[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BNVR16ZADW6FSDDGX3T4FV":3,"skill-same:01M7BNVR16ZADW6FSDDGX3T4FV":57},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":13,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7BNVR16ZADW6FSDDGX3T4FV","minimax-music-gen",null,"YYC-Cube\u002FYYC3-AI-Agent-Archive","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79K9J2WD44BBY4662XKNZRB",2,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fmarketplace\u002Fclaude-code-skills\u002Fskills\u002Fminimax-music-gen\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: minimax-music-gen\ndescription: >\ncategory: development-code\nversion: 1.0.0\n  Use when user wants to generate music, songs, or audio tracks. Triggers on any request\n  involving music creation, song writing, lyrics generation, audio production, or covers.\n  Also triggers when user provides lyrics and wants them turned into a song, or describes\n  a mood\u002Fscene and wants background music. Supports multilingual triggers — match equivalent\n  phrases in any language. Do NOT use for music playback of existing files, music theory\n  questions, or music recommendation without generation.\nlicense: MIT\nmetadata:\n  version: \"1.1\"\n  category: creative\n---\n\n# MiniMax Music Generation Skill\n\nGenerate songs (vocal or instrumental) using the MiniMax Music API. Supports two creation\nmodes: **Basic** (one-sentence-in, song-out) and **Advanced Control** (edit lyrics, refine\nprompt, plan before generating).\n\n## Prerequisites\n\n- **mmx CLI** (required): Music generation uses the `mmx` command-line tool.\n\n  **Check if installed:**\n  ```bash\n  command -v mmx && mmx --version || echo \"mmx not found\"\n  ```\n\n  **Install (requires Node.js):**\n  ```bash\n  npm install -g mmx-cli\n  ```\n\n  **Authenticate (first time only):**\n  ```bash\n  mmx auth login --api-key \u003Cyour-minimax-api-key>\n  ```\n  The API key can be obtained from [MiniMax Platform](https:\u002F\u002Fplatform.minimaxi.com\u002F).\n  Credentials are saved to `~\u002F.mmx\u002Fcredentials.json` and persist across sessions.\n\n  **Verify:**\n  ```bash\n  mmx quota show\n  ```\n\n- **Audio player** (recommended): `mpv`, `ffplay`, or `afplay` (macOS built-in) for local\n  playback. `mpv` is preferred for its interactive controls.\n\n## CLI Tool\n\nThis skill uses the `mmx` CLI for all music generation:\n\n- **Music Generation**: `mmx music generate` — model: `music-2.6-free`\n  - Supports `--lyrics-optimizer` to auto-generate lyrics from prompt\n  - Supports `--instrumental` for instrumental tracks\n  - Supports `--lyrics` for user-provided lyrics\n  - Structured params: `--genre`, `--mood`, `--vocals`, `--instruments`, `--bpm`, `--key`, `--tempo`, `--structure`, `--references`\n  \n- **Cover**: `mmx music cover` — model: `music-cover-free`\n  - Takes reference audio via `--audio-file \u003Cpath>` or `--audio \u003Curl>`\n  - `--prompt` describes the target cover style\n\n**Agent flags**: Always add `--quiet --non-interactive` when calling mmx from agents.\n\n**Pipeline**:\n- Vocal: `User description -> mmx music generate --lyrics-optimizer -> MP3`\n- Instrumental: `User description -> mmx music generate --instrumental -> MP3`\n- Cover: `Source audio + style -> mmx music cover -> MP3`\n\n## Storage\n\nAll generated music is saved to `~\u002FMusic\u002Fminimax-gen\u002F`. Create the directory if it doesn't\nexist. Files are named with a timestamp and a short slug derived from the prompt:\n`YYYYMMDD_HHMMSS_\u003Cslug>.mp3`\n\n---\n\n## Language & Interaction\n\nDetect the user's language from their first message and respond in that language for the\nentire session. This applies to all interaction text, questions, confirmations, and feedback\nprompts.\n\n**User-facing text localization rule**:\n- ALL text shown to the user — including preview labels, field names, confirmations, status\n  messages, playback info, feedback prompts, **and the prompt\u002Fdescription preview** — MUST\n  be fully translated into the user's language.\n- The **API prompt** sent to the model should always be written in English for best\n  generation quality. However, when previewing the prompt to the user, show a localized\n  description in the user's language instead of the raw English prompt. The English prompt\n  is an internal implementation detail — the user does not need to see it.\n- The templates below are written in English as reference. At runtime, translate every label\n  and message into the user's detected language.\n\n**Lyrics language rule**:\n- Default lyrics language = the user's language. A Chinese-speaking user gets Chinese lyrics;\n  an English-speaking user gets English lyrics.\n- Only generate lyrics in a different language if the user **explicitly** requests it.\n- When a different lyrics language is needed, embed it naturally into the vocal or genre\n  description in the prompt. For example, instead of appending \"with Korean lyrics\", use\n  \"featuring a Korean female vocalist\" or specify a genre that implies the language (e.g.,\n  \"K-pop\", \"J-rock\", \"Mandopop\", \"Latin pop\").\n\n---\n\n## Workflow\n\n### Step 0: Detect Intent\n\nParse the user's message to determine:\n\n1. **Song category**: vocal (with lyrics), instrumental (no vocals), or cover\n2. **Creation mode preference**: did they provide detailed requirements (Advanced) or a\n   casual one-liner (Basic)?\n\nIf ambiguous, ask using this decision tree:\n\n```\nQ1: What type of music?\n  - Vocal (with lyrics)\n  - Instrumental (no vocals)\n  - Cover\n\nQ2: Creation mode?\n  - Basic — one-line description, auto-generate\n  - Advanced — edit lyrics, refine prompt, plan\n```\n\nIf the user gives a clear one-liner like \"make me a sad piano piece\", skip the questions —\ninfer instrumental + basic mode and proceed.\n\n---\n\n### Step 1: Basic Mode\n\n**Goal**: User provides a short description, the skill auto-generates everything, then calls\nthe API.\n\n1. **Expand the description into a prompt**: Take the user's one-liner and expand it into a\n   rich music prompt. Refer to the **Prompt Writing Guide** appendix at the end of this\n   document for style vocabulary, genre\u002Finstrument references, and prompt structure.\n   **The API prompt should always be written in English** for best generation quality,\n   regardless of the user's language.\n   \n   Follow this pattern:\n   ```\n   A [mood] [BPM optional] [genre] song, featuring [vocal description],\n   about [narrative\u002Ftheme], [atmosphere], [key instruments and production].\n   ```\n\n2. **Show the user a preview** before generating. Translate all labels AND the prompt\n   description into the user's language. The English prompt is only used internally when\n   calling the API — the user should never see it. Example template (English reference —\n   localize everything at runtime):\n\n   ```\n   About to generate:\n   Type: Vocal \u002F Instrumental\n   Description: indie folk, melancholy, acoustic guitar, gentle female voice\n   Lyrics: Auto-generated (--lyrics-optimizer)\n   \n   Confirm? (press enter to confirm, or tell me what to change)\n   ```\n\n3. **Call mmx**: Generate the music directly.\n\n---\n\n### Step 2: Advanced Control Mode\n\n**Goal**: User has full control over every parameter before generation.\n\n1. **Lyrics phase**:\n   - If user provided lyrics: display them formatted with section markers, ask for edits.\n     The final lyrics will be passed via `--lyrics` to mmx.\n   - If user has a theme but no lyrics: will use `--lyrics-optimizer` to auto-generate.\n   - Support iterative editing: \"change the second chorus\" -> only rewrite that section.\n   - User can also write lyrics themselves and pass via `--lyrics`.\n\n2. **Prompt phase**:\n   - Generate a recommended prompt based on the lyrics' mood and content.\n   - Present it as editable tags the user can add\u002Fremove\u002Fmodify.\n   - Refer to the **Prompt Writing Guide** appendix for the full vocabulary.\n\n3. **Advanced planning** (optional, offer but don't force):\n   - Song structure: verse-chorus-verse-chorus-bridge-chorus or custom\n   - BPM suggestion (encode in prompt as tempo descriptor)\n   - Reference style: \"something like X style\" -> map to prompt tags\n   - Vocal character description\n\n4. **Final confirmation**: Show complete parameter summary, then generate.\n\n---\n\n### Step 3: Call mmx\n\nGenerate music using the mmx CLI:\n\n**Vocal with auto-generated lyrics:**\n```bash\nmmx music generate \\\n  --prompt \"\u003Cprompt>\" \\\n  --lyrics-optimizer \\\n  --genre \"\u003Cgenre>\" --mood \"\u003Cmood>\" --vocals \"\u003Cvocal style>\" \\\n  --instruments \"\u003Cinstruments>\" --bpm \u003Cbpm> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**Vocal with user-provided lyrics:**\n```bash\nmmx music generate \\\n  --prompt \"\u003Cprompt>\" \\\n  --lyrics \"\u003Clyrics with section markers>\" \\\n  --genre \"\u003Cgenre>\" --mood \"\u003Cmood>\" --vocals \"\u003Cvocal style>\" \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**Instrumental (no vocal):**\n```bash\nmmx music generate \\\n  --prompt \"\u003Cprompt>\" \\\n  --instrumental \\\n  --genre \"\u003Cgenre>\" --mood \"\u003Cmood>\" --instruments \"\u003Cinstruments>\" \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\nUse structured flags (`--genre`, `--mood`, `--vocals`, `--instruments`, `--bpm`, `--key`,\n`--tempo`, `--structure`, `--references`, `--avoid`, `--use-case`) to give the API\nfine-grained control instead of cramming everything into `--prompt`.\n\nDisplay a progress indicator while waiting. Typical generation takes 30-120 seconds.\n\n---\n\n### Step 4: Playback\n\nAfter generation, detect an available audio player and play the file.\n\n**Detect player:**\n```bash\ncommand -v mpv || command -v ffplay || command -v afplay\n```\n\n**Play based on detected player (in priority order):**\n\n| Player | Command | Controls |\n|--------|---------|----------|\n| `mpv` (preferred) | `mpv --no-video ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3` | space = pause\u002Fresume, q = quit, left\u002Fright = seek |\n| `ffplay` | `ffplay -nodisp -autoexit ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3` | q = quit |\n| `afplay` (macOS) | `afplay ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3` | Ctrl+C = stop |\n| None found | Do not attempt playback | Show file path only |\n\nAfter starting playback, tell the user (localize all text):\n\n```\nNow playing: \u003Cfilename>.mp3\nSaved to: ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\n```\n\nDo NOT show playback controls (e.g. keyboard shortcuts) — they don't work in this\nenvironment since the player runs in the background.\n\nIf no player is found (localize all text):\n\n```\nNo audio player detected.\nFile saved to: ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nTip: Install mpv for the best playback experience (brew install mpv).\n```\n\n---\n\n### Step 5: Feedback & Iteration\n\nAfter playback, ask for feedback:\n\n```\nHow was this song?\n  1. Love it, keep it!\n  2. Not quite, adjust and regenerate\n  3. Fine-tune lyrics\u002Fstyle then regenerate\n  4. Don't want it, start over\n```\n\nBased on feedback:\n- **Satisfied**: Done. Mention the file path again.\n- **Adjust & regenerate**: Ask what to change (prompt? lyrics? style?), apply edits,\n  re-run generation. Keep the old file with a `_v1` suffix for comparison.\n- **Fine-tune**: Enter Advanced Control Mode with the current parameters pre-filled.\n- **Delete & restart**: Remove the file, go back to Step 0.\n\n---\n\n## Cover Mode\n\nGenerate a cover version of a song based on reference audio. Model: `music-cover-free`.\n\n**Reference audio requirements**: mp3, wav, flac — duration 6s to 6min, max 50MB.\nIf no lyrics are provided, the original lyrics are extracted via ASR automatically.\n\n### Workflow\n\nWhen the user selects Cover mode:\n1. Ask for the source audio — a local file path or URL\n2. Ask for the target cover style (e.g., \"acoustic cover, stripped-down, intimate vocal\")\n3. Optionally ask for custom lyrics or lyrics file\n\n### Commands\n\n**Cover from local file:**\n```bash\nmmx music cover \\\n  --prompt \"\u003Ccover style description>\" \\\n  --audio-file \u003Csource.mp3> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**Cover from URL:**\n```bash\nmmx music cover \\\n  --prompt \"\u003Ccover style description>\" \\\n  --audio \u003Csource_url> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**With custom lyrics (text):**\n```bash\nmmx music cover \\\n  --prompt \"\u003Cstyle>\" \\\n  --audio-file \u003Csource.mp3> \\\n  --lyrics \"\u003Ccustom lyrics>\" \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**With custom lyrics (file):**\n```bash\nmmx music cover \\\n  --prompt \"\u003Cstyle>\" \\\n  --audio-file \u003Csource.mp3> \\\n  --lyrics-file \u003Clyrics.txt> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n### Optional flags\n\n| Flag | Description |\n|------|-------------|\n| `--seed \u003Cnumber>` | Random seed 0-1000000 for reproducible results |\n| `--channel \u003Cn>` | `1` (mono) or `2` (stereo, default) |\n| `--format \u003Cfmt>` | `mp3` (default), `wav`, `pcm` |\n| `--sample-rate \u003Chz>` | Sample rate (default: 44100) |\n| `--bitrate \u003Cbps>` | Bitrate (default: 256000) |\n\n### After generation\nProceed with normal playback and feedback flow (Step 4 & 5).\n\n---\n\n## Error Handling\n\n| Error | Action |\n|-------|--------|\n| mmx not found | `npm install -g mmx-cli` |\n| mmx auth error (exit code 3) | `mmx auth login` |\n| Quota exceeded (exit code 4) | Report quota limit, suggest waiting or upgrading |\n| API timeout (exit code 5) | Retry once, then report failure |\n| Content filter (exit code 10) | Adjust prompt to avoid filtered content |\n| Invalid lyrics format | Auto-fix section markers, warn user |\n| No audio player found | Save file and tell user the path, suggest installing mpv |\n| Network error | Show error detail, suggest checking connection |\n\n---\n\n## Important Notes\n\n- **Never reproduce copyrighted lyrics.** When doing covers, always write original lyrics\n  inspired by the song's theme. Explain this to the user.\n- **Prompt language**: The API prompt works best with English tags. Chinese tags are also\n  acceptable. Mixing is OK.\n- **Section markers in lyrics**: The API recognizes `[verse]`, `[chorus]`, `[bridge]`,\n  `[outro]`, `[intro]`. Always include them when providing `--lyrics`.\n- **File management**: If `~\u002FMusic\u002Fminimax-gen\u002F` has more than 50 files, suggest cleanup\n  when starting a new session.\n- **Structured params**: Prefer using `--genre`, `--mood`, `--vocals`, `--instruments`,\n  `--bpm` etc. over embedding everything in `--prompt`. This gives the API better control.\n- **Lyrics language via style**: When the user wants lyrics in a specific language, express\n  it through the vocal description or genre (e.g., \"Japanese female vocalist\", \"Mandopop\n  ballad\") rather than appending a language directive to the prompt.\n\n---\n\n## Appendix: Prompt Writing Guide\n\nSee [references\u002Fprompt_guide.md](references\u002Fprompt_guide.md) for the complete prompt writing guide,\nincluding genre\u002Fvocal\u002Finstrument references and BPM tables.\n","# MiniMax Music Generation Skill\n\nGenerate songs (vocal or instrumental) using the MiniMax Music API. Supports two creation\nmodes: **Basic** (one-sentence-in, song-out) and **Advanced Control** (edit lyrics, refine\nprompt, plan before generating).\n\n## Prerequisites\n\n- **mmx CLI** (required): Music generation uses the `mmx` command-line tool.\n\n  **Check if installed:**\n  ```bash\n  command -v mmx && mmx --version || echo \"mmx not found\"\n  ```\n\n  **Install (requires Node.js):**\n  ```bash\n  npm install -g mmx-cli\n  ```\n\n  **Authenticate (first time only):**\n  ```bash\n  mmx auth login --api-key \u003Cyour-minimax-api-key>\n  ```\n  The API key can be obtained from [MiniMax Platform](https:\u002F\u002Fplatform.minimaxi.com\u002F).\n  Credentials are saved to `~\u002F.mmx\u002Fcredentials.json` and persist across sessions.\n\n  **Verify:**\n  ```bash\n  mmx quota show\n  ```\n\n- **Audio player** (recommended): `mpv`, `ffplay`, or `afplay` (macOS built-in) for local\n  playback. `mpv` is preferred for its interactive controls.\n\n## CLI Tool\n\nThis skill uses the `mmx` CLI for all music generation:\n\n- **Music Generation**: `mmx music generate` — model: `music-2.6-free`\n  - Supports `--lyrics-optimizer` to auto-generate lyrics from prompt\n  - Supports `--instrumental` for instrumental tracks\n  - Supports `--lyrics` for user-provided lyrics\n  - Structured params: `--genre`, `--mood`, `--vocals`, `--instruments`, `--bpm`, `--key`, `--tempo`, `--structure`, `--references`\n  \n- **Cover**: `mmx music cover` — model: `music-cover-free`\n  - Takes reference audio via `--audio-file \u003Cpath>` or `--audio \u003Curl>`\n  - `--prompt` describes the target cover style\n\n**Agent flags**: Always add `--quiet --non-interactive` when calling mmx from agents.\n\n**Pipeline**:\n- Vocal: `User description -> mmx music generate --lyrics-optimizer -> MP3`\n- Instrumental: `User description -> mmx music generate --instrumental -> MP3`\n- Cover: `Source audio + style -> mmx music cover -> MP3`\n\n## Storage\n\nAll generated music is saved to `~\u002FMusic\u002Fminimax-gen\u002F`. Create the directory if it doesn't\nexist. Files are named with a timestamp and a short slug derived from the prompt:\n`YYYYMMDD_HHMMSS_\u003Cslug>.mp3`\n\n---\n\n## Language & Interaction\n\nDetect the user's language from their first message and respond in that language for the\nentire session. This applies to all interaction text, questions, confirmations, and feedback\nprompts.\n\n**User-facing text localization rule**:\n- ALL text shown to the user — including preview labels, field names, confirmations, status\n  messages, playback info, feedback prompts, **and the prompt\u002Fdescription preview** — MUST\n  be fully translated into the user's language.\n- The **API prompt** sent to the model should always be written in English for best\n  generation quality. However, when previewing the prompt to the user, show a localized\n  description in the user's language instead of the raw English prompt. The English prompt\n  is an internal implementation detail — the user does not need to see it.\n- The templates below are written in English as reference. At runtime, translate every label\n  and message into the user's detected language.\n\n**Lyrics language rule**:\n- Default lyrics language = the user's language. A Chinese-speaking user gets Chinese lyrics;\n  an English-speaking user gets English lyrics.\n- Only generate lyrics in a different language if the user **explicitly** requests it.\n- When a different lyrics language is needed, embed it naturally into the vocal or genre\n  description in the prompt. For example, instead of appending \"with Korean lyrics\", use\n  \"featuring a Korean female vocalist\" or specify a genre that implies the language (e.g.,\n  \"K-pop\", \"J-rock\", \"Mandopop\", \"Latin pop\").\n\n---\n\n## Workflow\n\n### Step 0: Detect Intent\n\nParse the user's message to determine:\n\n1. **Song category**: vocal (with lyrics), instrumental (no vocals), or cover\n2. **Creation mode preference**: did they provide detailed requirements (Advanced) or a\n   casual one-liner (Basic)?\n\nIf ambiguous, ask using this decision tree:\n\n```\nQ1: What type of music?\n  - Vocal (with lyrics)\n  - Instrumental (no vocals)\n  - Cover\n\nQ2: Creation mode?\n  - Basic — one-line description, auto-generate\n  - Advanced — edit lyrics, refine prompt, plan\n```\n\nIf the user gives a clear one-liner like \"make me a sad piano piece\", skip the questions —\ninfer instrumental + basic mode and proceed.\n\n---\n\n### Step 1: Basic Mode\n\n**Goal**: User provides a short description, the skill auto-generates everything, then calls\nthe API.\n\n1. **Expand the description into a prompt**: Take the user's one-liner and expand it into a\n   rich music prompt. Refer to the **Prompt Writing Guide** appendix at the end of this\n   document for style vocabulary, genre\u002Finstrument references, and prompt structure.\n   **The API prompt should always be written in English** for best generation quality,\n   regardless of the user's language.\n   \n   Follow this pattern:\n   ```\n   A [mood] [BPM optional] [genre] song, featuring [vocal description],\n   about [narrative\u002Ftheme], [atmosphere], [key instruments and production].\n   ```\n\n2. **Show the user a preview** before generating. Translate all labels AND the prompt\n   description into the user's language. The English prompt is only used internally when\n   calling the API — the user should never see it. Example template (English reference —\n   localize everything at runtime):\n\n   ```\n   About to generate:\n   Type: Vocal \u002F Instrumental\n   Description: indie folk, melancholy, acoustic guitar, gentle female voice\n   Lyrics: Auto-generated (--lyrics-optimizer)\n   \n   Confirm? (press enter to confirm, or tell me what to change)\n   ```\n\n3. **Call mmx**: Generate the music directly.\n\n---\n\n### Step 2: Advanced Control Mode\n\n**Goal**: User has full control over every parameter before generation.\n\n1. **Lyrics phase**:\n   - If user provided lyrics: display them formatted with section markers, ask for edits.\n     The final lyrics will be passed via `--lyrics` to mmx.\n   - If user has a theme but no lyrics: will use `--lyrics-optimizer` to auto-generate.\n   - Support iterative editing: \"change the second chorus\" -> only rewrite that section.\n   - User can also write lyrics themselves and pass via `--lyrics`.\n\n2. **Prompt phase**:\n   - Generate a recommended prompt based on the lyrics' mood and content.\n   - Present it as editable tags the user can add\u002Fremove\u002Fmodify.\n   - Refer to the **Prompt Writing Guide** appendix for the full vocabulary.\n\n3. **Advanced planning** (optional, offer but don't force):\n   - Song structure: verse-chorus-verse-chorus-bridge-chorus or custom\n   - BPM suggestion (encode in prompt as tempo descriptor)\n   - Reference style: \"something like X style\" -> map to prompt tags\n   - Vocal character description\n\n4. **Final confirmation**: Show complete parameter summary, then generate.\n\n---\n\n### Step 3: Call mmx\n\nGenerate music using the mmx CLI:\n\n**Vocal with auto-generated lyrics:**\n```bash\nmmx music generate \\\n  --prompt \"\u003Cprompt>\" \\\n  --lyrics-optimizer \\\n  --genre \"\u003Cgenre>\" --mood \"\u003Cmood>\" --vocals \"\u003Cvocal style>\" \\\n  --instruments \"\u003Cinstruments>\" --bpm \u003Cbpm> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**Vocal with user-provided lyrics:**\n```bash\nmmx music generate \\\n  --prompt \"\u003Cprompt>\" \\\n  --lyrics \"\u003Clyrics with section markers>\" \\\n  --genre \"\u003Cgenre>\" --mood \"\u003Cmood>\" --vocals \"\u003Cvocal style>\" \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**Instrumental (no vocal):**\n```bash\nmmx music generate \\\n  --prompt \"\u003Cprompt>\" \\\n  --instrumental \\\n  --genre \"\u003Cgenre>\" --mood \"\u003Cmood>\" --instruments \"\u003Cinstruments>\" \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\nUse structured flags (`--genre`, `--mood`, `--vocals`, `--instruments`, `--bpm`, `--key`,\n`--tempo`, `--structure`, `--references`, `--avoid`, `--use-case`) to give the API\nfine-grained control instead of cramming everything into `--prompt`.\n\nDisplay a progress indicator while waiting. Typical generation takes 30-120 seconds.\n\n---\n\n### Step 4: Playback\n\nAfter generation, detect an available audio player and play the file.\n\n**Detect player:**\n```bash\ncommand -v mpv || command -v ffplay || command -v afplay\n```\n\n**Play based on detected player (in priority order):**\n\n| Player | Command | Controls |\n|--------|---------|----------|\n| `mpv` (preferred) | `mpv --no-video ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3` | space = pause\u002Fresume, q = quit, left\u002Fright = seek |\n| `ffplay` | `ffplay -nodisp -autoexit ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3` | q = quit |\n| `afplay` (macOS) | `afplay ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3` | Ctrl+C = stop |\n| None found | Do not attempt playback | Show file path only |\n\nAfter starting playback, tell the user (localize all text):\n\n```\nNow playing: \u003Cfilename>.mp3\nSaved to: ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\n```\n\nDo NOT show playback controls (e.g. keyboard shortcuts) — they don't work in this\nenvironment since the player runs in the background.\n\nIf no player is found (localize all text):\n\n```\nNo audio player detected.\nFile saved to: ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3\nTip: Install mpv for the best playback experience (brew install mpv).\n```\n\n---\n\n### Step 5: Feedback & Iteration\n\nAfter playback, ask for feedback:\n\n```\nHow was this song?\n  1. Love it, keep it!\n  2. Not quite, adjust and regenerate\n  3. Fine-tune lyrics\u002Fstyle then regenerate\n  4. Don't want it, start over\n```\n\nBased on feedback:\n- **Satisfied**: Done. Mention the file path again.\n- **Adjust & regenerate**: Ask what to change (prompt? lyrics? style?), apply edits,\n  re-run generation. Keep the old file with a `_v1` suffix for comparison.\n- **Fine-tune**: Enter Advanced Control Mode with the current parameters pre-filled.\n- **Delete & restart**: Remove the file, go back to Step 0.\n\n---\n\n## Cover Mode\n\nGenerate a cover version of a song based on reference audio. Model: `music-cover-free`.\n\n**Reference audio requirements**: mp3, wav, flac — duration 6s to 6min, max 50MB.\nIf no lyrics are provided, the original lyrics are extracted via ASR automatically.\n\n### Workflow\n\nWhen the user selects Cover mode:\n1. Ask for the source audio — a local file path or URL\n2. Ask for the target cover style (e.g., \"acoustic cover, stripped-down, intimate vocal\")\n3. Optionally ask for custom lyrics or lyrics file\n\n### Commands\n\n**Cover from local file:**\n```bash\nmmx music cover \\\n  --prompt \"\u003Ccover style description>\" \\\n  --audio-file \u003Csource.mp3> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**Cover from URL:**\n```bash\nmmx music cover \\\n  --prompt \"\u003Ccover style description>\" \\\n  --audio \u003Csource_url> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**With custom lyrics (text):**\n```bash\nmmx music cover \\\n  --prompt \"\u003Cstyle>\" \\\n  --audio-file \u003Csource.mp3> \\\n  --lyrics \"\u003Ccustom lyrics>\" \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n**With custom lyrics (file):**\n```bash\nmmx music cover \\\n  --prompt \"\u003Cstyle>\" \\\n  --audio-file \u003Csource.mp3> \\\n  --lyrics-file \u003Clyrics.txt> \\\n  --out ~\u002FMusic\u002Fminimax-gen\u002F\u003Cfilename>.mp3 \\\n  --quiet --non-interactive\n```\n\n### Optional flags\n\n| Flag | Description |\n|------|-------------|\n| `--seed \u003Cnumber>` | Random seed 0-1000000 for reproducible results |\n| `--channel \u003Cn>` | `1` (mono) or `2` (stereo, default) |\n| `--format \u003Cfmt>` | `mp3` (default), `wav`, `pcm` |\n| `--sample-rate \u003Chz>` | Sample rate (default: 44100) |\n| `--bitrate \u003Cbps>` | Bitrate (default: 256000) |\n\n### After generation\nProceed with normal playback and feedback flow (Step 4 & 5).\n\n---\n\n## Error Handling\n\n| Error | Action |\n|-------|--------|\n| mmx not found | `npm install -g mmx-cli` |\n| mmx auth error (exit code 3) | `mmx auth login` |\n| Quota exceeded (exit code 4) | Report quota limit, suggest waiting or upgrading |\n| API timeout (exit code 5) | Retry once, then report failure |\n| Content filter (exit code 10) | Adjust prompt to avoid filtered content |\n| Invalid lyrics format | Auto-fix section markers, warn user |\n| No audio player found | Save file and tell user the path, suggest installing mpv |\n| Network error | Show error detail, suggest checking connection |\n\n---\n\n## Important Notes\n\n- **Never reproduce copyrighted lyrics.** When doing covers, always write original lyrics\n  inspired by the song's theme. Explain this to the user.\n- **Prompt language**: The API prompt works best with English tags. Chinese tags are also\n  acceptable. Mixing is OK.\n- **Section markers in lyrics**: The API recognizes `[verse]`, `[chorus]`, `[bridge]`,\n  `[outro]`, `[intro]`. Always include them when providing `--lyrics`.\n- **File management**: If `~\u002FMusic\u002Fminimax-gen\u002F` has more than 50 files, suggest cleanup\n  when starting a new session.\n- **Structured params**: Prefer using `--genre`, `--mood`, `--vocals`, `--instruments`,\n  `--bpm` etc. over embedding everything in `--prompt`. This gives the API better control.\n- **Lyrics language via style**: When the user wants lyrics in a specific language, express\n  it through the vocal description or genre (e.g., \"Japanese female vocalist\", \"Mandopop\n  ballad\") rather than appending a language directive to the prompt.\n\n---\n\n## Appendix: Prompt Writing Guide\n\nSee [references\u002Fprompt_guide.md](references\u002Fprompt_guide.md) for the complete prompt writing guide,\nincluding genre\u002Fvocal\u002Finstrument references and BPM tables.\n",{"name":5,"license":14,"version":23,"category":24,"metadata":25,"description":28},"1.0.0 Use when user wants to generate music, songs, or audio tracks. Triggers on any request involving music creation, song writing, lyrics generation, audio production, or covers. Also triggers when user provides lyrics and wants them turned into a song, or describes a mood\u002Fscene and wants background music. Supports multilingual triggers — match equivalent phrases in any language. Do NOT use for music playback of existing files, music theory questions, or music recommendation without generation.","development-code",{"version":26,"category":27},"1.1","creative","","main","d591030ef9fb1bbcebed3454aa5c2dcb8d608f69","skills-hub\u002Fmarketplace\u002Fclaude-code-skills\u002Fskills\u002Fminimax-music-gen","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive","https:\u002F\u002Fai-agent.yyc3.vip\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-13 22:26:14",{"source":7,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill minimax-music-gen",{"tool":43,"command":44},"bunx","bunx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill minimax-music-gen",{"tool":46,"command":47},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-AI-Agent-Archive --skill minimax-music-gen","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fmarketplace\u002Fclaude-code-skills\u002Fskills\u002Fminimax-music-gen\u002FSKILL.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fprompt_guide.md","REFERENCE","参考文档",5712,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Fskills-hub\u002Fmarketplace\u002Fclaude-code-skills\u002Fskills\u002Fminimax-music-gen\u002Freferences\u002Fprompt_guide.md",[58,65,72,79,86,95],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7BTB92RE8MT5YE706QBNDTQ","yingmi-skill","当用户需要查询基金、策略、公告、财经资讯，做资产配置、组合诊断、风险回测、现金流分析，或生成图表、PDF 时，优先使用本 Skill 获取真实数据与可执行能力。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fyingmi-skill\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M7BT7ZYR091HPJYEFNWVTEJJ","web-access","所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fweb-access\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7BT4NKS0DNP8A53M1BGGZR2","tencentmap-map-assistant","腾讯位置服务·地图助手 Skill，一句自然语言调用腾讯地图全套能力，无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索（含评分\u002F人均\u002F营业时间）、关键词提示、路线规划（驾车\u002F步行\u002F公交\u002F骑行）、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询，并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Ftencentmap-map-assistant\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7BSWKV1T5XYYRGV4W4JP88C","skill-scanner","Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-scanner\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":90,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7BSWGTCFW7F123S4BM4XY6W","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M7BSVV4DH8JK2ZMQSCW25VCD","shader-dev","Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-AI-Agent-Archive\u002Fblob\u002Fmain\u002Ftools-hub\u002Fcode-ide\u002Fskills-marketplace\u002Fskills\u002Fshader-dev\u002FSKILL.md",[],[]]