OpenClaw AI 技能

Turn images, video, audio, or documents into text. Use when the user says "what's in this image", "describe / caption this", "tag these photos", "read

Make a creator-style or UGC ad video: a direct-to-camera testimonial, a product demo, an unboxing, or a faceless voiceover cut. Use when the user says

Fine-tune a reusable brand, style, or character model (a LoRA) from a small set of reference images, then generate on-brand imagery from any prompt. U

Generate images where the copy has to be exactly right: posters, packaging, ads, social graphics, UI mockups, menus, signage, infographics. Use when t

Build and manually refresh a metadata-only local Markdown or Obsidian index with an offline HTML dashboard.

Make a person, portrait, or avatar talk on camera. Use when the user says "make this photo talk", "talking head video", "lip-sync this to my audio", "

How to actually call the Runware API correctly for any task - inspect the model's schema, send the right fields, run synchronously for images or async

Write effective prompts for Runware's image and video models. Use whenever an agent is composing a prompt and wants model-appropriate phrasing, in-ima

Pick the right Runware model for a task and keep that choice current. Use when an agent needs to decide "which model for X", discover what's available

Improve image quality and resolution. Use when the user says "upscale this", "make it sharper / higher-res", "deblur", "denoise", "dehaze", "restore t

Swap one on-camera element in an existing video while everything else stays put. Use when the user says "recast this character", "put a different acto

Convert a video to a new aspect ratio without cropping the subject. Use when the user says "make this 16:9 clip vertical for Reels", "reframe to 9:16"

Turn a plain product shot or packshot into clean studio, lifestyle, or hero imagery for e-commerce and ads. Use when the user says "make this a produc

Turn a product image into a short ad or promo video, the highest-polish commercial outcome: a hero product still in motion. Use when the user says "ma

Generate images that read as real photographs, not AI renders: candid portraits, editorial, documentary, food, architectural, lifestyle. Use when the

Generate music from a text description - full songs with vocals and lyrics, instrumental beds, jingles, intros, and background tracks. Use when the us

Tell a short story across several cuts in one video call, not one continuous take. Use when the user says "a reel that cuts between shots", "a few bea

Make true scalable vector art (logos, icons, app glyphs, scalable illustrations) or convert a raster image into clean editable SVG. Use when the user

Build a chat, reasoning, or tool-calling agent on top of Runware-hosted LLMs. Use when the user says "make an agent that can call my functions", "let

Monitor Hang Seng Indexes (hsi.com.hk) press releases, index/other notices, insights, and reports; detect newly published items, match them bilinguall