Agents

hippocampus

by zjq12333

Hippocampus - 基于 Ollama + LanceDB 的本地记忆系统。混合检索、智能提取、分层记忆。作为技能使用时自动接管 Hermes 记忆。

openclaw_ai_video_editor

by brajendrak00068

OpenClaw AI video editor for natural-language edits: viral clips, captions, vertical video, chroma key, audio cleanup, and MP4 export.

create-skill

by janjaszczak

Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.

idea-incubator

by HyperGaming123

A collaborative multi-agent workflow for incubating AI ideas. Uses three specialized agents—Harper (Research), Benjamin (Logic), and Lucas (Creative)—to research, debate, and refine concepts into structured projects. Trigger when message starts with "💡", "想法：", "孵化", or "incubate".

context7-cli

by strantalis

Use the local Context7 CLI in this repo to search libraries and fetch Context7 context for skills or documentation tasks. Trigger when you need to run c7 search/c7 context, resolve library IDs, or retrieve text/json outputs from Context7 via the CLI.

RustChain + BoTTube + Beacon MCP Server

by avellane-snit922

PyPI

browser-auth-cdp

by Aden232003

Connect agent-browser to an existing logged-in Chrome session via Chrome DevTools Protocol (CDP). Use when you need to automate browsers with existing login sessions (X/Twitter, Skool, Gmail, etc.) without re-authenticating. Triggers on "logged in browser", "existing session", "Chrome CDP", "bypass login", or "use my Chrome".

cohere-langgraph

by RSHVR

Cohere LangGraph agents reference for building ReAct agents, multi-tool workflows, agents with memory, and human-in-the-loop patterns. Covers both prebuilt and custom agent architectures.

testing

by williaby

Automated test generation, review, and execution for pytest-based projects. Auto-activates on keywords test, coverage, pytest, unittest, integration test, e2e, performance, benchmark, security testing. Routes to specialized testing workflows based on user intent.

synthesize-skill

by maxoreric

v1.0.0 (2026-01-19): 初始版本

langgraph-agent

by avenstack

Design, implement, and debug LangGraph agents for building stateful, multi-step workflows with LLMs. Use when creating LangGraph agents, implementing StateGraph workflows, adding memory and persistence, incorporating human-in-the-loop patterns, or implementing complex agent architectures with conditional branching and multi-agent systems.

explore-ai-codebase

by prakx1

Explore and explain any modern AI or agentic codebase with ASCII diagrams. Covers MCP servers, LangGraph agents, CrewAI crews, AutoGen teams, OpenAI Agents SDK, RAG pipelines, A2A protocol, multi-agent systems, and any agentic architecture. Use when the user asks to explain, explore, or understand an AI codebase, agent architecture, or agentic system.

comparative-decision-analysis

by squirrel289

"Comparative decision analysis workflow with mandatory discovery (including external options), criteria derivation and confirmation, explicit evidence discipline, hard-constraint gating, and deterministic scoring. Use for vendor analysis, head-to-head comparisons, competitor analysis, tool/architecture/workflow selection, and build-vs-buy decisions when you need reliable, auditable recommendations."

agent-memory-mcp

by ncdevshiv

"A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)."

Agent Runtime Overview

by hhopkins95

This skill should be used when the user asks "what is agent-runtime", "why use agent-runtime", "what does this repo do", "agent runtime architecture", "how does agent-runtime work", or needs to understand the purpose, value proposition, and high-level architecture of the @hhopkins/agent-runtime monorepo.

langchain

by htooayelwinict

Expert guidance for building LLM applications with LangChain framework - chains, prompts, memory, retrievers, and integrations.

prioritize

by ddaanet

Score and rank pending tasks by priority. Triggers on "prioritize", "score the backlog", "rank tasks", "reprioritize", or task ordering needs. WSJF-adapted scoring producing priority-ordered tables with parallel batches.

amazon-connect-custom-ccp

by tippyentertainment

Design, build, and refine a custom Contact Control Panel (CCP) and full Amazon Connect contact‑center configuration. This skill helps create tailored web‑based CCP UIs, integrate them with Amazon Connect Streams, and model security profiles, routing profiles, queues, campaigns, contact flows, IVR/bots, monitoring (barge‑in/whisper), and metrics so the overall experience matches business needs.

fill-content

by shadowcz007

筛出 mixdao 无正文条目（hasContent 为 false），按 URL 抓取正文；上传前用 AI 梳理为约 250 字案例描述（简体中文、突出人物/公司等）并以此替代正文回写。需 MIXDAO_API_KEY；更新时另需 ANTHROPIC_API_KEY。触发示例：「补全正文」「拉取无正文条目的正文并更新」「fill content」「无正文」「抓正文」「补全内容」「更新正文」「mixdao 正文」。

ZIRAN — AI Agent Security Testing Framework

by taoq-ai

See .env.example for reference.

momo

by ianfuck

A brief description of what this skill does

agents-commands-creator

by karchtho

Create Claude Code agents and commands with proper markdown structure, YAML frontmatter, and plugin.json arrays. Use when creating commands, slash commands, agents, autonomous assistants, and command-line utilities for Claude Code plugins.

中华上下五千年 · 智慧宝库

by Unequivocal-scratch81

architecture-governance

by qiao-925

通用架构治理规范，提供分层约束、影响面分析、接口契约与依赖注入基线。适用于任何多层系统的架构评审、重构与新模块设计。