Skill rating

Start or reuse CAD Viewer and return review links for explicit CAD, implicit CAD, robot-description, and G-code files. Use when visually reviewing `.step`, `.stp`, `.implicit.js`, `.implicit.mjs`, `.g

Interpretar métricas de producto contra objetivos y exponer señales accionables. Utiliza cuando se te pida analizar la salud del producto, revisar métricas clave, investigar un problema de rendimiento

Audita un SKILL.md de Claude/Agent (o cualquier skill de IA / instrucción del sistema) para verificar su seguridad antes de instalarlo o fusionarlo. Úsalo cuando te pidan revisar un skill por segurida

Crea un Agent Skill (SKILL.md) de alta calidad que la IA dispare y ejecute de forma fiable — frontmatter sólido, descripción incisiva con frases de activación, contrato de salida claro, controles de c

Turn a shower idea into a full best-seller manuscript in one command. Multi-agent pipeline — Planner → Character Designer → Chapter Writers (parallel) → Editor → KDP Packager. Produces a complete book

Stop drifting back to chatbot behavior. Patterns for maintaining autonomous agent effectiveness across sessions.

Autonomous DeFi agent that scans Sui mainnet for all possible opportunities in real-time — arbitrage, yield, swaps, and more — and shares discoveries with a multi-agent network.

Chat with the dlazy sandbox agent — a project-scoped assistant that runs skills end-to-end over multiple turns. Discover skills and projects with dlazy skills list / dlazy projects list. 与 dlazy 沙箱 ag

个人知识库构建系统（基于 Karpathy llm-wiki 方法论）。让 AI 持续构建和维护你的知识库， 支持多种素材源（网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件）， 自动整理为结构化的 wiki。 触发条件：用户明确提到"知识库"、"wiki"、"llm-wiki"，或要求对已初始化的知识库执行 消化、查询、健康检查等操作。不要在用户只是要求"总结这篇文章"时触发—

Orchestrates TRAE IDE for automated software development with multi-agent collaboration. Invoke when user wants to develop software using TRAE or needs automated project management.

通过 ACP runtime 委托 acpx-enabled harness（Claude Code / Codex 等）的标准协议。触发词：调用 Claude Code、通过 acp 调用、通过 acpx 调用、delegation to claude/codex、Coordinator 调用 Executor。

Point at any topic to build a compounding, domain-general expertise knowledge base: a high-fidelity source corpus, track-record-weighted experts, reconciled falsifiable stances, failure modes, benchma

基于腾讯会议(tmeet)通讯录与会议录制/纪要，覆盖面试全链路——会前生成候选人画像与结构化面试提纲，会中记录关键信息，会后输出带维度评分与录用建议的结构化评估。当用户说"准备面试""生成面试提纲""面试评估""候选人画像""面试记录整理"时触发。

Automates uploading multiple sources (files, URLs, YouTube, Drive, text) to a NotebookLM notebook, generating a deep dive audio overview in a preferred language, and downloading the result. It guides

Search Google Hotels for hotel discovery, prices, or availability. Do not use to scrape a known Booking.com hotel URL.

Design public-safe onboarding prompts and weekly concierge actions that help new Skool members make first comments, share first proof, surface blockers, and create free-course trust signals without sc

Watch and explain Mac disk usage. Use when the user asks about Mac storage/disk space ("what's eating my disk?", "disk full", "free up space"), wants a visual map of what's on the disk, or wants sched

Transforms your OpenClaw agent with the APEX cognitive framework — a battle-tested thinking system built by a solo founder over 10 months of AI product development. Enhances response quality with stru

OpenClaw's subconscious. Automatically distills conversation insights, corrections, and preferences into durable memory. The agent that learns from every session — so you never have to repeat yourself

Auto-generate a daily Bitcoin market brief from BTC-vision.org — price, halving countdown, Fear & Greed, AI predictions. Perfect for morning briefings on Telegram/Discord/Slack.

当用户需要查询、创建或更新 TAPD 需求、任务、缺陷、评论、工作流、迭代、测试用例、Wiki、工时、发布计划，或发送企业微信通知时使用本 Skill。使用 Python 标准库调用 TAPD 开放 API，不依赖 MCP 或第三方 HTTP 库。

Use when a project needs one or more verifier skills for web, CLI, or API runtime checks that the Verify agent can discover automatically.

Decode laundry care symbols from text descriptions (tub, triangle, iron, circle, square shapes with dots/bars), build a safe wash plan for a mixed load (color bleeding risk, temperature ceilings, fabr

专利技术全景分析报告自动生成。用户上传专利数据Excel表格（含标题、申请人、申请日、法律状态、受理局、被引次数等字段）和技术拆解Excel表格后，自动分析专利数据并生成可编辑的HTML全景分析报告。 报告包含5大模块：技术概况分析、重点技术分支分析、竞争对手分析、专利风险分析、企业专利布局建议。 触发条件：当用户提及"专利分析""技术全景分析""专利全景报告""专利布局分析""CMC专利分析""

Semantic code caching for AI agents. Cache, retrieve, and reuse code from prior agent executions.

基于 Tushare Pro A 股日线与 Baostock 风格指数生成盘后市场研报。当用户要求分析每日或历史盘面、指数与市场风格、情绪和成交额集中度、赚钱效应与上涨主线、即时及短中期催化、主线细分线路、爆量下跌，或容量上涨、全市场月线平台突破、10:30 前涨停、折扣启动等特征分组时使用；也用于特征分组量化回溯与相对收益因子挖掘。本 skill 先生成确定性证据包，再由模型按模块判断与写作；脚

Smart LLM Router — routes every query to the cheapest capable model. Supports 17 models across Anthropic, OpenAI, Google, DeepSeek & xAI (Grok). Uses a pre-trained ML classifier. No extra API keys req

A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for China A-shares. 15 specialized analysts collabo

Generate structural, semantic, and property constraints for knowledge graph schemas including RDF/OWL ontologies and property graph models.

输入任意技术领域关键词（如"OLED"、"固态电池"、"mRNA疫苗"），自动生成该领域的情报简报门户（HTML网站）。监控的企业和技术分支由AI模型自动检索和拆解，新闻由智慧芽新闻向量检索自动获取，专利使用关键词扩展后在智慧芽专利数据库直接检索。当用户说"生成XXX情报门户"、"XXX领域情报简报"、"帮我监控XXX技术"时触发。

The academic research platform for AI agents. Submit papers, review research, build consensus, and push toward AGI — together.

Moodle REST API client, batch downloader, and MCP server for Claude Code integration. SSO-enabled with support for Azure AD, Google, and SAML.

Manage X (Twitter) accounts — post tweets, like, reply, retweet, view timeline, search, auto-interact, analyze data.

Escalader un problème vers l'agent superviseur (David) via webhook gateway. Utiliser quand l'agent client est bloqué sur un problème qu'il ne peut pas résoudre seul après 2-3 tentatives.

Current market regime label at minimal cost for fast agent loops

Theta EdgeCloud AI, GPU, video and game-character workflows: discover live services, run inference, manage approved resources, and verify costs.

Apple Silicon AI — run LLMs, image generation, speech-to-text, and embeddings on Mac Studio, Mac Mini, MacBook Pro, and Mac Pro. Turn your Apple Silicon devices into a local AI fleet. M1, M2, M3, M4 M

Manage BRICKS workspace via CLI. Use for device status, screenshots, control, monitoring, group operations, application management, module management, project initialization and deployment, scanning a

Read a SimplePractice Client Portal (`<practice>.clientsecure.me`) from a shell — appointments, invoices/statements/superbills/receipts, documents to sign, announcements, practice and clinician info —

Activate when: determining country of origin; testing USMCA (or other FTA) preference eligibility; marking; 'does this qualify for duty-free?'; goods with multi-country inputs. Do NOT activate when: w

AI-powered decentralized voting arena. Agents debate topics, cast reasoned votes, and reach consensus.

清理 OpenClaw 无用会话的工具。当需要清理旧会话、删除过期 session 文件、或整理会话列表时使用此技能。触发场景包括：用户说"清理会话"、"删除旧 session"、"清理子 Agent"、"整理会话列表"。

Advanced multi-agent development system for complex software projects. Leverages Orchestrator, Builder, and Reviewer agents to decompose modules, implement code, and perform iterative quality reviews.

Fetch and summarize web pages for AI agents. Extract key information from URLs and return structured markdown summaries. No API key required.

iOS/macOS app automation — builds, signing, TestFlight, App Store via CLI

A cognitive growth framework that helps your AI truly know you — and help you know yourself. Includes personality profiling, behavioral pattern detection, reflective mirroring, and Socratic questionin

Claude Code 远程执行 Skill — 通过三通道（FastAPI/Redis/Screen）向远程机器上的 Claude Code 派发指令，支持重试机制。触发：博士让我"派发给 Claude Code"、"远程执行"、"让XX机器执行Claude Code"、remote cc。

把「已有的」静态网页文件（单个 HTML 或整个网站目录）安全发布到 GitHub Pages，生成可公开访问、能分享的网址链接。当用户已有现成网页，想「发到网上」「部署上线」「发布网页」「生成分享链接」时使用；本技能只做「发布已有文件」，不负责从零生成网站。提供可执行的 deploy.py 脚本（整站增量上传 / 单文件上传 / 仅启用 Pages 三种模式），纯标准库无额外依赖，逐文件增量上传

The writing-craft skill — style and tone as applied technique: rhythm, specificity, tone modulation, and the edit passes that make writing read as human. Use when someone's posts "sound like ChatGPT,"

Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and aut