风格克隆 AI 写歌。用户给一首参考歌/歌手 + 新主题，全自动跑完音乐基因解构→歌词DNA提取→同构填词→Suno生成，最终直接返回试听链接。中间不停
Rewrite a song with a new theme while preserving the original's rhyme scheme, line structure, and rhythmic skeleton. Use when users want to parody a song, wr...
Generate original background music for short videos from a natural language description. Use when creators need royalty-free BGM, video background music, or...
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Combines Wikipedia's "Sig...
Call any API without leaking credentials. Keychains proxies requests and injects real tokens server-side — your agent never sees them.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp...
Generate high-quality music/songs via AIMLAPI. Supports Suno, Udio, Minimax, and ElevenLabs music models. Use when the user asks for music, songs, or soundtr...
Convert voice notes, humming, and melodic audio recordings to quantized MIDI files using ML-based pitch detection and intelligent post-processing
#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. R...
Process, enhance, and convert audio files with noise removal, normalization, format conversion, transcription, and podcast workflows.
Remove AI writing patterns based on Wikipedia's "Signs of AI writing" research. 24 pattern detection and rewriting rules for making AI-generated text sound n...
Generate talking videos from images using Talking Image API. Create talking videos from audio and images, supporting non-human faces like pets or animated ch...
Analyze a video's mood and add AI-generated BGM. Optionally speed up/slow down. Uses Gemini for video analysis and fal.ai Lyria2 for music generation. Trigge...
Call the RawUGC API to generate AI videos/images/music, manage content (personas, products, styles, characters), schedule social media posts, research TikTok...
Text-to-speech conversion using OpenAI's TTS API for generating high-quality, natural-sounding audio. Supports 6 voices (alloy, echo, fable, onyx, nova, shimmer), speed control (0.25x-4.0x), HD qualit
World-Class Communication Playbook for HeySalad. Use this skill whenever any communication task is involved — internal team messages, external emails to inve...