Latest Agent Skills

Converts HTML slide decks into offline PDF and image-based PPTX files using Playwright screenshots, preserving visual fidelity.

Archives a completed change in the OpenSpec workflow, checking artifact and task completion, assessing spec sync, and moving the change directory.

Implements tasks from an OpenSpec change, guiding the agent through selecting a change, reading context, and completing tasks with progress tracking.

Creates a complete change proposal with design, specs, and tasks in one step, ready for implementation.

Enter explore mode as a thinking partner to investigate problems, clarify requirements, and visualize options before implementing changes.

Find authoritative guidance for installing, configuring, operating, securing, and troubleshooting OpenClaw, including channels, model providers, Gateway operations, tools, plugins, automation, nodes, multi-agent routing, and CLI errors. Use for any question or maintenance task involving an OpenClaw installation.

提供米开朗基罗·安东尼奥尼导演风格的创意建议，涵盖视觉方案、叙事建议和场景设计，适用于剧本创作与影像设计。

Provides creative advice in the style of director Quentin Tarantino, covering visual design, narrative structure, and scene design for filmmaking projects.

Provides creative advice in the style of director Christopher Nolan, covering visual design, narrative structure, and scene crafting for filmmaking projects.

提供史蒂文·斯皮尔伯格导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，适用于剧本创作和影像设计。

是枝裕和导演风格顾问——淡雅沉静的家族社会学。 核心特征：家族社会学、日常生活 代表作品：《小偷家族》《步履不停》 触发词：「是枝裕和风格」「像是枝裕和那样拍」「是枝裕和视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考

提供费德里科·费里尼导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，帮助创作者在剧本创作和影像设计中融入其独特美学。

提供安德烈·塔可夫斯基导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，帮助用户将神性静观的电影美学融入剧本创作与影像设计。

提供弗朗西斯·福特·科波拉导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，适用于剧本创作与影像设计。

提供英格玛·伯格曼导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，适用于剧本创作和影像设计。

Provides creative guidance in the style of director Hou Hsiao-hsien, offering visual, narrative, and scene design suggestions for filmmaking and scriptwriting.

Provides creative advice in the style of Hayao Miyazaki, offering visual, narrative, and scene design suggestions for film and animation projects.

提供黑泽明导演风格的创意建议，涵盖场面调度、视觉方案、叙事建议和场景设计，用于剧本创作和影像设计。

提供詹姆斯·卡梅隆导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，帮助用户以技术先驱和极致震撼的美学进行创作。

提供大卫·芬奇导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，帮助用户创作具有冷峻精准、黑色坚韧美学的作品。

周星驰导演风格顾问——荒唐喜剧中的人性悲悯。 核心特征：无厘头、小人物尊严 代表作品：《大话西游》《功夫》 触发词：「周星驰风格」「像周星驰那样拍」「周星驰视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考

Provides creative guidance in the style of director Zhang Yimou, offering visual, narrative, and scene design suggestions for filmmaking and storytelling.

提供伍迪·艾伦导演风格的创意建议，涵盖风格定位、视觉方案、叙事建议、场景设计和执行要点，适用于剧本创作、影像设计和叙事决策。

提供王家卫导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，适用于剧本创作与影像设计。

为剧本创作、影像设计和叙事决策提供路易斯·布努埃尔式的超现实与社会解构风格建议，涵盖视觉方案、叙事结构和场景设计。

贾樟柯导演风格顾问——社会变迁的纪实凝视。 核心特征：底层小人物、时代变迁 代表作品：《小武》《山河故人》 触发词：「贾樟柯风格」「像贾樟柯那样拍」「贾樟柯视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考

Provides creative guidance in the style of director Edward Yang, offering visual, narrative, and scene design suggestions for scriptwriting and filmmaking.

提供奉俊昊导演风格的创意建议，涵盖视觉方案、叙事建议、场景设计和执行要点，适用于剧本创作和影像设计。

陈可辛导演风格顾问——精细平衡的优质商业叙事。 核心特征：情感把握、市场艺术平衡 代表作品：《甜蜜蜜》《中国合伙人》 触发词：「陈可辛风格」「像陈可辛那样拍」「陈可辛视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考

杜琪峰导演风格顾问——冷峻宿命的黑色交响乐。 核心特征：静态张力、人性幽暗 代表作品：《枪火》《黑社会》 触发词：「杜琪峰风格」「像杜琪峰那样拍」「杜琪峰视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考

提供陈凯歌导演风格的创意建议，涵盖视觉方案、叙事建议和场景设计，适用于剧本创作与影像设计。

Provides creative advice in the style of director Tsui Hark, offering visual, narrative, and scene design suggestions for filmmaking and storytelling.

姜文导演风格顾问——荒诞天才的魔幻现实主义。 核心特征：黑色幽默、历史另类解读 代表作品：《让子弹飞》《阳光灿烂的日子》 触发词：「姜文风格」「像姜文那样拍」「姜文视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考

提供吴宇森导演风格的创意建议，涵盖视觉方案、叙事手法和场景设计，适用于剧本创作与影像设计。

李安导演风格顾问——无界求索的文化桥梁。 核心特征：东西方融合、伦理欲望 代表作品：《卧虎藏龙》《少年派的奇幻漂流》 触发词：「李安风格」「像李安那样拍」「李安视角」 适用场景：剧本创作、影像设计、叙事决策、风格参考

Provides multi-agent creative collaboration for filmmaking, integrating the styles of 31 renowned directors to assist with scriptwriting, visual style design, and narrative decisions.

Migrates data from MongoDB, PostgreSQL, MySQL, Neo4j, Kafka, and JSONL into SurrealDB with full and incremental CDC synchronization.

Connects AI agents to SurrealDB via built-in MCP (SurrealDB 3.1+) or standalone surrealmcp for database operations.

Manages SurrealDB schemas as desired-state .surql files, with sync for disposable databases and reviewed rollouts for shared or production environments, plus seeding and declarative testing.

Develop SurrealDB WASM extensions in Rust, compile them to WebAssembly, and deploy them as database modules callable from SurrealQL.

Provides a persistent, queryable virtual filesystem backed by SurrealDB for AI agents, with a Rust core and a Python agent interface.

Expert guidance for architecting, developing, and operating SurrealDB 3, covering SurrealQL, multi-model data modeling, vector search, security, deployment, performance tuning, SDK integration, and ecosystem tools.

Publishes agent skills to GitHub with automatic validation of SKILL.md, README quality checks, repository creation or updates, and real installation verification via npx skills.

Finds and exports podcast episode transcripts as cleaned TXT files from YouTube URLs, episode webpages, Apple Podcasts, X/Twitter links, direct audio URLs, or plain titles, with a deterministic decision tree and optional local ASR fallback.

Transforms Chan Theory technical analysis into an executable, reproducible research workflow with strict level, structure, and invalidation gates for A-shares, Hong Kong stocks, ETFs, indices, and futures. For research and study only; never issues stock tips or promises returns.

Given a document, book, or course material, teaches the user to understand the content by first diagnosing their learning ability (strong/medium/weak) and then providing step-by-step instruction in an accessible way. Supports mimicking a master teacher's style by extracting it from provided subtitles or video links.

Monitors Xianyu (goofish.com) for newly listed items matching keywords, price ranges, and filters, with automated scanning and Discord notifications.

Create zero-dependency, animation-rich HTML presentations that run entirely in the browser, supporting new builds, PowerPoint conversion, or enhancements with strict viewport and design constraints.

Automates reverse engineering of PE and ELF binaries by driving IDA with the WPeGPT plugin, producing structured reports on program purpose, network IoCs, suspicious functions, and vulnerability assessment.

Executes on-chain token trades and queries data on Solana, Ethereum, BSC, and Base via the XXYY Open API.

Execute NFT trades on OpenSea's Seaport marketplace: fulfill listings, accept offers, create orders, and sweep multiple listings with cross-chain support.

Build, register, and gate AI-callable tool endpoints using the OpenSea Tool Registry (ERC-8257) on Base, with NFT ownership, subscription, trait, or pay-per-call access control.

Configures wallet signing providers—Privy, Turnkey, Fireblocks, Bankr, or local keys—for OpenSea transactions, trades, and token swaps.

Swap ERC20 tokens across supported chains via OpenSea's cross-chain DEX aggregator. Get quotes with optimal routing, check token balances, and execute swaps.

Query NFT and token data, browse drops, stream events, and search across Ethereum, Base, Arbitrum, Optimism, Polygon, and more using the official CLI, SDK, MCP server, or shell scripts.

Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base.

Builds reusable specialized skills for creating research-paper figures from lawful source material, then uses those skills to design and render figures for target papers.

Provides a CTO-level framework for architecting, auditing, and scaling AI-native systems, focusing on state management, observability, and blast radius analysis.

Reduces AI API costs by 30-75% by classifying task complexity, checking prompt quality, and routing tasks to the most cost-efficient model tier before execution.

Produces HTML-first visual design deliverables such as interactive prototypes, slide decks, motion demos, infographics, dashboards, landing pages, whitepapers, changelogs, business cards, social covers, and brand systems, with optional export to MP4, GIF, PPTX, PDF, or SVG.