エージェントができること
- Plan multi-step tasks before executing code changes
- Dispatch and coordinate subagents for parallel work
- Debug systematically with structured investigation
- Run review loops and quality gates before shipping
- Manage context and memory across long sessions
- Integrate MCP tools and external APIs safely
このトピックのスキル
| Skill | Description | Source | Install |
|---|---|---|---|
| openclaw/openclaw | Personal AI agent that lives on your device; viral local-first assistant reaching 210k+ stars in 2026. | openclaw/openclaw | |
| obra/dispatching-parallel-agents | Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | obra/superpowers | |
| obra/subagent-driven-development | Use when executing implementation plans with independent tasks in the current session | obra/superpowers | |
| ollama/ollama | The foundation for local agent deployment, allowing private execution of large language models. | ollama/ollama | |
| skill-creator | Create, test, and publish new skills from within your agent | anthropics/skills | |
| langflow-ai/langflow | Langflow is a powerful tool for building and deploying AI-powered agents and workflows. | langflow-ai/langflow | |
| open-webui/open-webui | User security authorization handlers securing distributed agent workspaces against unauthorized data inspection passes. | open-webui/open-webui | |
| anthropics/claude-code | An agentic coding tool that lives in your terminal, understands your codebase, and executes routine development tasks natively. | anthropics/claude-code | |
| Shubhamsaboo/awesome-llm-apps | 100+ ready-to-run AI agent and RAG templates covering earnings calls, insurance, and travel planning. | Shubhamsaboo/awesome-llm-apps | |
| google-gemini/gemini-cli | An open-source AI agent that brings the power of Gemini directly into your terminal. | google-gemini/gemini-cli | |
| browser-use/open-source | Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead. | browser-use/browser-use | |
| browser-use/remote-browser | Controls a local browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels. | browser-use/browser-use | |
| tiangolo/fastapi | Boilerplate setup to deploy multi-agent streaming JSON interfaces over asynchronous WebSockets securely. | tiangolo/fastapi | |
| lobehub/lobehub | 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. | lobehub/lobehub | |
| ComposioHQ/awesome-claude-skills | A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows | ComposioHQ/awesome-claude-skills | |
| code-yeongyu/oh-my-openagent | omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode | code-yeongyu/oh-my-openagent | |
| microsoft/autogen | A web interface prototype enabling non-developers to curate multi-agent workflows and evaluate task progression tracks graphically. | microsoft/autogen | |
| mem0ai/mem0 | The Memory Layer for AI Agents. Personalizes agent workflows by maintaining continuous semantic context profiles over time. | mem0ai/mem0 | |
| crewAIInc/crewAI | Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly. | crewAIInc/crewAI | |
| mudler/LocalAI | Free Open-Source alternative to OpenAI. Provides embedded orchestration skills for entirely offline air-gapped security models. | mudler/LocalAI | |
| block/goose | an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM | block/goose | |
| gradio-app/gradio | Rapid prototyping components built to display multi-modal input arrays alongside cascading multi-agent decision steps. | gradio-app/gradio | |
| ChromeDevTools/chrome-devtools-mcp | Chrome DevTools for coding agents | ChromeDevTools/chrome-devtools-mcp | |
| phidatahq/phidata | Reference blueprint patterns showcasing proper tool setups and context loading configurations for enterprise agent instances. | phidatahq/phidata | |
| wshobson/agents | Intelligent automation and multi-agent orchestration for Claude Code | wshobson/agents | |
| Textualize/textual | Python TUI framework used to build terminal interfaces showing agent thought-loops, tool status, and execution streams. | Textualize/textual | |
| reworkd/AgentGPT | Assemble, configure, and deploy autonomous AI Agents directly in your web browser. | reworkd/AgentGPT | |
| addyosmani/deprecation-and-migration | Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code. | addyosmani/agent-skills | |
| addyosmani/shipping-and-launch | Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | addyosmani/agent-skills | |
| addyosmani/git-workflow-and-versioning | Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams. | addyosmani/agent-skills | |
| addyosmani/ci-cd-and-automation | Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies. | addyosmani/agent-skills | |
| addyosmani/debugging-and-error-recovery | Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing. | addyosmani/agent-skills | |
| addyosmani/test-driven-development | Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality. | addyosmani/agent-skills | |
| addyosmani/using-agent-skills | Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked. | addyosmani/agent-skills | |
| addyosmani/security-and-hardening | Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. | addyosmani/agent-skills | |
| addyosmani/idea-refine | Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan". | addyosmani/agent-skills | |
| addyosmani/incremental-implementation | Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step. | addyosmani/agent-skills | |
| addyosmani/context-engineering | Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project. | addyosmani/agent-skills | |
| addyosmani/code-simplification | Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity. | addyosmani/agent-skills | |
| addyosmani/documentation-and-adrs | Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase. | addyosmani/agent-skills | |
| addyosmani/performance-optimization | Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing. | addyosmani/agent-skills | |
| addyosmani/spec-driven-development | Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea. | addyosmani/agent-skills | |
| addyosmani/planning-and-task-breakdown | Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible. | addyosmani/agent-skills | |
| addyosmani/code-review-and-quality | Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. | addyosmani/agent-skills | |
| 1Panel-dev/1Panel | 🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface. | 1Panel-dev/1Panel | |
| CopilotKit/CopilotKit | The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol | CopilotKit/CopilotKit | |
| AstrBotDevs/AstrBot | AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨ | AstrBotDevs/AstrBot | |
| microsoft/playwright-mcp | Official Playwright MCP server. 30k+ stars. Browser automation with accessibility snapshots, Chromium/Firefox/WebKit, 22 tools | microsoft/playwright-mcp | |
| TabbyML/tabby | Self-hosted AI coding assistant backend featuring low-latency code completion agent skills over internal corporate repos. | TabbyML/tabby | |
| getcursor/cursor | Direct IDE integrations providing agents the skill to rewrite codebase contexts safely based on natural language feedback. | getcursor/cursor |
openclaw/openclaw
Personal AI agent that lives on your device; viral local-first assistant reaching 210k+ stars in 2026.
openclaw/openclaw
npx skills add openclaw/openclaw
obra/dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
obra/superpowers
npx skills add obra/superpowers
obra/subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
obra/superpowers
npx skills add obra/superpowers
ollama/ollama
The foundation for local agent deployment, allowing private execution of large language models.
ollama/ollama
npx skills add ollama/ollama
skill-creator
Create, test, and publish new skills from within your agent
anthropics/skills
npx skills add anthropics/skills
langflow-ai/langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
langflow-ai/langflow
npx skills add langflow-ai/langflow
open-webui/open-webui
User security authorization handlers securing distributed agent workspaces against unauthorized data inspection passes.
open-webui/open-webui
npx skills add open-webui/open-webui
anthropics/claude-code
An agentic coding tool that lives in your terminal, understands your codebase, and executes routine development tasks natively.
anthropics/claude-code
npx skills add anthropics/claude-code
Shubhamsaboo/awesome-llm-apps
100+ ready-to-run AI agent and RAG templates covering earnings calls, insurance, and travel planning.
Shubhamsaboo/awesome-llm-apps
npx skills add Shubhamsaboo/awesome-llm-apps
google-gemini/gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
google-gemini/gemini-cli
npx skills add google-gemini/gemini-cli
browser-use/open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead.
browser-use/browser-use
npx skills add browser-use/browser-use
browser-use/remote-browser
Controls a local browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels.
browser-use/browser-use
npx skills add browser-use/browser-use
tiangolo/fastapi
Boilerplate setup to deploy multi-agent streaming JSON interfaces over asynchronous WebSockets securely.
tiangolo/fastapi
npx skills add tiangolo/fastapi
lobehub/lobehub
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
lobehub/lobehub
npx skills add lobehub/lobehub
ComposioHQ/awesome-claude-skills
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
ComposioHQ/awesome-claude-skills
npx skills add ComposioHQ/awesome-claude-skills
code-yeongyu/oh-my-openagent
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
code-yeongyu/oh-my-openagent
npx skills add code-yeongyu/oh-my-openagent
microsoft/autogen
A web interface prototype enabling non-developers to curate multi-agent workflows and evaluate task progression tracks graphically.
microsoft/autogen
npx skills add microsoft/autogen
mem0ai/mem0
The Memory Layer for AI Agents. Personalizes agent workflows by maintaining continuous semantic context profiles over time.
mem0ai/mem0
npx skills add mem0ai/mem0
crewAIInc/crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly.
crewAIInc/crewAI
npx skills add crewAIInc/crewAI
mudler/LocalAI
Free Open-Source alternative to OpenAI. Provides embedded orchestration skills for entirely offline air-gapped security models.
mudler/LocalAI
npx skills add mudler/LocalAI
block/goose
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
block/goose
npx skills add block/goose
gradio-app/gradio
Rapid prototyping components built to display multi-modal input arrays alongside cascading multi-agent decision steps.
gradio-app/gradio
npx skills add gradio-app/gradio
ChromeDevTools/chrome-devtools-mcp
Chrome DevTools for coding agents
ChromeDevTools/chrome-devtools-mcp
npx skills add ChromeDevTools/chrome-devtools-mcp
phidatahq/phidata
Reference blueprint patterns showcasing proper tool setups and context loading configurations for enterprise agent instances.
phidatahq/phidata
npx skills add phidatahq/phidata
wshobson/agents
Intelligent automation and multi-agent orchestration for Claude Code
wshobson/agents
npx skills add wshobson/agents
Textualize/textual
Python TUI framework used to build terminal interfaces showing agent thought-loops, tool status, and execution streams.
Textualize/textual
npx skills add Textualize/textual
reworkd/AgentGPT
Assemble, configure, and deploy autonomous AI Agents directly in your web browser.
reworkd/AgentGPT
npx skills add reworkd/AgentGPT
addyosmani/deprecation-and-migration
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/shipping-and-launch
Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/debugging-and-error-recovery
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/test-driven-development
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/using-agent-skills
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/security-and-hardening
Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/incremental-implementation
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/documentation-and-adrs
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/performance-optimization
Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
addyosmani/code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
addyosmani/agent-skills
npx skills add addyosmani/agent-skills
1Panel-dev/1Panel
🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
1Panel-dev/1Panel
npx skills add 1Panel-dev/1Panel
CopilotKit/CopilotKit
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
CopilotKit/CopilotKit
npx skills add CopilotKit/CopilotKit
AstrBotDevs/AstrBot
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
AstrBotDevs/AstrBot
npx skills add AstrBotDevs/AstrBot
microsoft/playwright-mcp
Official Playwright MCP server. 30k+ stars. Browser automation with accessibility snapshots, Chromium/Firefox/WebKit, 22 tools
microsoft/playwright-mcp
npx skills add microsoft/playwright-mcp
TabbyML/tabby
Self-hosted AI coding assistant backend featuring low-latency code completion agent skills over internal corporate repos.
TabbyML/tabby
npx skills add TabbyML/tabby
getcursor/cursor
Direct IDE integrations providing agents the skill to rewrite codebase contexts safely based on natural language feedback.
getcursor/cursor
npx skills add getcursor/cursor