AI Agent Skills

The English language layer for lyric writing (英文词的重音与节拍对齐). Word stress is fixed inside a polysyllabic word, so the melody bends to the word and never the reverse; stres…

The Japanese language layer for lyric writing (日文词的モーラ与符割り). The counting unit is the mora, not the kana or the syllable - the small tsu, the moraic n and the long vowel…

The Korean language layer for lyric writing (韩文词的音节与받침). One hangul block is one syllable is one note by default - unlike Japanese, a final consonant takes no beat of it…

The Mandarin language layer for lyric writing (普通话作词的语言层). What Chinese as a language adds to the job: tone is phonemic, so the melody that enters a syllable can change…

The gate you must pass before writing a single line (动笔前必填). Five questions that force an actual choice - which kind of song this is (attitudinal, situational, narrative…

Compiling a finished lyric into generation-backend input (词稿 → 后端). Section tags and how they map, why line breaks inside a section are read as phrase boundaries rather…

Entry point and router for the lyric writing library (作词工作流与路由). The two workflows that fork at the very first question - music-first versus lyrics-first - and their dif…

Songwriting guide for ACE-Step music generation. Helps craft captions (style descriptions), lyrics with structure tags, and choose optimal BPM/key/duration/time signatur…

Generates music from text descriptions and lyrics using ACE-Step 1.5's Python API. Creates full songs with vocals, instrumentals, or both. Supports 50+ languages, 10-600…

Run the Lofn music/audio pipeline (steps 00–11) backed by Codex — Suno-ready song packages with two-field style/exclude prompts, EMO-tagged lyrics, song guides. Use for…

For musicians, video creators, and social-media editors producing AI music videos or emotional short films with lyric typography. Users provide music, lyrics, references…