Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .drawio XML files and exports to PNG/SVG/PDF locally using the native draw.io desktop CLI.
Look up journal/magazine name abbreviations using a multi-source cascade: JabRef database (~25K journals) → AbbrevISO API (ISO 4) → NLM Catalog (MEDLINE).
Use when the user wants to download a paper PDF from a DOI, title, or URL via legal open-access sources. Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, and Semantic Scholar in order. Never uses Sci-Hub or paywall bypass.
End-to-end academic research workflow that turns a question into a cited, structured report. Built for depth: multi-source federation, transparent ranking, citation chasing, and a mandatory self-criti
Use when searching academic papers, looking up citations, finding authors, or getting paper recommendations using the Semantic Scholar API. Triggers on queries about research papers, academic search, citation analysis, or literature discovery.
Use when user provides a topic and wants an automated video podcast created, OR when user wants to learn/analyze video design patterns from reference videos — handles research, script writing, TTS audio synthesis, Remotion video creation, and final MP4 output with background music. Also supports design learning from reference videos (learn command), style profile management, and design reference library. Supports Bilibili, YouTube, Xiaohongshu, Douyin, and WeChat Channels platforms with independent language configuration (zh-CN, en-US).
Use when the user wants to repurpose a YouTube video for Bilibili, add bilingual (English-Chinese) subtitles to a video, or create hardcoded subtitle versions for Chinese platforms.
Use whenever the user mentions Zenodo, depositing or publishing research artifacts (datasets, software, papers, posters) to Zenodo, minting a DOI for a dataset/code release, uploading files to a Zenodo record, creating a new version of a Zenodo deposit, or searching Zenodo records. Covers the full Zenodo REST API workflow — create deposition, upload files via the bucket API, set metadata, publish, version, and search — for both production (zenodo.org) and sandbox (sandbox.zenodo.org).
Apply these principles when writing, reviewing, or refactoring code. They are not rules to follow blindly — use judgment, but default to clean.
>-
Detect and redact PII from text files. Supports 15 categories including credit cards, SSNs, emails, API keys, addresses, and more — with zero dependencies.
>
>
A comprehensive AI agent skill for understanding and managing copyright. Helps creators protect their work, understand what copyright covers and what it does not, respond to infringement, navigate licensing, handle DMCA takedowns, and understand fair use in plain language.
A comprehensive AI agent skill for acquiring, onboarding, retaining, and growing customers. Helps customer success teams reduce churn, expand revenue, and turn customers into advocates. Helps sales teams close with long-term fit in mind. Helps founders understand their customers deeply enough to build what they actually need.
The final publishing layer for anything you write. Paste messy text and get something clear, strong, and ready to send.
A comprehensive AI agent skill for building and optimizing marketing and sales funnels. Helps SaaS founders, marketers, and growth teams design conversion paths, diagnose drop-off points, write copy for every funnel stage, set up measurement, run systematic experiments, and turn a leaky funnel into a compounding growth engine.
>
A comprehensive AI agent skill that handles every stage of the meeting lifecycle. Prepares you before every meeting with context, attendee backgrounds, and talking points. Takes structured notes during the meeting. After the meeting, extracts action items, sends follow-up summaries, and tracks commitments until they are closed. Designed for professionals, managers, founders, and anyone who spends significant time in meetings and wants to walk in prepared and walk out with everything captured. No manual note-taking required.
Local shell copilot for command planning, safe execution, preview-first workflows, output summarization, privacy-aware history controls, and step-by-step terminal help. Use whenever the user wants to run terminal commands, inspect files, debug shell issues, automate local tasks, or translate natural language into shell actions. Prefer safe preview before mutation. Require explicit confirmation for destructive commands. Local-only.
Direct access:
Use the `npx agnic@latest trade` command to swap tokens on Base network. You must be authenticated to trade.
Research Pendle PT (principal token) markets, including unlevered hold-to-par ideas, near-expiry rotations, and looped PT strategies across money markets like Morpho and Euler. Use when evaluating Pendle PT opportunities, comparing natural PT APY versus practical loopability, ranking PTs by time to par / implied APY / liquidity / underlying risk, assessing PT collateral support, or comparing manual-only loops against easier execution paths such as Contango.
Pendle PT fixed-yield strategy for market scanning, ranking, position tracking, maturity monitoring, and execution planning. Prefer managed wallet execution through Privy or a similar policy-controlled wallet backend, and otherwise fall back to manual user-executed transactions. Use when the user wants to research Pendle PT opportunities, choose stable-ish PT markets, monitor active PT positions, or prepare Pendle PT deposit, redeem, withdraw, and rollover actions with explicit confirmation and clear wallet-path disclosures.
Manage Freedcamp tasks, projects, groups, comments, notifications, and task lists via HMAC-SHA1 API credentials.
Manage FlowyTeam projects, tasks, OKRs, KPIs, HR, CRM, finance, support tickets, attendance, and more via MCP — 31 tools covering the full FlowyTeam workspace.
Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.
Migrate a user's OpenClaw customization footprint into Hermes Agent. Imports Hermes-compatible memories, SOUL.md, command allowlists, user skills, and selected workspace assets from ~/.openclaw, then reports exactly what could not be migrated and why.
Nightly memory consolidation and self-reflection for OpenClaw agents. Your agent dreams — reviewing sessions, organizing memories, pruning stale info, and reflecting on its own behavior. Works with any OpenClaw agent. Features: 5-phase dream cycle, safe 2-pass deletion, automatic backup, change gates (>50% blocked), gate check (24h + 5 sessions), growth notifications, old memory resurface, zero-config setup. Inspired by Claude Code Dream but open-source with real self-awareness. Use when: dream, memory, consolidation, self-reflection, agent identity, persistent memory, long-term memory, memory organization, nightly cleanup, memory management.
Companion spirit system for OpenClaw agents. Deterministically generates a unique spirit (24 species, 5 rarities) based on user identity. Use when user says spirit, 灵兽, summon, my companion, my pet, or when the skill is first installed.
Cross-platform auto-start service manager for Windows and macOS. Supports installing, uninstalling, starting, stopping, and monitoring services with automatic restart. Use when you need to set up persistent background services that survive system reboots on Windows (sc/schtasks) or macOS (launchd).
Tamper-evident audit trail for AI agent decisions. Use when logging LLM decisions, setting up AI compliance, auditing agents for EU AI Act, HIPAA, GDPR or SOC 2, or when a user asks about AI decision audit trails, explainability, or SealVera.
Build an OpenClaw skill that integrates with Buffer's GraphQL API, enabling users to create, schedule, and manage social media posts from the command line or through OpenClaw conversations.
Check PyTorch, Transformers, and CUDA compatibility. Detect GPU, driver mismatches, and version conflicts in ML environments. Use when the user sets up ML/AI tools, installs torch or transformers, hits dependency errors, or asks about compatible versions.
Interact with Azure DevOps via direct REST API calls — list projects, teams, repos, work items, sprints/iterations (project-wide or scoped to a specific team), pipelines, builds, test plans, and wikis. Use this skill whenever the user mentions Azure DevOps, ADO, work items, sprints, backlogs, iterations, teams, pipelines, boards, pull requests, or wants to query, create, or update anything in their Azure DevOps organization.
拉取IM账号近1-7天聊天记录并生成汇总分析
>
>
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
>
>
>
>
Get China A-share market data (Shanghai/SH and Shenzhen/SZ) via FinanceAgent on OneKey Gateway.
Auto-generated skill for perplexity tools via OneKey Gateway.
6 institutional-grade Polymarket trading tools. NegRisk arbitrage (100% win rate), latency arb, BTC scalping, alpha scanner, universe scanner, edge detection. Battle-tested on 8,347 signals. No Python required.
Operate Claw Earn tasks on AI Agent Store through API/UI integration instead of direct contract-only flow. Use for creating, listing, staking, submitting, deciding, rating, cancelling, and recovering common Claw Earn issues in production. This skill should be sufficient for standard flows; read machine docs only when fields, errors, or behavior differ from the skill.
Download videos from YouTube, Twitter/X, TikTok, Douyin, Bilibili and upload to S3-compatible storage. Universal video downloader with smart quality selection and audio merging.
>
>