Skill rating

Audit tool usage patterns and permissions to identify security risks and excessive access. Use when you need to review tool usage, check for permission issues, or generate security audit reports.

Create placeholder data, test fixtures, and sample datasets for dev work. Use when generating mocks, building fixtures, or scaffolding content templates.

从小红书笔记图片提取结构化数据（租金/面积/单价等），自动裁切长图 + OCR 识别 + 导出 Excel。 使用 Apple Vision 框架进行离线 OCR，支持中文识别。 Use when: 用户需要从小红书/社交媒体图片提取表格数据、价格信息、统计数据等。

Check Washington DC weather using Open-Meteo API. Use when user asks about DC weather, current conditions, or needs a weather report for Washington DC.

Install and configure the DefiLlama MCP server for DeFi analytics. Provides 23 tools for TVL, token prices, yields, protocol metrics, stablecoins, bridges, ETFs, hacks, raises, and more. Supports OAut

Run spreadsheet-compatible Four-Square rental analysis for Paragon MLS deals. Use when evaluating rental properties for cash flow, NOI, DSCR, appreciation, depreciation, ROI, ROE, and IRR using the Go

Query WakaTime coding statistics including time ranges, projects, languages, categories, editors, and machines. Use when the user asks about WakaTime, coding time, project breakdown, language breakdow

End-to-end Product Innovation R&D workflow — inspiration gathering, research, and professional report generation. Use whenever the user wants to create a product innovation or R&D report, develop a ne

Generate monthly ledger statistics in CNY with amount and ratio by tag/category, top expense breakdown, and labeled charts. Use when user asks to统计收支, 看占比, 画图表, or requests monthly summary visuals.

Collect all customer reviews from an Amazon product URL or product-reviews URL through a logged-in Chrome session on port 9222, export a 14-column factual workbook, optionally fill translations throug

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,

Research technical projects/papers and generate comprehensive reports with PDF export. Modes: lite (analysis + writing) or full (+ environment setup + experiments). Params: iterations, mode, project-p

Work with cat feeding, weight, and water tracking records. Use when validating CatFoodCalculator-style JSON backups, calculating dry-equivalent cat food totals, estimating water intake from wet food,

Researches software/SaaS products, business reputation, and crowdfunding campaigns via the Crawlora API — Product Hunt launches/makers/alternatives, Trustpilot business reviews, TrustMRR revenue-verif

Separate vocals and instrument stems on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `separate-vocals`, `stem-split`, `upload-and-separate-vocals`, vocal remover workflows, st

Audio search tool: searches Pixabay Music and returns royalty-free track URLs and metadata for background music selection. Use 2-3 short English style keywords (e.g. 'upbeat pop energetic'); a long ph

Audit an OpenClaw agent workspace and generate standardized evaluation reports, scores, and patches. Use when asked to review memory quality, retrieval efficiency, productive output, reliability, or a

Use when an agent needs to run GEO/SEO audits through x402geo.com with payment gating, status tracking, and report delivery via MCP or ACP.

PA network health dashboard. Use when: checking if all PAs in the network are active, checking billing status, verifying calendar connections, or generating a network status report. Reads from data/pa

Deep-research skill for Chinese outputs using 横纵分析 / Horizontal-Vertical Analysis. Use when Codex needs to systematically study a product, company, concept, technology, market, or person: rebuild the

Repair the OpenClaw Control UI Skills modal when clicking a skill row does nothing and DevTools shows a showModal InvalidStateError because the dialog is not yet in the document.

Views and searches evolution cycle history with filtering capabilities for tracking progress and analyzing patterns. Use when reviewing past cycles, searching for specific outcomes, or generating hist

Grocery ordering via Kroger-family stores (Kroger, Fred Meyer, Ralph's, Harris Teeter, King Soopers, Mariano's, QFC, Smith's, etc). Use when: (1) user asks to order groceries or add items to cart, (2)

使用微软 markitdown 库将多种文档格式（PDF、DOCX、PPTX、XLSX、XLS、CSV、JSON、TXT、EPUB、HTML等）转换为 Markdown。支持批量转换、保留格式、图片提取等功能。使用场景：(1) "把这个 PDF 转成 Markdown"，(2) "把这个 word 文档转成 Markdown"，(3) "批量转换这个文件夹里的文档"，(4) "提取文档中的图片"。

Use this skill for Eastmoney MX condition-based stock screening and universe lookup when the user asks to find stocks, listed companies, sector constituents, index constituents, or recommendations bas

面向专题研究报告生成的能力。适用于用户提出“某主题/事件/政策的深度研究报告”类请求时，自动生成结构化研究内容。覆盖主题投资、政策影响、事件冲击、趋势判断等跨行业议题。触发核心条件：用户目标是“专题研究/深度解读/报告输出”，而非单行业常规研究或单标的诊断。

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

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

Define custom distance/similarity metrics for clustering and ML algorithms. Use when working with DBSCAN, sklearn, or scipy distance functions with application-specific metrics.

Workers' compensation navigation and workplace injury rights. Use when someone is injured at work, needs to file a workers' comp claim, is being pressured not to report an injury, or doesn't understan

EVR Framework — Execute-Verify-Report. Force AI to actually DO, then VERIFY, then REPORT. Stop fake completions and silent failures. Use when user mentions 'done', 'finished', 'created', 'completed',

Advanced English polish skill for non-native writing. Nativization, style consistency, diff output. CLI scripts: detector.py + polish.py

Track congress stock trades and politician stock trades: Pelosi tracker, senate stock trades, House trades, congress trades by ticker, and STOCK Act disclosures sourced from House Clerk and Senate eFD

Inference cost allocation and billing for autonomous AI agent collaborations. Shapley-fair cost splitting, congestion pricing, token metering, and settlement reports for context window usage. The econ

Build and grow developer and user communities from scratch — covering ambassador programs, community-led growth (CLG), event operations, content strategy, and health metrics. Grounded in real playbook

Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.

Build large-screen data-visualization dashboards (大屏 / 数据大屏 / 可视化大屏) as Slidev presentations using the datav-vue3 (DataV) component library. Use when the user wants a data dashboard, monitoring/comman

Predict English Premier League football match outcomes first, keep World Cup national-team support for compatibility, include schedule/result context, answer in the user's language, and keep output as

AI-powered automated job search skill. Searches LinkedIn and Indeed daily, scores jobs against the user's profile, and saves results to a local CSV. Use when: - User says "run job search", "find jobs

Twitter API Alternative — Search 1B+ tweets with natural language queries, boolean filters, and one-click CSV exports (up to 64K rows). Look up profiles, find users by topic, and track conversations.

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.

Automate posting content with images to LinkedIn, X/Twitter, Facebook, WordPress, and Substack via browser automation. Use when: (1) posting a new article or social update to one or more platforms, (2

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

Invoke ChatDev ability units (workflows) via local API (port 6400). Use when the user needs specialized agent workflows like data visualization (from CSV), or when they mention "ChatDev", "ability uni

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

Opt-in reporter for the OpenClaw global claw heatmap. On first use, ASKS the user for consent before registering. Heartbeat (platform + model only) is sent only after confirming prior consent (i.e. ~/

Time series forecasting for AI agents. ARIMA and Holt-Winters predictions with confidence intervals. Predict revenue, traffic, prices, or any sequential data. Sub-5ms inference.

Manage Hugging Face Hub via hf CLI. Use when working with HF AI models, datasets, spaces, or repos.

Use when analyzing or predicting World Cup or international football matches, especially when the user asks for match forecasts, score predictions, betting-market comparison, card or discipline foreca

Use DebugBundle for runtime error reporting, crash reporting, incident reporting, incident response, live app monitoring, and production monitoring focused on runtime failures, customer-facing inciden