Skill rating

Query MaxCompute (ODPS) Information Schema metadata views. Tenant-level (SYSTEM_CATALOG.INFORMATION_SCHEMA.*, recommended) or project-level (Information_Schema.*, deprecated). NL→SQL for IS views: tab

Audit whether the Task Execution Signal Protocol is still being followed, with low-token, exception-first checks for version drift, queue hygiene, numeric stage format, and core execution anchors. Use

Use when you have surplus garden produce, foraged items, bulk buys, or need reliable shelf-stable food for 12–36 months in unstable supply chains, blackouts, or gig-economy self-reliance. Agent valida

Consul CLI command reference for service discovery, key-value store, health checks, cluster management, and service mesh operations. Use when executing Consul commands via the command line for: (1) St

Beginner fishing skills covering licensing, gear, techniques, and catch-to-cook basics. Use when someone wants to start fishing for food or recreation, needs affordable outdoor activity options, or wa

Query Tock (exploretock.com — restaurant discovery, availability, and the signed-in user's reservations) from a shell with the fpx CLI (@fetchproxy/cli) instead of running the tock-mcp server — list m

Design or implement a bilingual lightweight teacher grading pipeline for K12 paper exams and homework. Use when the user discusses or asks to build workflows involving scanners, document cameras, mobi

LYGO Site Card — turn a public HTTPS URL or local HTML file into a compact identity card: title, description, canonical, security headers, security.txt/robots companions, SHA-256, yield ALIGNED/DRIFT/

Gera documentação técnica consolidada para sistemas de software com múltiplos repositórios (frontend, backend, microservices, wikis). Use quando o usuário pedir documentação de multi-repo, visão de ar

Real-time AI news briefing for any topic. Say "给我看大谷翔平的新闻" or "AI今天有什么大新闻", and your agent instantly searches the web, summarizes the top stories in Chinese, and delivers a rich Feishu card with AI-po

Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package. Use when a

Save and track per-stock investment strategies with entry/exit conditions. Triggers on "保存策略", "跟踪策略", "检查股票策略", "核对建仓条件", "scheme", "stock strategy". Two modes: save (extract strategy from analysis →

Fetch a single property from Paragon MLS by MLS number and system ID. Use when looking up one listing's parsed details, including address, price, beds, baths, rents, taxes, and listing links.

专门用于将 Excel (.xlsx, .xls) 和 CSV (.csv) 文件上传至DataAgent API并转换为高度格式化的 Markdown 文档。 该工具具有内置的结构解析逻辑，能够自动识别表头、合并单元格并优化长文本换行。 当用户需要将表格数据转化为文档报告或在 Markdown 环境中展示数据时，**必须优先调用此工具**，以确保格式的准确性和视觉上的专业性，避免普通代码分析产生

Explain how Openclaw should use Codex CLI as a non-interactive coding engine. Use when Codex needs to document or answer questions about installing Codex CLI, authenticating, configuring approvals and

Create a new OpenClaw agent with a workspace directory and SOUL.md configuration. Use when you need to create a new agent, set up an agent workspace, configure SOUL.md, or initialize agent memory stru

Zero Trust security audit for AI agent workspaces, skills, and configurations. Based on Microsoft's Zero Trust for AI (ZT4AI) framework and the "Caging the Agents" research (arXiv:2603.17419). Audits

Reference reading, not a runtime policy: a field guide of 40 lessons from running AI agents 24/7 on real tasks — ethics, messaging security, context and memory layout, configuration safety, scheduled

Reviews a tech/AI/industry research or in-depth analysis long-form article before publishing, via a fixed eight-role expert panel (target-reader reps, quality gatekeepers incl. fact+originality check,

Investment, partnership, and acquisition due diligence framework. Use for deep dives on companies, people, deals, and properties. Produces a structured risk assessment with a clear Go / No-Go / Renego

Extract public WeChat Official Account articles from mp.weixin.qq.com links or saved HTML into clean Markdown or structured JSON, including title, account name, publish time, article text, tables, ima

Expand, compile, and write back the user's second brain around a knowledge point. Use when the user gives a topic/concept and asks to 拓展, 编译, 沉淀, 扩充, 构建, enrich, research, or update their second brain

Build and maintain GitLab CI/CD pipelines with the CI Tools Components Catalog at ci-tools.xrow.de. Use when creating or fixing .gitlab-ci.yml files, choosing CI Tools components, validating component

安全生产法规标准导入工具。当用户需要导入新法规或标准到知识库、PDF文本提取、条款拆分、批量导入、数据质量验证时使用。触发词：导入法规、添加标准、入库、导入知识库、补充标准、PDF提取文本、拆分条款、KB导入、safety-review import

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agen

Fine-tune a reusable brand, style, or character model (a LoRA) from a small set of reference images, then generate on-brand imagery from any prompt. Use when the user says "train a model on our brand

Generate UGC-style promotional videos with AI lip-sync. Takes an image (person with product from Morpheus/Ad-Ready) and a script (pure dialogue), creates a video of the person speaking. Uses ElevenLab

PostgreSQL database management and optimization assistant. Provides complete database operation capabilities: health checks, index optimization, query plan analysis, schema queries, SQL execution. Use

Build and maintain an isolated local personal fitness context for body weight, fat loss, diet, meals, calories, protein, hunger, fasting, food options near work or home, delivery choices, exercise pre

多智能体双盲 A/B 测试工作流。对多个 AI 模型/Agent 进行多轮次、双盲对照测试。 核心角色：协调者（Coordinator）、受测者 A/B（Contestant）、评测者（Judge）。 触发场景："A/B 测试"、"双盲测试"、"比较 AI 模型"、"模型评测"、"测试工作流"、 "compare models"、"blind test"、"multi-round evaluati

Measure information entropy and redundancy in agent group communications. Use when user asks about agent communication efficiency, information redundancy, entropy metrics, or how to quantify knowledge

OpenClaw is the high-autonomy agent mode. It proactively decides, plans, and executes tasks with deep context fusion, including a full sweep of historical memory files (`MEMORY.md` and `memory/*.md`)

AI agent trust scoring and reputation data from the ACP marketplace. Returns reliability grades (A-F), success rates, job counts, buyer diversity, and service offerings for 239+ tracked agents. Use wh

RenderingVideo preview assistant that uses the public preview flow at POST /api/preview without an API key. Use this when Codex needs to draft or edit RenderingVideo schema JSON, validate it with a te

This skill should be used when developers need to create dynamic C# features at runtime, including dynamic class generation, dynamic method creation, accessing private members through dynamic compilat

Query and manage Sanity CMS content via GROQ queries and the Sanity HTTP API. Use when asked to fetch content from a Sanity dataset, create or update documents, upload assets, run GROQ queries, manage

Physical navigation skills without digital devices. Use when someone wants to learn map reading, compass use, natural navigation, or needs to navigate when technology fails.

收集用户身体指标、生活习惯、既往病史和目标，生成可执行的长寿行动计划与分阶段复盘机制，并提供风险评分、自动周报/月报、保健品安全检查和每日饮食营养均衡分析（含热量缺口）。Use when users ask for longevity plans, healthy routine optimization, behavior-change schedules, supplement safety

Supports text-to-image and image-to-image. Use when the user needs to create or generate images. Use cases: (1) Generate from text description, (2) Use reference images, (3) Customize model, aspect ra

Find any local business by category and location on Google Maps. Get names, phone numbers, emails, websites, ratings, and hours. Search restaurants, dentists, plumbers, or any service.

Generate and edit images with Qwen 2 through RunAPI. Use when the user asks an agent to create, edit, or transform images with Qwen 2. Default to the RunAPI CLI for one-off generation; use SDKs only w

Local voice system for OpenClaw using faster-whisper for inbound transcription and Edge TTS for outbound replies. Use when you need private voice workflows, offline transcription, cached reply audio,

OpenClaw text-to-speech workflow for an OpenAI-compatible TTS server, including remote/self-hosted deployments such as vLLM Omni. Use when configuring, testing, debugging, or validating `/v1/audio/spe

Analyze data with `phylogenetic-tree-styler` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.

Türkiye Kayıtlı Elektronik Posta (KEP) rehberi. KEP nedir, nasıl alınır, zorunlu mu, hangi kurumlar kullanıyor, entegrasyon yöntemleri. Use when asked about KEP, registered electronic mail, Türkkep, o

Provides string manipulation and transformation operations for working with text. Use when you need to transform, format, or manipulate strings.

Generate escalating payment reminder emails that match days-past-due. Four stages: friendly, firm, urgent, final notice. Supports contractor, professional, and general business verticals.

Normalize the final JSON output of a single-session CTR product-card click diagnosis. Use after the diagnosis draft is complete and before replying, whenever the report must contain exactly the agreed

Rigorous workflow for high-stakes decision-making: investments (stocks/crypto/real-estate), major purchases, technology selection, supplier choice. Use when the decision commits >$1000 or >1 day of ef

Coach Pybricks and LEGO robot debugging through evidence, one-variable tests, and observable pass/fail checks.