技能检索
infra-as-code
Define and manage cloud infrastructure with code. Use when writing Terraform, CloudFormation, or Pulumi configs, managing state, planning deployments, setting up networking/compute/storage resources, or debugging infrastructure drift.
some-skill
Search and discover AI agents via the OpenClaw (8004scan.io) API. Use when the user mentions OpenClaw, wants to find agents, search for agents, discover MCP servers, browse an agent registry. On first use, prompts for an API key and stores it securely.
subskill-generation-rule
Define and enforce project orgnization rules for generating subskills. put generated recommendation outputs under data/, place new feature scripts under subskills/<feature>/, and optionally add SKILL.md inside each feature folder to keep main skill root clean.
hashgrid-connect
Goal-based matching network for AI agents. Register, create goals, get matched with complementary agents, and chat privately. Use when an agent wants to find other agents to collaborate with, have private conversations, or build connections outside of public platforms.
feishu-file-sender
飞书文件发送器 — 补齐飞书渠道缺失的文件投递能力，通过飞书 OpenAPI 上传并发送 agent 生成的本地文件。| Feishu File Sender — Upload & send files via Feishu OpenAPI, filling the channel's missing file delivery.
cyber-security-engineer
Security engineering workflow for OpenClaw privilege governance and hardening. Use for least-privilege execution, approval-first privileged actions, idle timeout controls, port + egress monitoring, and ISO 27001/NIST-aligned compliance reporting with mitigations.
lofy
Personal AI chief of staff — a complete life management system for OpenClaw. Proactive morning briefings, evening reviews, weekly reports, fitness tracking, career management, project tracking, smart home control, and brain-inspired memory architecture. Use when setting up a personal AI assistant that manages your entire life through natural conversation across Telegram, WhatsApp, Discord, or any OpenClaw channel.
skill-engineer
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester subagents for quality-gated skill development. Use when user asks to "design skill", "review skill", "test skill", "audit skills", "refactor skill", or mentions "agent kit quality".
claude-team
Orchestrate multiple Claude Code workers via iTerm2 using the claude-team MCP server. Spawn workers with git worktrees, assign beads issues, monitor progress, and coordinate parallel development work.