Stats
Actions
Tags
From recoup-songs
Transcribe a song's lyrics from its audio into a sectioned lyric sheet using Recoup's audio language model (Music Flamingo). Use when asked to "transcribe the lyrics", "get the lyrics from this song", "make a lyric sheet", "write out the words", "find explicit lines", or "make a clean/radio lyric reference". Needs a public audio URL. Output is a draft for human review.
How this skill is triggered — by the user, by Claude, or both
Slash command
/recoup-songs:recoup-song-lyricsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn a song's audio into a draft lyric sheet with section headers
Turn a song's audio into a draft lyric sheet with section headers
([Verse], [Chorus], [Bridge], …).
The endpoint contract (auth, base URL, request/response, presets, call patterns,
gotchas) is in references/flamingo-api.md. Read it before calling.
For full catalog metadata, use recoup-song-metadata.
lyric_transcriptioncontent_advisory when the user asks about explicit content,
brand safety, clean edits, or radio readinesssong_description or a custom prompt for lyrical themes / hook /
story interpretationaudio_url (no local file upload).lyric_transcription. Add content_advisory if the user cares about
explicit/brand-safety/radio.lyrics.md.lyrics.md — lyrics with [Verse] / [Chorus] / [Bridge] headers.lyrics-review.md (optional) — uncertain lines, explicit terms, manual
verification notes.content_advisory.json (optional) — profanity / theme / radio-friendliness
fields.If inside an artist workspace, save under songs/{song-slug}/lyrics/.
[inaudible] or
[unclear: …]. Do not invent lines to make the sheet feel complete.account_id in the body.references/flamingo-api.md — auth, base URL, request/response, preset table,
call patterns, gotchas.npx claudepluginhub recoupable/skills --plugin recoup-skillsSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.