Skill rating

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

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

Use StepFun Chat Completions with model step-audio-r1.1 for non-streaming speech turns that can send text with optional local audio input and save the returned audio, transcript, and raw response obje

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

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

Reduce Anthropic API costs (cache read, compaction, context bloat) for OpenClaw agents. Use when users ask about token optimization, reducing API costs, cache read expenses, context management, worksp

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

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

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

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

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

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.

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

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

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

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

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

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

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

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

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

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

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

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

Military-Civilian Dual-Use Talent Assistant based on the classic Military-Civilian Dual-Use Talent Handbook. Covers agriculture, machinery, construction, electrical, photography, seal-carving, cooking

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", "

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

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,

Comprehensive time series data science skill covering feature engineering, model training, and competition-winning strategies for forecasting and prediction problems.

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

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

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.

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

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

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

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

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.

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。

Monitor construction progress from multi-temporal satellite imagery. Classifies project stages (clearing, earthwork, foundation, structure, finishing, completed) using spectral indices and detects sta

Extract shorelines, centerlines and channel widths from multi-temporal water body masks. Quantify shoreline migration, channel migration, change hotspots and migration zones. Use when analyzing river

Render reports (HTML/DOCX/PDF) from other skills' output-manifest.json. Auxiliary tool only — does not analyze data, does not download anything. Workflow: run another skill to produce output-manifest.

Seedream 4 image generation and editing on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `seedream-4`, `seedream-4-edit`, text-to-image, image editing, reference images, 1K/2K/

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

Professional KuCoin (KC) trading system - multi-account support, spot/margin/futures trading, asset transfers. Use to check balances, transfer assets, open/close positions, and manage your KuCoin port

Validate Moltbook API requests before sending. Checks required fields (content, title, submolt), warns about incorrect field names (text vs content), prevents failed posts and wasted cooldowns. Use be

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

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