n8n-multi-instance
Use when an n8n-mcp account targets more than one n8n instance — i.e. the `n8n_instances` tool is available, the user mentions multiple n8n instances or…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Agents & models
24,945 results
jwt-auth
Implement secure JWT authentication with refresh token rotation, secure storage, and automatic renewal. Use when building authentication for SPAs, mobile apps,…
agent-memory
Add memory capabilities to your agent. Use when: (1) User asks about 'memory', 'state', 'remember', 'conversation history', (2) Want to persist conversations…
authoritative-server
Build multiplayer Decentraland scenes with a headless authoritative server. Covers isServer() branching, registerMessages() for client-server communication,…
camera-control
Control camera behavior in Decentraland scenes. CameraMode detection, CameraModeArea (force first/third person in regions), VirtualCamera (cinematic scripted…
self-improve
Update skill documentation and extend OpenCode capabilities based on learnings
llm-wiki
Build and maintain a personal knowledge base Wiki. Use when the user needs to collect and organize knowledge, manage research notes, build a persistent knowledge system, or document problem-solving experience.
kuroco-admin-mcp
Supports connection setup, authentication, and tool usage for Kuroco Admin MCP (the Admin MCP server). This is the recommended means for performing Kuroco administrative operations from AI agents, with OAuth 2.0 / CIMD authentication, scopes (mcp:admin / mcp:tools.all / mcp:tools.write /…
cook-parallel
[Implementation] Parallel implementation - multiple tasks simultaneously
mcp-builder
[AI & Tools] Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
orchestration
Orchestrate complex work through parallel agent coordination. Decompose tasks into parallel lanes, iterate with verify loops, spawn background workers, and…
setup-auto-handoff
Set up a Claude Code PreCompact hook that blocks compaction until a fresh handoff exists in .agents/handoffs/, so a session reaching its context limit never…
find-skills
Helps users discover and install capabilities from the open agent skills ecosystem. Use when users ask "how do I do X" for specialized tasks, request "find a…
openclaw
Deploy and configure OpenClaw AI gateway on KASM workspaces or standalone Docker. Multi-provider LLM routing (Anthropic, OpenAI, Gemini, Groq, Bedrock) with…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores,…
stitch-mcp-generate-variants
Generates design variants of existing Stitch screens using the native variant API. Explore alternative layouts, color schemes, fonts, or content with…
orchestrate
Conductor: coordinate Task subagents with bounded worker briefs from the parent’s inline execution context, then report progress in chat.
claude-use-gemini-acp
Delegate a sub-task to Gemini CLI via the Agent Client Protocol (ACP). Use this skill whenever you want to hand off work to Gemini — large-context…
heartbeat
Agentic OS Orchestrator. Process and execute tasks from the shared .agent/state/tasks.json queue. Use when the user asks to 'check the queue', 'process tasks',…
new-skill
Scaffold a new skill directory under skills/ that passes scripts/audit_skills.py on first run. Use when adding a new portable agent skill to this repo.
step-by-step
when configuring step-by-step workflows — agent work with manual actions, rollout checklists, human-in-the-loop confirmation. MCP-compatible. Not for…
repair-agent
This skill should be used when the user asks to "repair an agent", "audit an agent", "fix my agent", "review agent quality", "check if my agent is…
update-claudemd
This skill should be used when the user says "update CLAUDE.md", "refresh CLAUDE.md", "sync CLAUDE.md with the codebase", "reorganize CLAUDE.md", "optimize…
i18n
Audit internationalization coverage and find hardcoded strings. Use when asked to "check i18n", "find hardcoded strings", or verify translation coverage. Don't…