Skill rating

Evaluate a README file text, score it out of 100, and provide specific, actionable improvement suggestions.

Perform text review on user-specified input text that may be inappropriate or offensive.

Discover Angels for Agents funding opportunities, assess an agent-led venture's readiness, prepare and validate an AFA pitch, submit an explicitly authorized application, or report an existing Proof G

Multi-round review skill for Chinese management-oriented master's theses, especially MBA, MEM, and MPA, with applicability to similar professional and applied research theses.

Check if phone numbers exist in the local Baileys session cache

Cloud infrastructure & IaC security scanner -- detects insecure Terraform, open S3 buckets, permissive IAM, missing encryption, exposed ports, and cloud misconfigurations

AI-powered configuration validator. Automatically validate JSON/YAML configs, detect conflicts, and suggest best practices.

站点综合分析工具，析出域名/IP的机房位置、ISP、网络路径、robots策略等完整站点画像。当用户要分析某个域名或IP的机房部署、归属、网络质量时触发。支持：分析源机房位置、ISP/ASN归属、GeoDNS/CDN检测、traceroute路径分析、延迟探测、robots.txt策略。首次使用自动探测本机网络环境作为参照基准。

Track and analyze your OpenClaw session costs. Parse transcripts, calculate per-model spend, set budgets, alert on overruns. Stop burning money blindly.

用 UbD 逆向设计把"经验型备课"变成可观测的教学设计。当老师说"帮我设计一节《一次函数》新课"、"写一份物理教案"、"做一份分层教案"、"帮我设计一节讲评课"、"这节课的提问链草案"时，建议激活此 SKILL。工作流：预期结果 → 评估证据 → 核心素养目标 → 环节时间矩阵 → 提问链草案 → A/B/C 分层。本 SKILL 不出卷、不算学情、不负责课堂实施：命题转 xiaozhi-tea

Analyze dead letter queue (DLQ) messages to identify failure patterns, root causes, and remediation strategies. Supports AWS SQS, RabbitMQ, Kafka, Azure Service Bus, and generic message queues.

彻底断绝主代理长期对话中累积的偏见与情绪对产出的裹挟，确保每次产出忠实于需求本身，不再随对话越长越偏离预期。你只负责提需求和最终验收。传统单agent反复调prompt、人工审核输出的工作流，在这里被架构级消解了。角色隔离的双子代理对抗架构：执行和QA子代理运行在完全架空的环境中，看不到主代理的会话上下文、用户画像和记忆。5维10分制评分，满分才交付，否则自动打回重构，5次不过熔断兜底。需求说一次

Discover, score, and monitor Chinese GitHub developers with GitHub signals, rule-based processing, optional OpenClaw AI evaluation, shortlist queries, cron management, workspace export, and controlled

Search patents owned or filed by one or more specified applicants within a defined technology topic. Use when an IP searcher or analyst needs an applicant-first, topic-constrained PatSnap strategy; ev

Security audit tool for AI agent skills. Scans skill packages for malware, credential theft, and suspicious patterns before installation. Defensive security tool with optional enterprise reporting (us

AI-powered diagnosis and repair for AI agents. Send your health data, get diagnosed, execute prescribed repairs, report back until healed.

Subagent-driven development. Dispatch fresh subagent per task with 2-stage review (spec + quality). Cost-aware model routing. From Superpowers by Jesse Vincent.

Portfolio news intelligence — monitors breaking news, SEC filings, price moves, and analyst actions for your stock/crypto/ETF holdings. Pushes personalized alerts to Telegram 24/7. Reply "deep" for AI

eBay review and feedback authenticity analyzer. Detect fake reviews, suspicious seller feedback patterns, and buyer manipulation. Includes time clustering detection, content similarity analysis, and e

A Chinese message preprocessor that detects obvious typos, grammar errors, and punctuation issues in user messages without auto-correcting. It prompts users to confirm using the original sentence befo

Interactive OpenClaw setup wizard that diagnoses, configures, and optimizes a fresh or existing OpenClaw installation. Use when a user asks to set up OpenClaw, configure providers, connect chat channe

Monitors Twitter for competitor hiring announcements to track growth signals using apidojo's Tweet scraper. Triggers when the user asks to: monitor competitor job postings on Twitter, track hiring sig

Formal verification with Lean 4, Coq, and Z3 SMT solver

基于 Qlib 的 A 股自选股智能分析系统，集成 LLM Agent ReAct 推理引擎和技术指标择时模块（MA 多头排列、乖离率阈值严进策略），自动生成每日 buy/hold/sell 指令并推送至微信。触发场景：(1) 用户要查询自选股当天的 AI 交易信号和涨跌预测；(2) 用户要获取符合 MA 多头排列且乖离率低于 5% 的可买入股票列表；(3) 用户要在收盘后自动接收个股的买卖建议和

Apple Health 数据全景分析。从 export.zip 流式解析 XML（支持 1-2GB 大文件），提取 RHR/HRV/VO₂Max/睡眠/步数/血氧等核心指标，基于用户个人信息（年龄/性别/身高/体重/病史）动态校准参考范围，生成个性化交互式 HTML 报告（含 6 张 Chart.js 图表）。使用场景：用户说「帮我分析健康数据」「看看我的 Apple Health 数据」「生成

Lock down any LLM agent against prompt injection, data exfiltration, social engineering, and channel-based attacks. Use when setting up a new agent, auditing an existing agent's security posture, hard

Detect guaranteed-profit arbitrage opportunities across sportsbooks and prediction markets. Compares odds from 20+ bookmakers, Polymarket, and Kalshi. Calculates optimal stake distribution. Use when a

AI-powered pet sneeze/cough detection from real-time camera (optional audio fusion). Analyzes head and thoracic-abdominal motion plus sound features to distinguish single occasional events (normal air

数据库锁分析与死锁检测，支持当前锁分析、死锁检测、锁等待链追踪。 使用场景： - 用户说"看锁" → 执行 analyze - 用户说"死锁" → 执行 deadlocks - 用户说"阻塞" → 执行 chains - 用户说"终止事务" → 执行 kill <事务ID> 用法： - dbskiter --output-mode=ai --database=<name> lock analy

信创与 IT 信息化采招数据分析助手。当用户涉及以下任何场景时，必须使用此SKILL：搜索信创/国产化/IT信息化招标中标公告（服务器、数据库、操作系统、云、数据中心、网络安全、软件等）、查询某IT品牌/型号的中标占有率与历史单价、分析IT集成商的主营业务与竞争对手、查询某品类的Top采购单位/Top中标单位、推荐潜在投标供应商、数字政府与信创项目趋势分析、IT采购寻源/渠道拓展等场景。即使用户没

Analyze keywords for SEO optimization. Research search volume, competition level, and ranking difficulty. Generate keyword suggestions, content ideas, and optimization recommendations for better searc

OpenClaw + Claude Code 编程工作流。当用户想用 Claude Code 写代码、调试、重构、做 PR review 时激活。支持两种模式：ACP 集成（推荐，通过飞书/Telegram/Discord 直接对话 Claude Code）和 PTY 后台模式（通过 exec 控制 Claude Code CLI）。不用于纯聊天问答（直接用主 agent）或 Kiro 开发（用

Generate viral social media posts using AI with trend analysis and hashtag optimization for X, Instagram, and Telegram

Monitors tech acquisition news and M&A activity using apidojo's Google Search scraper. Triggers when the user asks to: track tech acquisition news, monitor M&A activity in a sector on Google, find rec

Evaluate whether an article, document, video transcript, or webpage is worth reading; recommend full reading or specific sections; maintain a private local reading profile; and learn from explicit fee

Automatically discover novel, statistically validated patterns in tabular data. Find insights you'd otherwise miss, far faster and cheaper than doing it yourself (or prompting an agent to do it). Disc

Capture Doubao translation results with auto-scroll and auto-end detection.

This skill should be considered when you need to answer reflow machine maintenance questions or provide detailed guidance based on thermocouple data, MES data or defect data and reflow technical handb

Exam paper OCR rebuilder with LLM audit. Supports 11 question types, tencent-docs OCR integration, and interactive HTML report generation. Triggers: 试卷OCR, 试卷识别, 试卷重建, 试卷录入, PDF试卷, exam OCR, exam pape

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use before starting work and after responding to th

Using multispectral or high-resolution RGB cameras mounted on agricultural UAVs to capture orthophotos or mosaics of farmland, AI models compute vegetation indices (e.g., NDVI, NDRE) and generate a fa

AI-powered Git assistant that analyzes staged changes and terminal history to craft meaningful, conventional commit messages.

QA lead skill for evidence review, gate enforcement, release-readiness assessment, and quality signoff recommendations.

Auto-discover and map service dependencies from code, configs, and runtime data. Generate dependency graphs, identify critical paths, find single points of failure, and assess blast radius for each se

Finds industry event and conference coverage on Google using apidojo's Google Search scraper. Triggers when the user asks to: find coverage of an industry conference or event on Google, track press co

Install, configure, verify, or troubleshoot the @jwongart/openclaw-minimax-media OpenClaw plugin for MiniMax image understanding, image generation, music generation, video generation, text-to-speech,

Detect and optionally mask PII (emails, phone numbers, SSNs, names, addresses, credit cards) in text. Pay $0.02 USDC via x402.

AI-powered multimodal analysis for images and videos. Structured tags, scene descriptions, mood analysis, virality scores. 15 languages. Users provide their own URLs — this tool does not scrape or ...

Analyzes and rewrites calendar events into clear, actionable tasks. Removes meeting fluff and converts vague descriptions into specific deliverables with deadlines.

将论文 PDF 批处理为中文精读总结报告的工作流技能。适用于“PaddleOCR 或 pdfplumber 抽取文本 + 大模型总结论文”场景。使用时仅读取 skill 目录下 config.json 与 prompt.md，并运行 scripts 中所需脚本，用户可在prompt.md中定义用户研究主题与研究方向。