handoff-gemini
Delegate tasks to Gemini CLI to save Claude context
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,710 results
mcp-check
Validate MCP configuration and suggest improvements
apify
Apify integration for AI agents via ClawLink — browser login, no API key setup. Connect Apify through ClawLink's hosted setup to run web scrapers, manage…
app-integrations
Connect Gmail, Notion, Slack, GitHub, Google Workspace (Drive, Docs, Sheets, Calendar), HubSpot, Shopify, LinkedIn, and 1,000+ other apps to your agent through…
freeagent
FreeAgent integration for AI agents via ClawLink — browser login, no API key setup. Connect FreeAgent through ClawLink's hosted setup to manage invoices,…
heygen
HeyGen integration for AI agents via ClawLink — browser login, no API key setup. Connect HeyGen by pasting your API key. Watch the short video on the connect…
hugging-face
Hugging Face integration for AI agents via ClawLink — browser login, no API key setup. Connect Hugging Face through ClawLink's hosted setup to manage models,…
openai
OpenAI integration for AI agents via ClawLink — browser login, no API key setup. Connect openai through ClawLink's hosted setup. Use this skill when the user…
youtube
YouTube integration for AI agents via ClawLink — browser login, no API key setup. Connect YouTube through ClawLink's hosted setup to manage videos, playlists,…
agent discovery
Structured repository scanning and agent evaluation skill for discovering agents from the AI ecosystem
g-pilot fleet operations
Protocol for orchestrating multi-agent missions using Google Workspace and Gemini reasoning.
g-pilot tool architect
Guidelines for building "Skill Modules" that the G-Pilot Architect can plan and the Executor can deploy.
cobo-agentic-wallet-developer
Developer guide for integrating the Cobo Agentic Wallet SDK into AI agents, bots, and automation pipelines. Covers SDK installation (Python/TypeScript), `caw`…
multi-agent-orchestration
Decide when to split work across multiple agents vs one agent with tools, and design the handoffs when you do. Use when the user is sketching a multi-agent…
mcp-orchestrator
Discover available MCP servers, evaluate their fit, install and configure them safely, and then use them effectively within sessions. Use when the user needs…
subagent-arena
Run parallel independent subagents on the same investigation or design question, collect structured outputs, then synthesize the best elements or score…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
init-deep
(builtin) Initialize hierarchical AGENTS.md knowledge base
start-work
Execute a Prometheus work plan in Codex with Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation. Use…
ulw-loop
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
start-work
Execute a Prometheus work plan with Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation. Use after…
pi-goal
Persistent Codex-style goal tracking for pi. Use when the user explicitly asks to set, continue, audit, pause, resume, complete, or inspect a long-running goal.
prompt-engeneering
Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this…
codebase-arena
Build, execute, and judge human-reviewed Chinese-English bilingual codebase capability benchmarks. Use when an agent must generate a repository-specific…