Multi-agent workflows, orchestration frameworks, and autonomous runs.
Tools for running more than one agent, or one agent for longer than a single turn. This covers orchestration frameworks that split work across sub-agents, planning loops that decompose a task before executing it, handoff patterns, and harnesses that keep long autonomous runs from drifting. Useful when a job is too big for one prompt and you need structure rather than a bigger context window.
Ranked by GitHub stars. Search to find fast, or page through the full list.
Cua (Computer Use Agent) mono-repo
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.
This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies, and neuro-symbolic AI integration.
Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, token usage, and quality metrics. NOTE: Reliability, Cost, Safety, and Security alerts use generic OTel metrics and work across runtimes (e.g., Cloud Run, Vertex AI). Quality alerts rely on Vertex AI Online Monitors and are strictly bound to Vertex AI deployments.
This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model evaluations.
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For general production deployment, use agent-platform-deploy.
Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.
Use when adding A2UI rendering to any AG-UI-supported framework or custom AG-UI application, scaffolding an AG-UI app that should render A2UI, adapting an AG-UI integration to emit A2UI surfaces, or wiring the AG-UI A2UI middleware/toolkit with a compatible renderer.
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when you need to generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
Security auditing for code, configs, and infrastructure. Use when the user wants to audit or improve security: scan for vulnerabilities (SQL injection, XSS, command injection, path traversal), detect hardcoded secrets and credentials, review auth and authorization, check dependencies for known CVEs, audit config files for insecure defaults, or generate security reports. Trigger on "security audit", "vulnerability scan", "code review for security", "find secrets", "check for vulnerabilities", "OWASP", "CVE", or questions about code security.
Generates a Gemini LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate a client that connects to the Gemini Enterprise LiveAPI websocket endpoint, handles session setup/resumption, bearer token refresh, and sending/receiving ClientMessage/ServerMessage protos. Don't use for general (non-live, non-bidirectional) Gemini API usage such as one-shot generateContent, embeddings, image/video generation, or fine-tuning — use the gemini-api skill for those.
Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 79 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 18 market-data sources (tushare, yfinance, okx, akshare, baostock, tencent, mootdx, ccxt, futu, local, eastmoney, sina, stooq, yahoo, plus optional-key finnhub/alphavantage/tiingo/fmp).
Official GSAP skills for Claude, Cursor, and other AI agents — animations, timelines, ScrollTrigger, plugins, utilities, React, and performance
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
Full Stack MCP framework for python, build MCP agents, clients, and servers.
Generate production-quality SVG+PNG technical diagrams from natural language.
The team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation). Claude Code용 팀 아키텍처 팩토리: 도메인 한 문장을 에이전트 팀과 스킬 세트로 변환하는 메타 스킬.
GitMCP is a tool that allows you to get the documentation for a given repository.
Unified AI router with 160+ providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.
Agent Framework For Fintech
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
TypeScript multi-agent framework: one runTeam() call from goal to result. Auto task decomposition and parallel execution for multi-step LLM jobs. Deploys anywhere Node.js runs.
Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, or Claude Code, apply an author's frameworks while working, or build a reusable knowledge base from a file.
MCP server that provides session-scoped tools (SubmitPlan, config_validate, etc.) to Codex via stdio transport
Feishu/Lark Integration plugin bundle
CUA Computer Use Runtime plugin bundle
CLI tool for managing Klavis AI MCP servers in Google Gemini CLI
Generate AntV Infographic syntax outputs. Use when asked to turn user content into the Infographic DSL (template selection, data structuring, theme), or to output infographic <template> plain syntax.
DeepChat app settings modification (DeepChat 设置/偏好) skill. Activate ONLY when the user explicitly asks to change DeepChat's own settings/preferences (e.g., theme, language, font size...). Do NOT activate for OS/system settings, editor settings, or other apps.
Autonomous improvement engine. 14 commands: iterate, plan, debug, fix, security, ship, scenario, predict, learn, reason, probe, improve, evals, regression.
DeepChat，一个简单易用的 Agent 客户端
Shape pitches, brand stories, presentations, and creative writing with narrative frameworks such as the Hero's Journey, Story Spine, and Freytag's Pyramid. Use when a user wants to structure, critique, or strengthen a story.
Prepare a concise exam review from study materials and a syllabus supplied by the user. Use for topic summaries, recall questions, MCQ cues, and time-limited revision plans that must stay grounded in those materials.
Generate low-stakes retrieval-practice questions with grounded answer notes and implementation guidance. Use for quiz starters, revision activities, delayed recall, misconception checks, or adapting recall difficulty.
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
Recommend practical study strategies matched to the material, learning goal, assessment, time, and learner constraints. Use for revision planning, homework routines, independent study, replacing ineffective habits, or adapting recall, spacing, explanation, and practice activities.
Draft or reformat copy-paste-ready LinkedIn posts from user-provided ideas and source material. Use for professional posts, concise thought-leadership drafts, resource announcements, story-led posts, carousel text, or optional Unicode emphasis with an accessible plain-text alternative.
Draft flexible daily or weekly schedules around a user's priorities, availability, energy patterns, and fixed commitments. Use for day planning, deadline reverse-planning, focus protection, or a time audit.
Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.