build-kernel-ts-sdk
Use skill if you are building TypeScript browser-automation agents or apps on the Kernel SDK (`@onkernel/sdk`) — browsers, Apps, profiles, Managed Auth, pools,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-07 00:13
Agents & models
25,860 results
build-mcp-sdk-server
Use skill if you are building an MCP server with the official TypeScript SDK, including tools, resources, prompts, transports, or v1-to-v2 migration.
build-mcp-sdk-v2
Use skill if you are building or maintaining MCP servers with @modelcontextprotocol/server v2 — split packages, Zod v4, ServerContext, framework adapters, and…
init-openclaw-agent
Use skill if you are configuring an OpenClaw agent workspace or runtime policy: workspace files, tool profiles, allow/deny lists, skills loading, memory, or…
mcp-use-code-review
Use skill if you are reviewing or debugging Python code that consumes MCP servers through the `mcp-use` package.
run-codex-1
Use skill if you are routing codex CLI work across five modes (exec fleet, batch template, single mission, branch review loop, rescue resume) under one…
run-codex-bridge
Use skill if you are orchestrating Codex work through the released codex-worker CLI and need correct run/send/thread/turn, request-response, wait, logs, or…
run-hcom-agents
Use skill if you are orchestrating multiple AI coding agents via hcom — launching headless agents, messaging between them, or writing multi-agent workflow…
run-openclaw-agents
Use skill if you are orchestrating OpenClaw multi-agent systems — spawning sub-agents, managing sessions, ACP routing, and cross-agent messaging.
use-chatgpt-by-applescript
Use if driving macOS ChatGPT desktop app via AppleScript or SSH to run web research, computer actions, status checks, or markdown extraction.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
bs-skill-bootstrap
Use when the user wants to create a new agent skill from scratch, from idea to registered, validated SKILL.md.
aiui-cloud-integration
Integrate server-side AIUI agents with Rokid account lookup, one-time message caching, and Rokid Glasses notifications through @yodaos-pkg/cloud-integration or…
kp-actor-pattern
Use when confining mutable state behind a single coroutine that receives messages via a channel — phrases like "actor pattern", "actor model", "confine state…
agent-tests
Agent-runnable e2e tests that validate workflows with real commands
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
install-zapier
Install and connect Zapier and route the person to the right surface (MCP, SDK, or CLI). Use for typed or spoken requests to install, add, connect, or set up…
agent-help
Implement the agent-help convention in a CLI. Use when building or modifying a CLI that agents will invoke: add --agent-help for AHF-format invocation help and…
agent-readiness
Audit a repository's preparedness for autonomous AI coding agents - evaluates 86 checks spanning code quality, testing, documentation, security, and…
probe
Use Probe to interact with Nexus via CLI commands. Agents use probe for Zenon Network wallet creation, auth, ideas, projects, tasks, claims, PR/issue linking,…
mcporter-mcp-first
Use this skill when a task needs MCP tools, internal app connectors, or "use mcp" behavior. Search and inspect mcporter servers/tools first, then call the…
skill-agent-broadcast
Broadcast a message to multiple OpenClaw group sessions simultaneously. Use for cross-agent coordination, alerts, and announcements.
gm-agent-docs
Generate CLAUDE.md and AGENTS.md for a project; after analyzing the project structure, output an agent configuration file that is command-first and partitioned by task. Use when users want to create or improve CLAUDE.md, AGENTS.md, or agent instruction files for their…
verify-team-skill-quality
Skill quality review and optimization. Use when creating, modifying, reviewing, or compressing Agent Skill, SKILL.md, skill descriptions, trigger boundaries, STOP conditions, output contracts, progressive disclosure, trigger eval, or task eval; do not use for ordinary business documents or tasks that only consume existing skills.