives and consensus-based decisions.
Repository housekeeping workflows for AGENTS/CLAUDE architecture, progressive disclosure, and migration of legacy monolithic instruction files.
Dispatch background AI worker agents to execute tasks via checklist-based plans.
Chat with web AI agents (ChatGPT, Gemini, Claude, Grok, NotebookLM) via browser automation. Use when stuck, need cross-validation, or want a second-model review.