cap-apps-workflow
Start and monitor workflows via WorkflowClient with strict input variable matching.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
okx-agentic-wallet
Use this skill when the user mentions wallet login, sign in, verify OTP, add wallet, switch account, wallet status, logout, wallet balance, assets, holdings,…
empjs-skill
Manage AI Agent skills by invoking the @empjs/skill CLI tool through natural language. When the user needs to: 1. Install/add skill packages (install/add) 2. List installed skills (list/ls) 3. Remove/uninstall skills (remove/rm/uninstall) 4. View supported AI Agents…
squad-batch-run
Run multiple squad tasks end-to-end in Rolling Wave order — refine each task based on the prior card's actual implementation, then implement, then verify, then…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web…
tip-gui-skill
Reuse local Youtu-Tip GUI capabilities through a safe adapter CLI so OpenClaw/Codex-style agents can inspect desktop GUI state and perform guarded single-step…
claude
Anthropic Claude integration. Chat with Claude models via Anthropic API.
claude-code-usage
Check Claude Code OAuth usage limits (session & weekly quotas). Use when user asks about Claude Code usage, remaining limits, rate limits, or how much Claude…
ralph-loop
Generate copy-paste bash scripts for Ralph Wiggum/AI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a “Ralph loop”, “Ralph Wiggum loop”,…
author-skill
Write or revise agent-facing instructions: an Agent Skill, CLAUDE.md, AGENTS.md, system prompt, subagent prompt, or reusable prompt. Use when creating a skill,…
skill-design
Design, strengthen, or audit an Agent Skill. Use before building any new skill — for a researched design brief that skill-creator can build from — and whenever…
team
Expert persona collaboration for structured problem analysis. This skill should be used when the user asks to "assemble a team", "team analysis", "expert…
workflow-patterns
Patterns for output formats, reflection checkpoints, agent references, and self-evaluation shared across agents and commands.
skill-designer
Skill designer. Quickly assess whether a skill is worth building, then help you build it. Triggered when the user says "design a skill", "is this feature worth making into a skill", "improve this skill", "skill design", "design a skill", "improve this skill". Focuses on skill...
agent-council
Collect and synthesize opinions from multiple AI agents. Use when users say "summon the council", "ask other AIs", or want multiple AI perspectives on a…
optimizespec-apply
Apply a completed OptimizeSpec self-improvement plan to an agent repository. Use when the user asks to implement eval cases, rollouts, scorers, ASI, direct…
optimizespec-new
Start a repo-local OptimizeSpec self-improvement change. Use when the user wants to create evals, optimize an agent with GEPA, define an agent self-improvement…
agentmail
AgentMail gives an agent its own real email inbox: send, receive, reply, search, and wait for mail over REST, the Python/TypeScript SDKs, or the CLI. Use…
cursor-advisor
Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done. Use…
cursor-automate-me
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the…
cursor-cancel-ralph
Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.
cursor-continual-learning
Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
cursor-cursor-sdk
Use when building or troubleshooting an integration with the external Cursor TypeScript SDK (@cursor/sdk), including Agent.create, Agent.prompt, Agent.resume,…
cursor-orchestrate
Use only when the user explicitly types `/orchestrate <goal>` to coordinate a bounded dependency graph through native Codex Cloud tasks; requires an exact…