Skill rating

When the user wants to run CTV, OTT, or streaming TV ads. Also use when the user mentions "CTV ads," "connected TV," "OTT advertising," "streaming ads," "TV ads," "Hulu ads," "Roku ads," "YouTube TV a

Establish level-area-storage relationships from multi-period water surface, DEM, and water level data. Monitor reservoir capacity change and sedimentation trends. Use when analyzing reservoir storage

Compare the current Git branch against master/main, identify newly added or changed code paths, and produce simulated unit-test-style case tables without generating test code. Use when the user asks f

Create custom React hooks in TypeScript for game loops and animations. Use when the user asks for a React hook, requestAnimationFrame integration, game loop pattern, or delta-time handling. Handles st

Comprehensive Claude Code CLI reference covering interactive mode, CLI flags, commands, environment variables, hooks, channels, checkpointing, plugins, and tools. Use when asked about Claude Code feat

Audit third-party or custom skills for permission risk, unsafe commands, and integration safety. Use before: installing a new skill, enabling external scripts or repos, granting broad permissions, rec

使用本地 ModelCLI 完成目标检测、OCR、语音识别、语音合成、模型管理与运行诊断。 Use when the user asks to detect objects in an image, extract Chinese or English text from an image, transcribe WAV/FLAC/MP3 audio, synthesize or clone sp

Audit any website for AI search visibility (GEO / AEO). Use when the user asks to "audit my site for AI search", "check if AI can cite my site", "GEO audit", "AEO audit", "AI SEO check", "can ChatGPT

AI专利撰写全流程专家。覆盖专利类型引导→技术交底分析→新颖性检索指导→五书撰写(权利要求书/说明书/摘要/附图)→权利要求专项设计→提交前质量审查→OA答复辅助7大模块。支持发明/实用新型/外观设计三种专利类型，内置中国专利法核心条款(第22条/第26条)、CNIPA审查指南(含2026新规)和五书撰写规范。生成交互式HTML可视化报告，含完整专利文档、质量雷达评分、合规自查清单。触发词：写专利

Analyze geospatial data using geopandas with proper coordinate projections. Use when calculating distances between geographic features, performing spatial filtering, or working with plate boundaries a

Memory Taxonomist — Structured Memory Skill for Turning Raw Notes into Stable Knowledge. Use it when the user needs a disciplined protocol and fixed output contract for this kind of task rather than a

Use SourceHarbor watchlists, briefings, Ask, MCP, and HTTP API to answer one question with current story context and evidence.

Plan a specific museum or exhibition visit with verified logistics and 90/180-minute routes, get concise on-site exhibit explanations, or turn a completed visit into a sourced memory note. Also advise

Activate when: someone says 'MVP', 'minimum viable product', 'smoke test', 'concierge MVP', or 'Wizard of Oz'; a team is scoping a build and hasn't named the assumption they're testing; engineers are

AI-orchestrated usability testing using Amazon Nova Act. The agent generates personas, runs tests to collect raw data, interprets responses to determine goal achievement, and generates HTML reports. T

Skill Base server deployment guide. Covers starting the Skill Base server (npx skill-base), Docker configuration, port mapping, and SQLite database backup. For deploying and operating the Skill Base p

Browse categories, preview, apply, and restore OpenClaw SOUL.md personas from a curated remote catalog. Use for /soul categories, /soul list <category>, /soul show <id>, /soul apply <id>, /soul curren

Parse JSON, CSV, XML, and logs into structured output. Use when converting formats, validating structure, extracting fields, analyzing nested data.

Auto-detect and enable OpenClaw Browser Relay Chrome extension when disconnected. Uses native mouse control to click the extension icon.

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

Search and resolve Korean road addresses (도로명주소) via the official juso.go.kr OpenAPI. Keyword search with zip codes, English address lookup, and address-to-coordinate conversion. Use when a task needs

OpenClaw Agent Templates system reference and workflow guide. Use when creating, editing, reviewing, debugging, or extending the built-in Agent Templates feature; when working with template-backed age

Trades Polymarket Bitcoin 5-minute sprint markets using real-time BTC price momentum from Binance. Buys YES when BTC momentum is bullish, NO when bearish.

Practical Stoic philosophy applied to daily life. Use when someone is overwhelmed by things outside their control, needs a framework for resilience, wants a daily mental practice, or is facing adversi

Gives your AI agent a formal channel to propose changes to its own soul files (SOUL.md, IDENTITY.md, or any protected workspace file) — without ever letting it self-edit. The agent submits a structure

Use this skill when a user wants a trust decision before installing from a skill URL, marketplace, or GitHub repo. It checks a compact allowlist of trusted distribution channels and returns whether th

Provides tools for implementing feedback loops to fine-tune LLM agents using user feedback for continuous personalization and improvement, including training dataset generation, prompt optimization, a

Runs SERP and keyword research via the Crawlora API — Google, Bing, Brave, DuckDuckGo, and Yahoo search results plus Google Trends interest-over-time and related/rising queries — returning clean JSON.

Read your Jobber Client Hub — the customer portal a service business (pest control, lawn care, HVAC, cleaning) uses to send you appointments, quotes and invoices — from a shell with the fpx CLI (@fetc

Improve image quality and resolution. Use when the user says "upscale this", "make it sharper / higher-res", "deblur", "denoise", "dehaze", "restore this old photo", "fix this low-res / pixelated imag

Expand a structured brief in `content-production/inbox/` into a reusable long-form markdown article draft, then run a local writer / critic / judge quality loop with a constrained humanization pass. U

Describes product collection task HTTP APIs (create, pick, update, batch-update), task types, statuses, success payload rules, and browser-extension vs dashboard roles. Use when integrating collection

Privacy redaction toolkit for images, PDFs, Word documents, and PowerPoint presentations. Use when the user needs to redact, mask, or replace sensitive/private information in files. Triggers: - Reda

Bootstrap and enforce fast direct API execution in a workspace. Use when you want an agent to run API calls directly in-session, avoid unnecessary subagents, use one upfront preflight followed by a co

Mental health support designed for workers in trades, service, and physical occupations. Use when someone in a physical job is struggling with stress, substance use, anger, isolation, or burnout and t

DNS reconnaissance and subdomain enumeration using rapiddns-cli (RapidDNS API). Use when: searching subdomains of a domain, reverse IP lookup, CIDR enumeration, advanced DNS queries, bulk DNS data exp

Rewrite a rough sentence into 5 better title options.

Researches hotels, flights, attractions, short-term rentals, and live events via the Crawlora API — Booking.com, Expedia, Agoda, TripAdvisor, Trip.com, Airbnb, and Ticketmaster — returning clean JSON.

Detect forest disturbance from multi-temporal NDVI. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.

Is this skill safe? Use this before installing any third-party ClawHub skill or running its scripts, and whenever the user asks whether a skill is safe. Inspects every file in the skill folder — SKILL

Interact with Codeberg using the `tea` CLI. Use `tea issue`, `tea pr`, `tea actions`, and `tea api` for issues, PRs, Actions, and advanced queries.

多维度合约信号分析引擎 — 扫描全市场筛选妖币信号，给出独立多空研判

Query and search medical records from CareMax Health API. Supports structured query, AI-powered semantic search with RAG (natural language answers with citations). Use when a user asks about medical r

Serve spec-driven dev tools via MCP for AI-assisted workflows. Use when adding tasks, planning iterations, tracking completion, reviewing quality.

Get-started-fast guides for accessible physical instruments. Use when someone wants to learn an instrument, needs a stress relief practice, wants to play music with others, or is looking for an embodi

Practical protocol for rebuilding human connection during isolation. Use when someone feels lonely, isolated, has no friends in their area, struggles to make connections, moved to a new city, works re

Practical skills for cooking and hosting groups of 10-50 people. Use when someone needs to feed a crowd for events, community gatherings, family reunions, block parties, or regular group meals on a bu

Practical fire building, management, and safety skills. Use when someone needs to build a campfire, use a fireplace safely, learn to grill, or needs fire emergency response guidance.

Rigorous workflow for producing long-form knowledge content (textbooks, knowledge bases, deep reports) with multi-agent collaboration. Use when the task requires >5,000 words, >2 parallel sub-agents,

Global, namespaced learning memory for OpenClaw. Use when users correct output, set stable preferences, ask what was learned, ask for memory stats, or request forgetting learned patterns. Keep memory