fish-audio
Generate expressive audio clips using Fish Audio S2 TTS with bracket emotion tags. Record voice memos, narration, audio messages, or any spoken content.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Generate expressive audio clips using Fish Audio S2 TTS with bracket emotion tags. Record voice memos, narration, audio messages, or any spoken content.
Create images from a text description, or edit photos and graphics the user provides (remove backgrounds or watermarks, retouch, restyle, in-paint). Can produce multiple variants when the user wants options to choose from.
Ingest and process media files (video, audio, image)
Generate memes from 170+ classic templates using the free Memegen.link API. Search templates, generate captioned images, and download them for posting. No API key required.
Refresh fact-based sections of crates/AGENTS.md (STRUCTURE, WHERE TO LOOK, COMPLEXITY HOTSPOTS, KNOWN BROKEN) from current codebase state. Use after refactoring, renaming files, adding crates, or when the agent notices AGENTS.md info is stale.
Use when asked to make a narrative video — an ad, brand film, short, trailer, music video, or any multi-shot clip that tells a story (not a single shot or loop). Also use when a video was rejected for "no story", "doesn't flow", "feels like a montage", or characters that change between shots.
How to present and interact during comfy creative work (images, video, audio) — show visual previews in chat, not text about files. Creative media work is iterative and visual; it is NOT like code. Use whenever generating, reviewing, or iterating on media with the comfy CLI.
Help users understand media capabilities including audio/video import, processing, transcription, and organization.
Check and fix formatting and other issues in markdown files using markdownlint-cli2.
Workflow for refactoring discipline-level guides (e.g., JavaScript, CSS) to remove "Common Knowledge" by generating and comparing against model-specific "Knowledge Mirrors".