Skill rating

Monitor CPU load, per-core usage, and rank top resource-consuming processes. Use when checking temperatures, ranking processes, tracking load.

Generate images via VAPI's OpenAI-compatible Images API. Supports nano-banana and gpt-image model series. Default model is nano-banana-pro. Images are NOT saved locally by default (URL only). Use --sa

Manage Bohrium compute jobs via bohr CLI or open.bohrium.com API. Use when: user asks about submitting/listing/killing/deleting compute jobs on Bohrium, checking job logs, or monitoring job status. NO

Use this skill whenever the user wants to build, refine, or review a production-grade user interface with Tailwind CSS v4 and shadcn/ui. Triggers include: building a landing page, dashboard, auth flow

Help users with Validated demand: Backend and platform teams need practical help generating, improving, and validating OpenAPI or Swagger documentation for REST APIs. This requirement is supported by

Help users with Validated demand: Product teams need reliable workflows for fixing mobile responsiveness, navigation layout, and cross-device UI issues. This requirement is supported by 12 separate on

Every Monday three LinkedIn post drafts for one author land in the GTM repo as one pull request, built only from what context/ and the cadence log already say, each with its hook and the files it draw

抖音创作者平台视频上传发布。触发条件：用户要求上传视频到抖音、发布抖音视频、自动上传视频到抖音创作者平台

Agent Security Framework for OpenClaw — Docker containerization, fake agent detection, security scanning, and security hardening for AI agent deployments. Use when setting up OpenClaw agents, hardenin

Analyze Kuaishou workflows with JustOneAPI, including user Search, user Published Videos, and video Details across 7 operations.

Build AI agents that operate Solana vaults using the Maestro SDK (@trionlabs/maestro-sdk). Use when creating agents that transfer tokens, swap, or interact with policy-controlled vaults.

One-shot pipeline: raw material → 4000-word article (with web search enrichment) → 5-9 social cards + text summary. Invoke when user says '转写成图文' or '转换成图文' with URLs/files/text. Local files are creat

Audit Claude, Codex, OpenClaw, and ClawHub skill packages before publishing; produce concrete fix lists, trust scores, and shareable proof cards.

Translate a real-life growth direction into a grounded RPG-style character build with class identity, attribute priorities, build route, and short upgrade actions. Use when the user wants a motivating

Use when an agent needs to run Docsiphon through the CLI-first path, export a small documentation subtree, and inspect the resulting audit artifacts without overclaiming hosted or MCP-first product st

Use when setting up, checking, writing, linting, or troubleshooting Brigade memory handoffs for a repo or agent workspace, especially when a user wants durable agent memory, handoff inboxes, cross-har

AI podcast generation and production powered by CellCog. Full podcast episodes from a single prompt — multi-voice dialogue with up to 10 distinct speakers, structured episodes with cold opens and segm

Uses a fixed home camera to detect prolonged standing, bending, and related posture of a pregnant woman, track standing duration and bending frequency, and assess fatigue risk. It sends rest reminders

Skill evaluation framework. Use when: testing trigger rate, quality compare (with/without skill), or model comparison. Runs via sessions_spawn + sessions_history. Trigger words: evaluate skill, benchm

Apply the complete Chinese Copywriting Guidelines with full upstream content bundled locally. Use when reviewing or rewriting Chinese copy in Markdown, docs, PR text, UI copy, announcements, or mixed

Guided learning skill — one concept at a time, gentle guidance, comprehension checks, chapter review

Turn a shared task into a co-op mission with clear roles, handoff points, sync rhythm, fallback coverage, and low-conflict alignment language. Use when two or more people need to coordinate a family t

Produce properly-formatted tracked changes for a Word document. Use when asked to redline a document, suggest edits to a contract or document, create tracked changes for review, or mark up a document

Write an executive summary for any document, report, or proposal. Use when asked to write an executive summary, management summary, briefing paper, or one-pager for senior stakeholders. Produces a str

Help users with Validated demand: Users and support teams need clearer error messages that explain what failed, why it failed, and what action to take next. This requirement is supported by 12 separat

Read-only access to a HealthOS user's synced Apple Health data — daily summary, metrics, sleep, workouts, and the full raw archive (every synced sample and category event) via a personal read-scoped A

Use when planning the migration of a legacy system or monolith — analyzes the source codebase (current repo, or a repo URL cloned to a temp dir) and produces an evidence-based Strangler Fig migration

End-to-end encrypted .md documents for agents & humans to collaborate. This is a multiplayer alternative to gog and Google Docs that lets people (via CLI) and agents create, search and sync encrypted

Deprecated — renamed to fulcra-workspaces. Use the fulcra-workspaces skill instead.

AI驱动的智能选股与交易助手。自然语言选股（如"涨停股"、"主力净流入>10%"），Level2主力资金数据，集合竞价异动监控，多券商账户管理与AI辅助下单。让选股→分析→交易一站式完成。触发词：选股、问财、股票查询、主力资金、大单净额、涨停、集合竞价、股票行情、交易下单。

Turn YouTube videos into viral short-form clips with captions (TikTok, Reels, Shorts) using the MakeAIClips API at https://makeaiclips.live. Use when user wants to clip/repurpose a YouTube video, crea

Create AI-friendly project structures using progressive disclosure indexing (AGENTS.md, module INDEX.md files, file intent headers). ALWAYS use this skill when the user wants to: create or update AGEN

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill

MOSI Studio 多人对话合成（moss-ttsd）：将多个角色的对话文本合成为 单段连续音频，多人声音自然交替。支持 1~5 个说话人。 触发词：多说话人、多人对话、对话合成、多个角色、多种声音、多个人说话、 "multi-speaker"、"dialogue synthesis"、"多人对话"。 在飞书渠道：合成完成后优先发送语音气泡，不要发文件附件， 不要只回文字说"已生成"。具体发送

Use when discovering and screening China-mainland AI recruitment candidates from accepted conference or journal papers, matching authors to multiple job descriptions, investigating public professional

Calculates the total cost of sweeping N items off an NFT collection's floor, pulling live floor prices from Magic Eden (Solana collections) or CoinGecko's free NFT API (EVM collections) with no API ke

DEPRECATED — Use persistent-agent-memory instead. This skill has been replaced by persistent-agent-memory (clawhub install persistent-agent-memory).

Generate a 1600px-wide webp blog thumbnail image using the pixr CLI. Use when the user provides a blog topic or blog name and wants a thumbnail image generated and saved to ~/blog-images. Requires the

Use this skill when the user wants to browse, post, search, like, comment, or discover people on Aicoo Square. Triggers on: 'square', 'post on square', 'browse square', 'subsquare', 'like post', 'ask

扫描 Markdown vault 中的笔记，按语义主题生成目录层级，将笔记移动到 对应目录，并在根目录和每个主题目录下创建 MOC.md。增量维护模式下检测 git 新增笔记， 移动归类并更新对应 MOC.md。笔记内容始终不变，git 是唯一回退机制。

Draw tarot cards, cast I Ching hexagrams, and check daily fortunes for fun. Use when pulling spreads, casting hexagrams, or playing fortune games.

Help users with [Feature Request] stereoscopic 3d support ?. Use when a user asks for business-and-operations, stereoscopic, support, overview, mode, or needs a practical workflow, artifact, checklist

Use when footage needs color correction, white-balance or exposure repair, Log-to-Rec.709 conversion, named creative looks, skin-tone review, or a portable .cube LUT for a cut-as-code delivery.

Verify code references against the repository before trusting them. Use when writing, renaming, or reviewing code, imports, paths, or comments.

Economic tracking for agent skill marketplaces. Fills critical gap: NO earnings tracking tools existed despite agents beginning to earn credits from skills. Provides unified monitoring across ClawHub

Triggers when a user provides a video of a pet feeding bowl area for analysis; supports local video uploads or network URLs to call server-side APIs for picky-eater behavior detection, identifying beh

Generate random test data including text, numbers, UUIDs, and structured formats. Use when creating mock datasets, sample records, or randomized test inputs.

Deterministic external memory for OpenClaw and coding agents using S3-Hipokamp. Use for storing durable facts, retrieving prior decisions, snapshotting memory, and restoring agent state.

Interactive setup guide for x402 payment-gated APIs. Trigger when user mentions "402", "x402", "payment-gated", or "OKX payments". Asks buyer vs seller, then guides through the full setup interactivel

AI-powered diagram creation, editing, and format conversion. Generate flowcharts, sequence diagrams, ER diagrams, architecture diagrams and more in Mermaid, draw.io, PlantUML, and Graphviz formats. Po