dspy-copro
Use when you want to optimize instructions by generating many candidates and picking the best — useful when few-shot demos alone are not enough and you want to…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,660 results
agentcore
Run chrome-use on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS…
sessions
Run multiple isolated browser sessions in parallel (each --session = own cookies/tabs/refs), recover a stranded tab by CDP targetId across sessions,…
agent-update-manager
The English introduction is being prepared.
question-refiner
Refine original research questions into structured deep research tasks. Clarify requirements by asking questions, and generate structured prompts that meet OpenAI/Google Deep Research standards. Use this skill when users raise research questions, need help defining research scope, or want to generate structured research prompts.
edu-solid-geometry
Solve a solid geometry problem into a self-contained interactive teaching webpage: on the left, a step-by-step MathJax explanation; on the right, an interactive Three.js 3D model (step-by-step highlighting + camera switching). Supports three entry points—a given text problem, randomly generated problems, and uploading a problem image for recognition followed by solving. Covers line-plane angles on cubes/rectangular prisms, pyramids/prisms, cylinders/cones, …
skill-template
Copy-paste scaffold for creating a new Antigravity Agent Skill. Use when you want to author a skill folder that follows the official SKILL.md format.
agent-e2e
Discover, record, and execute E2E test cases using browser exploration. Use when exploring test scenarios, recording user flows, organizing test structure, or…
project-memory
Use when setting up, updating, reviewing, repairing, compacting, or summarizing project memory files across Codex, Claude, and other agent sessions.
ljg-skill-map
Generates a real-time ASCII topology of all ljg-* skills, organized by CogOS layers (Intake, Decompose, Synthesize, Create, Reflect, Meta). Use when user says…
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
calm-down
Invoke this skill ONLY when you are actively making edits or executing a plan and the user shows clear frustration with the direction things are going:…
sso-embed
This skill allows agents to assist users in setting up, implementing, and troubleshooting Looker SSO (signed) and Cookieless embedding using the Looker Embed…
lov-clean-mac
Use when cleaning Mac storage, freeing a target capacity, archiving inactive files, or mentioning legacy `lov-macos-disk-optimizer`; plans guarded cleanup,…
lov-install-ai
Quickly initialize production-ready AI capabilities for an existing or new App, with a choice of local Agent Client, MaaS relay channel, model preferences, and accompanying UI. Use when the user says to integrate AI, add chat/generation capabilities to an App, or mentions Agent Client, MaaS, or model selection.
lov-organize-storage
Inventory entire storage drives by project, purpose, and lifecycle, plan safe same-volume renames and migrations, and output mappings, rollback records, and non-deletable gates. Use when a drive or archive folder is messy or needs project-based organization.
cx-init
CX workflow — project initialization. Each project individually confirms developer_id, GitHub sync strategy, agent teams, code review, worktree isolation, auto memory, and establishes a project-level `开发文档/CX工作流 + .cx` runtime truth directory. Only when the user explicitly invokes…
prompt-master
The English introduction is being prepared.
claude-ecosystem
Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles…
claude-code-reverse
Perform read-only static reverse engineering on local executables, application binaries, and version artifacts that the user owns or is explicitly authorized to analyze, including Claude Code and other CLIs, Mach-O, ELF, PE, Wasm, or packaged applications. Use only when the user explicitly requests "reverse engineering, extracting the implementation, checking binary strings/symbols/dependencies, verifying internal behavior, or comparing two versions"; do not trigger it merely because software is mentioned, and do not use it to execute unknown samples, bypass…
personal-arsenal-lifecycle-doctor
Scan and diagnose the health status of the skills in your personal ~/.claude/skills. Use when the user says any of the following: - "My skills stopped working" "After the upgrade, the old skills aren't recognized anymore" - "The skills have rotted" "The external dependencies are broken" "My personal Arsenal is a mess" - "Help me check skill health" "Skill lifecycle" "Long-term skill maintenance" - "The Skill that worked so well for me 1-2 years ago…
dotnet-mcp
Build or consume Model Context Protocol (MCP) servers and clients in .NET using the official MCP C# SDK, including stdio, Streamable HTTP, tools, prompts,…
maple-agent-tracing
Trace an AI agent or LLM app with Maple so each conversation shows up as one Agent Session with its transcript, model calls, tool calls, tokens, cost and…
maple-agent-tracing-agno
Trace Agno agents with Maple: installs the OpenInference Agno instrumentor with an OTLP exporter and GenAI attributes, and sets session_id per conversation so…