发现优质的 AI Agent 技能

Packs are collections of background images used in slideshows.

> **TL;DR:** Wraps genviral's Partner API into 50+ bash commands. Core flow: `get-pack` → analyze images (metadata + vision) → `generate` with `pinned_images` → `render` → visual review (hard gate) → `create-post` → log to `workspace/performance/log.json`. Studio AI: `studio-models` → `studio-generate-image` (sync) or `studio-generate-video` → `studio-video-status --poll` (async). Auth via `GENVIRAL_API_KEY`. Config in `defaults.yaml`. Instance data in `workspace/`.

Generate AI images and videos through the Partner API. Same model catalog and credit rules as the Genviral web app.

Packs are collections of background images used in slideshows.

> **TL;DR:** Wraps genviral's Partner API into 50+ bash commands. Core flow: `get-pack` → analyze images (metadata + vision) → `generate` with `pinned_images` → `render` → visual review (hard gate) → `create-post` → log to `workspace/performance/log.json`. Studio AI: `studio-models` → `studio-generate-image` (sync) or `studio-generate-video` → `studio-video-status --poll` (async). Auth via `GENVIRAL_API_KEY`. Config in `defaults.yaml`. Instance data in `workspace/`.

Generate and edit images using NVIDIA's FLUX models.

Integrates with local ComfyUI instance at http://192.168.31.7:8000 to generate images from text (txt2img) and edit images using uploaded references (img2img). Uses the workflow: `~/clawd/skills/comfy-ai/image_flux2_klein_image_edit_4b_distilled.json`.

Use `next/image` for automatic image optimization.

Convert PDF, Word, PPT, and images to clean Markdown using MinerU's VLM engine — LaTeX formulas, tables, and images all preserved.

Mistral OCR returns each page's main content as Markdown. When you ask it to extract images and/or tables, the Markdown contains **placeholders** that reference those extracted artefacts.

来自 openclaw/skills 技能

End-to-end workflow from concept to final video: Storyboard → Reference images → Submit video task → Get results.