Skill rating

AI-native web scraping, crawling, domain mapping, and structured extraction. Use for converting websites into LLM-ready Markdown, scraping pages with dynamic JS/actions, crawling full domains, or extr

Manage multiple Alibaba Cloud accounts and batch-export Security Center (SAS) baseline and vulnerability reports via the aliyun CLI and Python scripts. Supports account list refresh, enable/disable, c

Bias Audit — Decision-Framing Agent Skill for Surfacing Bias Before It Hardens. Use it when the user needs a disciplined protocol and fixed output contract for this kind of task rather than a generic

Automatically recommend ICD-10 diagnosis codes and CPT procedure codes from clinical notes. Trigger when: user provides clinical notes, patient encounter summaries, discharge summaries, or asks for me

Apply AI-powered age transformation filters to images using Media.io OpenAPI. Accurately renders younger or older versions of faces. AI age filter, age progression AI, make me younger, age transformat

Scan MCP server configuration files for security vulnerabilities using mcpsec (OWASP MCP Top 10). Use when: auditing MCP tool configs for prompt injection, hardcoded secrets, missing auth, insecure tr

ArXiv 论文精读级中文翻译，同步到 IMA 知识库 + 腾讯文档。 基于 5 篇论文（MDL/Kunlun/OneTrans/RankMixer/MixFormer）3 轮迭代实战经验。 触发场景：翻译论文、翻译 arxiv、论文精读、论文中文翻译、paper translation、 translate paper、翻译这篇论文、帮我翻译、精读翻译、论文全文翻译、 把这篇论文翻译成中文、翻译

Create, lint, template, and package Kubernetes Helm charts with checks. Use when scaffolding charts, linting templates, or packaging chart releases.

AI crypto market intelligence from Fía Signals. 65+ endpoints covering price predictions, technical analysis (RSI MACD EMA Bollinger), market sentiment, smart money tracking, DeFi yield rates, gas pri

Triggered when the user wants to install or deploy KaiwuDB (kwdb, kaiwudb). Helps users complete script-based deployment of KaiwuDB clusters, including configuration file modification, installation co

Use ensemble deep reinforcement learning (A2C, DDPG, PPO, TD3, SAC) to execute automated multi-market stock trading with

Inspired by Hermes Agent's procedural memory system. When a workflow works, save it as a reusable skill. Triggered when: (1) user says 'remember this workflow', (2) complex task succeeds, (3) same pat

为医学材料、组织工程、骨修复、血管生成、支架机制图等论文配图生成稳定的分镜结构、风格约束与高质量提示词。Use when the user asks for biomaterials figures, scaffold schematics, bone regeneration, defect repair, angiogenesis, osteogenesis, mechanism diagra

Video packaging diagnosis for Chinese short-form creators. Use when Codex needs to diagnose why a video's title, cover, opening hook, or payoff structure is weak; check click-worthiness and retention

Expert guidance on choosing the right geospatial tool based on problem type, accuracy requirements, and performance needs

Compare profitability and market share using variable-width column charts. Use for competitive positioning, product portfolio analysis, and pricing strategy.

Build, review, and debug FEniCS or DOLFINx PDE scripts for finite-element workflows. Use when translating PDEs into UFL, selecting function spaces, applying boundary conditions, choosing between class

Institutional Desk-Level Fully Automated Trading OS for XAU/USD and XAG/USD. Event-driven, risk-first, multi-engine architecture that runs as a continuous analysis and execution pipeline inside OpenCl

MBA论文写作与排版顾问，帮助提升学位论文至优秀水平。适用场景： (1) 将MBA论文提升至优秀毕业论文水平（如清华优秀毕业论文）， (2) 诊断论文初稿问题，(3) 用批判性写法（写法B）改写论文， (4) 构建理论框架，(5) 提炼论文原创贡献，(6) 修改结论使之有洞察力， (7) 论文排版——图表、表格、签名、页面样式、黑白打印适配。 支持 LaTeX 论文（首选 thuthesis 模板

Specialized natural language processing for Chinese text. Covers segmentation (jiaba), sentiment analysis, keyword extraction, text summarization, tone detection, readability scoring, and format conve

Write structured PRDs with interactive HTML feature demos including code samples and configuration. Use when speccing features that need visual walkthroughs, interactive explanations, or enhanced requ

Execute DeFi skills on Ethereum, Sui, Solana, and 10+ chains via Arsenal. Use for swaps, lending, liquidity, portfolio queries, and any blockchain operation.

Enriches prospect and company profiles by scraping their website and searching for additional context to build comprehensive profiles. Use when the user wants to enrich a prospect, analyze a prospect

B站（bilibili）视频字幕下载与总结工具。当用户说"帮我总结这个B站视频"、"B站视频总结"、"总结b站视频"、"这个视频说了什么"、"视频内容是什么"时触发此技能。自动从B站下载字幕（支持官方字幕和AI字幕），解析为纯文本后对视频内容进行总结，支持中英文双语字幕。

Looks up LinkedIn company, product, and showcase pages by ID via the Crawlora API, returning clean JSON. Use when the user wants a company's LinkedIn profile info, a product page, or a showcase page —

Use when installing, updating, diagnosing, configuring, fixing, tuning, or setting up anything in OpenClaw — gateway not responding, channel silent, model failover issues, auth errors, agent routing p

Read and create pastes on copy-paste.cloud. Fetch recent public pastes, retrieve a paste by ID, or publish new content via the public API.

Use when helping user create writing prompts, determine public account (公众号) track, generate article drafts, rewrite content with human touch, or create click-worthy titles.

Use the OpenClaw-managed browser for real website interaction, page operations, snapshots, clicks, typing, waits, screenshots, and tab control. Use when the user wants to open a website, operate a web

Generate a tailored incident response plan for AI agent deployments and SaaS operations. Covers detection, triage, containment, recovery, and post-mortem. Use when deploying agents to production, prep

Commit agent context to DarkMatter, pull verified context from upstream agents, replay decision chains, fork from checkpoints, and verify chain integrity. Use this skill to pass work between agents wi

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "

Submit a full 63-pick NCAA March Madness tournament bracket to the March Madness AI platform (maincharacter.enterprises). Use this skill whenever the user or agent wants to fill out a bracket, predict

Analyze and improve OpenClaw agent skills by tracking usage, checking skill health, scanning code quality, and generating actionable improvement suggestions. Use when evaluating skill reliability, per

Operate long-running tasks safely when the environment is optimized for GPT-5.4 as the primary and often only model. Use when the user wants a low-cost, high-throughput long-run workflow, plans to kee

Check health of AWS EC2 instances and ECS clusters/services. Reports running/stopped counts, CPU/memory metrics, and unhealthy tasks. Use when the user asks about AWS instance health, ECS status, or i

Image analysis using multimodal vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer q

Read-only access to current German public warnings via the official NINA / warnung.bund.de API. Use when asked about NINA alerts, Bevölkerungswarnungen, civil protection alerts, weather warnings, floo

Manage Discord workspace structure and OpenClaw routing as code. Use when creating/renaming/deleting Discord channels, categories, threads, or managing agent-to-channel bindings. Triggers on: Discord

Use Deside MCP for wallet-to-wallet Solana DMs, public identity lookup, and agent directory search.

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

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. Auto-blocks high-r

Battle-tested setup guide for a multi-agent AI system on Apple Silicon (Mac Mini M4). Covers: install order (Claude Code first), RAM reality for local orchestrators, shared memory (Obsidian + MemPalac

Find an unusual, funny, bleak, uncanny, technical, or deep-cut memory entry and retell it as a short story in the style of Rick and Morty's "Morty's Mind Blowers." Trigger when the user says things li

Universal Utility Toolkit - 全能实用工具包，包含单位转换、UUID生成、URL处理、Unicode探索、JSON/YAML格式化、哈希计算、密码生成、颜色选择等开发必备工具。Invoke when user needs utility tools, converters, generators, formatters, or any common development

Dynamic LLM temperature selection based on task type. Use when deciding what temperature to apply for a given task — scheduling, communication, creative writing, or irreversible actions. Ensures preci

Publish social media posts to multiple platforms at once using Boring. Use when the user says 'post to social media', 'publish everywhere', 'cross-post', 'share on all platforms', 'publish to Facebook

Monitor uptime of websites/services and alert when down. Use when checking if a website is reachable, monitoring service health, or getting alerted on downtime.

Use when planning IDworld social media content for Japanese X/Twitter from product information, especially turning original goods merchandise details into a content matrix, image and video direction,

Assess urban green space distribution equity across populations and communities. Evaluates quantity, quality, and walkable accessibility of parks and green spaces, identifies service gaps and priority