发现优质的 AI Agent 技能

Modify existing images based on professional prompts.

How to select and apply scoring frameworks in Phase 4. The principle: **one framework per round, applied consistently to all images.**

Generate images, videos, and transcripts using fal.ai's API with support for FLUX, Stable Diffusion, Whisper, and more.

In the era of infinite synthesis, a **Photo** is a proof of observation. This protocol defines the standard for embedding cryptographic provenance into visual data, bridging the gap between raw light capture and AI-generated imagery.

- This skill assumes Taskwarrior is installed in the runtime/base image. - The skill does **not** run system package installs at runtime.

Convert files to clean, structured Markdown using the [Markdown Anything](https://markdownanything.com) API. Supports PDF, DOCX, XLSX, PPTX, images, audio, and 25+ formats.

Use MacPilot to capture screenshots of the screen, specific regions, or application windows, and extract text from images or screen regions using Apple's built-in Vision OCR.

Generate images and videos from text prompts using the xAI API.

Full LinkedIn content management through Reepl's MCP integration. Write posts in your authentic voice, schedule content, manage drafts, generate AI images, create carousels, post to Twitter/X, browse your saved content library, and maintain contacts -- all from your AI assistant.

Generate images using Azure OpenAI's DALL-E deployment.

Rotate through these patterns to generate diverse, non-repetitive image prompts. Never use the same pattern twice in a row. Track the last pattern used in `data/prompt_history.json`.

Generate high-quality, diverse image prompts by feeding real visual references into a structured prompt pipeline.