Manage multi-tier AI inference clusters for homelabs. Health monitoring, expert MoE routing, automatic node recovery, and model deployment across Ollama and llama.cpp nodes. Covers GPU memory planning
Provides end-to-end encrypted, authenticated, and forward-secret messaging between AI agents with cryptographic identities and tamper-proof delivery.
Omarchy operating guardrails for day-to-day system work: assume the host is Omarchy by default, choose Omarchy-native workflows first, map user intent to the correct omarchy-* wrapper/script family, a
A decision capture and review system that records every significant choice — with context, reasoning, and alternatives — so you can detect your own blind spo...
定义多 Agent 团队两种核心协作模式：后台 spawn 实现统一调度与汇总，Discord @mention 实现角色外显与公开协作。
Your agent does the same things the same way forever. inner-life-evolve analyzes patterns, challenges assumptions, and proposes improvements — writing propos...
Generate comprehensive Knowledge Graphs (RDF-Turtle by default, or JSON-LD and other RDF serializations on request) from content at file: or http(s): scheme...
Use this skill whenever the user has a DOCX file (.docx) and wants to convert, read, view, extract content from, or process it in any way — including summari...
Generate reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from refer...
Manage Alibaba Cloud DataWorks via OpenAPI/MCP Server. Use for data development, workflow operations, data quality, metadata lineage, workspace management, a...
Your OpenClaw agent forgets everything between sessions — after /new, after compaction, after overnight. Clever Compact fixes all three: injects your last st...
Use D:\internal-hub as the shared learning and coordination forum for OpenClaw roles. Use when an agent should post a reusable finding, request a new skill,...
Manage a remote Docker host securely via docker-socket-proxy, supporting container lifecycle, images, networks, volumes, swarm, plugins, and system info APIs.
Iterative code review using multiple independent subagent reviews. Use when user asks to review PR, code, or mentions "review", "审查", "检查代码", "代码质量". Automat...
OpenClaw wrapper for Muratcan Koylan's Agent Skills for Context Engineering. 13 skills covering context optimization, multi-agent patterns, memory systems, t...
WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects. This skill should be us...
Navigate Tencent products, Tencent Cloud services, and WeChat ecosystem decisions with region-aware planning and official-source verification.
TAPD API 完整集成。实现 18 个模块、70+ API 方法，支持 OAuth 和 Basic Auth 认证。涵盖需求、任务、缺陷、迭代、测试、Wiki、工时等所有 TAPD 功能。
Sign in to OpenAnt. Use when the agent needs to log in, sign in, check auth status, get identity, or when any operation fails with "Authentication required"...
Turn complex business goals into navigable strategic maps. Identify milestones, resource nodes, risk points, bottlenecks, and route logic so users can see th...
Use ClawLodge to search, inspect, download, and publish OpenClaw workspaces. Trigger when the user wants to find reusable workspaces, compare versions, fetch...
When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "page...
Manage project schedules stored as YAML in the workspace planning/ directory. Use whenever the user asks about project delivery progress, module status, week...
Handle CAPTCHAs encountered during web scraping. Avoid triggering Cloudflare Turnstile, reCAPTCHA, and hCaptcha through residential proxies and stealth techn...