تصفح المهارات

Create professional cinematic scripts for AI video generation with character consistency and cinematography knowledge. Use when the user wants to write a cinematic script, create story contexts with characters, generate image prompts for AI video tools (Midjourney, Sora, Veo), or needs cinematography guidance (camera angles, lighting, color grading). Also use for character consistency sheets, voice profiles, anachronism detection, and saving scripts to Google Drive.

Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: images, videos, reels, shorts, thumbnails, captions, hashtags. Tools: FLUX, Veo, Seedance, Wan, Kokoro TTS, Claude for copywriting. Use for: content creators, social media managers, influencers, brands. Triggers: social media content, tiktok, instagram reels, youtube shorts, twitter post, content creator, ai influencer, social content, reels, shorts, viral content, thumbnail generator, caption generator, hashtag generator, ugc content

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, whisper, PlayAI TTS, Llama, vision API, tool calling, voice agents, real-time AI.

Use when editing videos with DashScope HappyHorse 1.0 video editing model (happyhorse-1.0-video-edit). Use when implementing instruction-based video editing such as style transfer or local replacement, optionally guided by 0-5 reference images, via the video-synthesis async API on Alibaba Cloud Model Studio.

Comprehensive diagnostic, error-fixing, and skill recommendation tool for OpenClaw

Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts. Models: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting. Use for: better AI outputs, consistent results, complex tasks, optimization. Triggers: prompt engineering, how to prompt, better prompts, prompt tips, prompting guide, llm prompting, image prompt, ai prompting, prompt optimization, prompt template, prompt structure, effective prompts, prompt techniques

Expert Node.js and TypeScript development assistant. Use when writing, reviewing, or debugging Node.js code, TypeScript projects, async programming, streams, performance optimization, or npm packages.

Use when building Next.js 14/15 applications with the App Router. Invoke for routing, layouts, Server Components, Client Components, Server Actions, Route Handlers, authentication, middleware, data fetching, caching, revalidation, streaming, Suspense, loading states, error boundaries, dynamic routes, parallel routes, intercepting routes, or any Next.js architecture question.

Generate 10 perspective/angle variations from a single image for multi-shot UGC videos. ✅ USE WHEN: - Have a hero image and need camera angle variations - Creating multi-scene UGC videos (need different shots) - Want close-ups, wide shots, side angles from one source - Building a video with scene changes ❌ DON'T USE WHEN: - Don't have a hero image yet → use morpheus-fashion-design first - Need completely different scenes/locations → use Morpheus multiple times - Just need one image → skip this step - Want to edit images manually → use nano-banana-pro INPUT: Single image (person with product) OUTPUT: 10 PNG variations with different perspectives TYPICAL PIPELINE: Morpheus → multishot-ugc → select best 4 → veed-ugc each → Remotion edit

Single-image generation skill for posters, key art, and editorial illustrations. Defaults to gpt-image-2 but is provider-agnostic — the same workflow drives Flux, Imagen, or Midjourney via the active upstream tooling. Output is one or more PNG/JPEG files saved to the project folder.

Use this skill when users need to search the web for information, news, images, or videos. Triggers include: requests to "search for", "find information about", "look up", "what's the latest on", or any request requiring current web content. Also use for research tasks, fact-checking, finding visual resources, or gathering recent news. Requires OpenClawCLI installation from clawhub.ai. Do NOT use when Claude's built-in web_search tool is more appropriate for simple queries.

#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. Research, videos, images, audio, dashboards, presentations, spreadsheets, and more.

Deep ReSearch Conversation is provided by Baidu for multi-round streaming conversations with "Deep Research" agents. "In-depth research" is a long-process task involving multi-step reasoning and execution, which is different from the ordinary "question-and-answer". A dialogue that requires the user to repeatedly verify and correct it until a satisfactory answer is reached.

Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. Supports standard and distilled models with word-level timestamps.

Seedance 2.0 专业分镜提示词生成 + 视频生成一体化工具。当用户想要创作分镜视频、使用 Seedance/即梦生成视频、需要专业分镜提示词并直接生成视频时调用。支持多图参考、分镜引导、API 调用生成视频、自动下载。

Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.