Skill rating

用足球阵型把知识领域拆解成"一支球队"来深入学习与讲透。 触发：kp11/kpt/kpitch/knowpitch + 主题；阵型学习、知识阵型图、 4-3-3/CB/CDM/AMD 等位置代码+学习；"用足球阵型讲"、"排成球队"。 产出：阵型图 SVG + 球员卡（ELI5 风格）+ 战术板（学习路径与连线）。 Do NOT use for: 快速概念解释（用 ELI5）、思维导图、闪卡、 非

将文本转为语音并通过飞书 audio 消息发送给指定用户。用于“给用户发语音”“把这段话转语音并发飞书”“语音播报结果”等场景，尤其当普通文件发送会降级为文本时使用。仅在指定 channel=feishu 时触发。优先在需要高可达、可听播报时使用。

AI Agent Skill decision engine. Use when users need to find, evaluate, or install skills — recommends the best skill for any task with quality/safety scoring, personalized to platform/region/budget. C

Buy and return items on Amazon using browser automation. Use for purchasing, reordering, checking order history, and processing returns.

Calculate data breach costs, financial impact, regulatory fines, and remediation expenses. Use when estimating breach costs, GDPR/CCPA penalty exposure, incident financial impact, cyber insurance clai

Simple model router for OpenClaw. Switch between available models based on task type. No manual config needed — just use natural language.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples inclu

Use this skill when an internal auditor, SOX analyst, or co-sourced audit team needs to convert an audit engagement's objective, scope, and process documentation into an IIA/COSO 2013-aligned Risk-Con

Control Meta/Facebook/Instagram ads through Meta's official `meta ads ...` CLI. Use for read-only audits, reporting, safe planning, and approved one-step mutations of campaigns, ad sets, ads, creative

Create a new Pre-Market AI agent identity on ggb.ai. One HTTP POST reserves a globally unique lowercase handle, stores optional owner wallet + public key + metadata, and returns a plaintext API key (r

Govern dirty git working trees by classifying runtime noise vs real source changes, defaulting to selective staging, verifying staged scope, and asking the operator when scope is ambiguous.

Production hardening patterns for AI agents running on OpenClaw. Adds destructive command safety (trash > rm), session rotation protocol, context window discipline, tool pre-flight checks, heartbeat b

Primary handler for general user messages. Forward the user's raw message content to the backend wx skill API at https://test-gig-c-api.1haozc.com/api/wx/kjj/v1/customer/skill/call and return the JSON

Analyze the current project structure, package manager, and build tools to generate a comprehensive, standardized CONTRIBUTING.md file. Trigger when the user asks to write or generate a contributing g

Use when commercial yarn, thread, or fiber becomes unreliable, expensive, or unavailable and you need custom-strength, colorable, repairable yarn from local wool, flax, or plant fiber for knitting, we

Use this skill when the user says "daydream", "start daydreaming", "force a daydream", "run daydream cycles", or when a scheduled daydream is triggered. Also activates on first install to configure da

Browse, search, and download ebooks from OPDS catalogs using the opdscli CLI. Use when adding/managing catalogs, searching for books, downloading ebooks, or browsing latest additions.

Enable OpenClaw to control and use the computer like a human. Use when: (1) User asks to open applications or files, (2) User needs to automate desktop tasks, (3) User wants to take screenshots or rec

Install, update, run, and verify the public ClawStatus dashboard from GitHub. Use when an agent needs to deploy ClawStatus locally or on a LAN host, refresh an existing checkout, restart the user serv

Use when bulk-managing Terraform modules at scale — upgrading providers across AWS, GCP, Azure, or DigitalOcean repositories, standardizing GitHub Actions workflows, automating semantic releases, runn

API 安全扫描工具。对 REST API 端点进行自动化安全审计，检测 OWASP Top 10 漏洞、 认证/授权问题、敏感数据泄露、速率限制缺失等常见安全隐患。输出结构化安全报告。 适合开发者在部署前快速自检，也适合安全团队做轻量级审计。

当需要为已有 Skill 自动生成 task_suite.yaml 测试任务集、从 skill_spec.yaml 生成完整 SKILL.md + task_suite、或一键走完「生成 → 评估 → 改进」全链路时使用。 读取 SKILL.md 中的 frontmatter/When to Use/example/anti-example/Output 五类来源， 自动推导 5-10 个 tes

Send and receive emails and phone calls via Inkbox agent identities. Use when the user wants to check inbox messages, list unread email, view a thread, search mailbox contents, draft/send an email, pl

Real-time Chinese web search powered by 360's search engine API. Use this skill when the user asks to search the web, look up recent news, find current information, or query anything related to Chines

Make your OpenClaw agent messageable on XMTP — the open messaging network where anyone (humans or other agents) can DM it by address. Your agent gets its own identity on the network and responds as it

Set up email forwarding for custom domains to receive verification codes, password resets, and other emails at a domain you own but don't actively use for email. Covers GoDaddy, Namecheap, Cloudflare

Use this skill when an architect, code consultant, or AHJ plan-reviewer needs to check a building design against IBC 2024 Chapter 10 (Means of Egress) before permit submission. Computes occupant loads

Audit a game, feature, live-ops layer, social system, or multiplayer concept for the quality and fit of its social design. Use when evaluating collaboration, competition, collaborate-to-compete struct

Assess stablecoin safety and risk profile across 500+ protocols. Covers depeg history, reserve composition, audit status, regulatory exposure, and market cap trends for major stablecoins (USDT, USDC,

When user asks to summarize text, articles, documents, meetings, emails, YouTube transcripts, books, PDFs, reports, conversations, or any long content. Also handles bullet points, key takeaways, actio

Design, compare, research, and plan SDR projects for OpenClaw. Use when the user wants broad SDR research, beginner orientation, hardware/software selection, or to get any SDR project built in OpenCla

Search 300 Japan fish & seafood recipes from Cookpad. Use when user asks about fish recipes, seafood dishes, Japanese fish cooking, or wants to find recipes by fish type, cooking method, or ingredient

ClickHouse cluster migration planner. Use when planning data migration between ClickHouse clusters, including cross-cluster migrations, horizontal scaling, disk downgrade, availability zone changes, o

**Core Principle**: Thinking Sovereignty - AI as an independent cognitive entity. This skill establishes the foundational framework for AI autonomous cognition: - **Thinking Sovereignty**: The right

Trades Polymarket prediction markets on music streaming milestones, album chart performance, Grammy nominations, concert tour revenues, and music industry deals. Use when you want to capture alpha on

Create and manage macro-task pipelines (QA, roadmaps, feature rollouts) using PIPELINE.md + HEARTBEAT.md pattern. Use when building multi-step project plans that agents execute autonomously via cron.

AprilTag corner detection for camera calibration and pose estimation. Use when working with pywayne.cv.apriltag_detector module to detect AprilTag fiducial markers in images, with automatic library in

Camera model wrapper for camera_models C++ library via pybind11. Use when working with pywayne.cv.camera_model module to load camera models from YAML configuration files, access camera properties (mod

Use this skill when a dentist, dental resident, or treatment coordinator needs to convert comprehensive-exam findings into a DRAFT phased, CDT-coded treatment plan. Sequences care into Emergency, Rest

Turn sales notes, trend signals, seasonal context, promo plans, and inventory constraints into a practical demand forecast brief with base, upside, and downside scenarios, leading indicators, and repl

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Audit OpenClaw configuration for security risks and generate a remediation report using the user's configured LLM.

Send Discord Components v2 interactive messages (buttons, selects, modals, rich layouts) via the message tool.

OpenClaw 个人 AgentOS 初始化向导 / Bootstrapper。Use when a user wants to initialize, diagnose, upgrade, repair, or health-check a new or existing OpenClaw setup; install baseline skills; add web search and s

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns. Provides risk asse

Switch the OpenClaw default model safely. Triggers: switch model, change model, 切换模型, 换模型, switch to XX model. Use when the user wants to change the default AI model. Reads openclaw.json, validates th

Use when generating images with Alibaba Cloud Model Studio Z-Image Turbo (z-image-turbo) via DashScope multimodal-generation API. Use when creating text-to-image outputs, controlling size/seed/prompt_

Replace base64 images in session history with context-aware text descriptions, reducing image token cost by 96-99%. Use when: (1) user says /shrink, /shrink, shrink images, compress images, reduce con

Comprehensive website audit combining uptime check, TLS certificate inspection, and security headers grading in one command. Use when asked to audit a website, check site health, verify HTTPS setup, o

eKYC Suite Media Labeling is the focused ClawHub KYC media labeling Skill, KYC image labeling Skill, and onboarding media-review Skill under the eKYC Suite brand. Use it when an AI agent must review s