[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JC83M5TDAH11JRPDN2EEKX":3,"skill-same:01M6JC83M5TDAH11JRPDN2EEKX":88},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6JC83M5TDAH11JRPDN2EEKX","open-source-music-generation",null,"Open-source AI music generation tools — HeartMuLa (lyrics+tags) and AudioCraft\u002FMusicGen (text-to-music, text-to-sound). Covers installation, generation parameters, model variants, and pitfalls for both ecosystems.","S3YED\u002Fappie-kit","S3YED","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F62743867?v=4","01M6JBKBRRVP6KMS0VWZ27T3R6","01M6JBKBX0KG30284PW1DBYJT1",14,"MIT","https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fcontent\u002Fopen-source-music-generation\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"open source music generation","open","music","source","generation","open source","music generation","Text-to-Music","encodec","audiogen","for","pitfalls","audiocraft","MusicGen","ai music generation","ecosystems","model","text","Audio","Tools","2026-11-10 10:12:30",false,"---\nname: open-source-music-generation\ndescription: \"Open-source AI music generation tools — HeartMuLa (lyrics+tags) and AudioCraft\u002FMusicGen (text-to-music, text-to-sound). Covers installation, generation parameters, model variants, and pitfalls for both ecosystems.\"\nversion: 1.0.0\nauthor: Hermes Agent\ntags: [music, audio, generation, ai, open-source, heartmula, audiocraft, musicgen, audiogen, encodec]\n---\n\n# Open-Source Music Generation\n\nA unified guide to two major open-source music generation ecosystems: **HeartMuLa** and **AudioCraft (MusicGen\u002FAudioGen)**. Both generate audio from text descriptions; HeartMuLa specializes in lyrics-conditioned song generation while AudioCraft offers broader text-to-music and text-to-sound capabilities with melody conditioning.\n\n## Quick Comparison\n\n| Feature | HeartMuLa | AudioCraft |\n|---------|-----------|------------|\n| Focus | Lyrics+tags song generation | Text-to-music, text-to-sound |\n| Model sizes | 3B, 7B | 300M (small) to 3.3B (large) |\n| Output | MP3 48kHz stereo | WAV 32kHz mono\u002Fstereo |\n| VRAM (min) | ~6.2GB (3B lazy) | ~2GB (small fp16) to ~16GB (large) |\n| Lyrics support | Core feature (required) | Not supported (text-only) |\n| Melody conditioning | No | Yes (musicgen-melody) |\n| License | Apache-2.0 | MIT |\n| Setup complexity | Medium (patches needed) | Low (pip install) |\n\n**When to use HeartMuLa:** You need to generate a full song with lyrics, multiple languages, or want the most open-source-capable Suno alternative.\n\n**When to use AudioCraft:** You need text-to-music or text-to-sound effects, melody conditioning, stereo output, or style transfer.\n\n---\n\n## HeartMuLa — Lyrics-to-Song Generation\n\nHeartMuLa generates full songs from lyrics + genre\u002Fstyle tags. Families of models: HeartMuLa (music language model), HeartCodec (12.5Hz audio codec), HeartTranscriptor (lyrics transcription), HeartCLAP (audio-text alignment).\n\n### Hardware Requirements\n\n- **Minimum**: 8GB VRAM with `--lazy_load true` (loads\u002Funloads models sequentially, peaks ~6.2GB)\n- **Recommended**: 16GB+ VRAM for single-GPU\n- **Multi-GPU**: `--mula_device cuda:0 --codec_device cuda:1`\n- **CPU mode**: Possible with `--mula_device cpu --codec_device cpu` but extremely slow (30-60 min per song)\n\n### Installation\n\n```bash\n# 1. Clone\ngit clone https:\u002F\u002Fgithub.com\u002FHeartMuLa\u002Fheartlib.git\ncd heartlib\n\n# 2. Python 3.10 venv\nuv venv --python 3.10 .venv\n. .venv\u002Fbin\u002Factivate\nuv pip install -e .\n\n# 3. Fix dependency conflicts\nuv pip install --upgrade datasets transformers\n\n# 4. Download models (all in parallel)\nhf download --local-dir '.\u002Fckpt' 'HeartMuLa\u002FHeartMuLaGen'\nhf download --local-dir '.\u002Fckpt\u002FHeartMuLa-oss-3B' 'HeartMuLa\u002FHeartMuLa-oss-3B-happy-new-year'\nhf download --local-dir '.\u002Fckpt\u002FHeartCodec-oss' 'HeartMuLa\u002FHeartCodec-oss-20260123'\n```\n\n### Source Patches Required\n\n**Patch 1 — RoPE cache fix** in `src\u002Fheartlib\u002Fheartmula\u002Fmodeling_heartmula.py`:\nAdd RoPE reinitialization in `setup_caches` after `reset_caches` and before `with device:`:\n```python\nfrom torchtune.models.llama3_1._position_embeddings import Llama3ScaledRoPE\nfor module in self.modules():\n    if isinstance(module, Llama3ScaledRoPE) and not module.is_cache_built:\n        module.rope_init()\n        module.to(device)\n```\n\n**Patch 2 — HeartCodec loading fix** in `src\u002Fheartlib\u002Fpipelines\u002Fmusic_generation.py`:\nAdd `ignore_mismatched_sizes=True` to ALL `HeartCodec.from_pretrained()` calls.\n\n### Usage\n\n```bash\ncd heartlib && . .venv\u002Fbin\u002Factivate\npython .\u002Fexamples\u002Frun_music_generation.py \\\n  --model_path=.\u002Fckpt \\\n  --version=\"3B\" \\\n  --lyrics=\".\u002Fassets\u002Flyrics.txt\" \\\n  --tags=\".\u002Fassets\u002Ftags.txt\" \\\n  --save_path=\".\u002Fassets\u002Foutput.mp3\" \\\n  --lazy_load true\n```\n\n**Tags** (comma-separated, no spaces): `piano,happy,wedding,synthesizer,romantic`\n**Lyrics** use bracketed structural tags: `[Intro]`, `[Verse]`, `[Chorus]`, `[Bridge]`, `[Outro]`\n\n### Key Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `--max_audio_length_ms` | 240000 | Max length (240s = 4 min) |\n| `--temperature` | 1.0 | Sampling temperature |\n| `--cfg_scale` | 1.5 | Classifier-free guidance scale |\n| `--lazy_load` | false | Load\u002Funload models on demand |\n\n**Pitfall:** Do NOT use bf16 for HeartCodec — degrades audio quality. Use fp32.\n\n### Links\n- Repo: https:\u002F\u002Fgithub.com\u002FHeartMuLa\u002Fheartlib\n- Models: https:\u002F\u002Fhuggingface.co\u002FHeartMuLa\n- Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.10547\n- License: Apache-2.0\n\n---\n\n## AudioCraft — Text-to-Music and Text-to-Sound\n\nMeta's AudioCraft framework covers MusicGen (text-to-music), AudioGen (text-to-sound), and EnCodec (neural audio codec).\n\n### Quick Start\n\n```bash\npip install audiocraft\n# Or for latest: pip install git+https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Faudiocraft.git\n```\n\n### Model Variants\n\n| Model | Size | Use Case |\n|-------|------|----------|\n| `musicgen-small` | 300M | Quick generation |\n| `musicgen-medium` | 1.5B | Balanced quality\u002Fspeed |\n| `musicgen-large` | 3.3B | Best quality |\n| `musicgen-melody` | 1.5B | Melody-conditioned generation |\n| `musicgen-stereo-medium` | 1.5B | Stereo output |\n| `musicgen-style` | 1.5B | Style transfer from reference audio |\n| `audiogen-medium` | 1.5B | Sound effects generation |\n\n### Basic Text-to-Music\n\n```python\nfrom audiocraft.models import MusicGen\nimport torchaudio\n\nmodel = MusicGen.get_pretrained('facebook\u002Fmusicgen-medium')\nmodel.set_generation_params(duration=30, top_k=250, temperature=1.0, cfg_coef=3.0)\nwav = model.generate([\"upbeat electronic dance music with synths\"])\ntorchaudio.save(\"output.wav\", wav[0].cpu(), sample_rate=32000)\n```\n\n### Text-to-Sound (AudioGen)\n\n```python\nfrom audiocraft.models import AudioGen\nmodel = AudioGen.get_pretrained('facebook\u002Faudiogen-medium')\nmodel.set_generation_params(duration=5)\nwav = model.generate([\"dog barking in a park with birds chirping\"])\ntorchaudio.save(\"sound.wav\", wav[0].cpu(), sample_rate=16000)\n```\n\n### Melody Conditioning\n\n```python\nfrom audiocraft.models import MusicGen\nmodel = MusicGen.get_pretrained('facebook\u002Fmusicgen-melody')\nmodel.set_generation_params(duration=30)\nmelody, sr = torchaudio.load(\"melody.wav\")\nwav = model.generate_with_chroma([\"acoustic guitar folk song\"], melody, sr)\n```\n\n### Generation Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `duration` | 8.0 | Length in seconds (1-120) |\n| `top_k` | 250 | Top-k sampling |\n| `top_p` | 0.0 | Nucleus sampling |\n| `temperature` | 1.0 | Sampling temperature |\n| `cfg_coef` | 3.0 | Classifier-free guidance |\n\n### Performance\n\n| Model | FP32 VRAM | FP16 VRAM | Generation Time (30s) |\n|-------|-----------|-----------|----------------------|\n| musicgen-small | ~4GB | ~2GB | ~5s |\n| musicgen-medium | ~8GB | ~4GB | ~15s |\n| musicgen-large | ~16GB | ~8GB | ~30s |\n\n### Advanced Usage\n\nSee `references\u002Faudiocraft-advanced-usage.md` for fine-tuning, MultiBand Diffusion, API server deployment, batch processing, LangChain integration, and evaluation.\n\n### Troubleshooting\n\nSee `references\u002Faudiocraft-troubleshooting.md` for common installation, model loading, generation, memory, and format issues.\n\n### Links\n- GitHub: https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Faudiocraft\n- Paper (MusicGen): https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.05284\n- Paper (AudioGen): https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.15352\n- HuggingFace: https:\u002F\u002Fhuggingface.co\u002Ffacebook\u002Fmusicgen-small\n\n---\n\n## Songwriting Craft & Prompt Engineering\n\nFor songwriting craft, lyric structure, rhyme schemes, Suno AI metatag engineering, and phonetic tricks for AI vocalists, see the `songwriting-and-ai-music` skill. That skill covers:\n\n- Song structure (verse\u002Fchorus\u002Fbridge patterns)\n- Rhyme types and meter\n- Emotional arc and dynamics\n- Suno AI style prompt engineering\n- Metatags for vocal and dynamic control\n- Parody and adaptation techniques\n\nFor audio analysis and spectrogram visualization, see the `songsee` skill.","# Open-Source Music Generation\n\nA unified guide to two major open-source music generation ecosystems: **HeartMuLa** and **AudioCraft (MusicGen\u002FAudioGen)**. Both generate audio from text descriptions; HeartMuLa specializes in lyrics-conditioned song generation while AudioCraft offers broader text-to-music and text-to-sound capabilities with melody conditioning.\n\n## Quick Comparison\n\n| Feature | HeartMuLa | AudioCraft |\n|---------|-----------|------------|\n| Focus | Lyrics+tags song generation | Text-to-music, text-to-sound |\n| Model sizes | 3B, 7B | 300M (small) to 3.3B (large) |\n| Output | MP3 48kHz stereo | WAV 32kHz mono\u002Fstereo |\n| VRAM (min) | ~6.2GB (3B lazy) | ~2GB (small fp16) to ~16GB (large) |\n| Lyrics support | Core feature (required) | Not supported (text-only) |\n| Melody conditioning | No | Yes (musicgen-melody) |\n| License | Apache-2.0 | MIT |\n| Setup complexity | Medium (patches needed) | Low (pip install) |\n\n**When to use HeartMuLa:** You need to generate a full song with lyrics, multiple languages, or want the most open-source-capable Suno alternative.\n\n**When to use AudioCraft:** You need text-to-music or text-to-sound effects, melody conditioning, stereo output, or style transfer.\n\n---\n\n## HeartMuLa — Lyrics-to-Song Generation\n\nHeartMuLa generates full songs from lyrics + genre\u002Fstyle tags. Families of models: HeartMuLa (music language model), HeartCodec (12.5Hz audio codec), HeartTranscriptor (lyrics transcription), HeartCLAP (audio-text alignment).\n\n### Hardware Requirements\n\n- **Minimum**: 8GB VRAM with `--lazy_load true` (loads\u002Funloads models sequentially, peaks ~6.2GB)\n- **Recommended**: 16GB+ VRAM for single-GPU\n- **Multi-GPU**: `--mula_device cuda:0 --codec_device cuda:1`\n- **CPU mode**: Possible with `--mula_device cpu --codec_device cpu` but extremely slow (30-60 min per song)\n\n### Installation\n\n```bash\n# 1. Clone\ngit clone https:\u002F\u002Fgithub.com\u002FHeartMuLa\u002Fheartlib.git\ncd heartlib\n\n# 2. Python 3.10 venv\nuv venv --python 3.10 .venv\n. .venv\u002Fbin\u002Factivate\nuv pip install -e .\n\n# 3. Fix dependency conflicts\nuv pip install --upgrade datasets transformers\n\n# 4. Download models (all in parallel)\nhf download --local-dir '.\u002Fckpt' 'HeartMuLa\u002FHeartMuLaGen'\nhf download --local-dir '.\u002Fckpt\u002FHeartMuLa-oss-3B' 'HeartMuLa\u002FHeartMuLa-oss-3B-happy-new-year'\nhf download --local-dir '.\u002Fckpt\u002FHeartCodec-oss' 'HeartMuLa\u002FHeartCodec-oss-20260123'\n```\n\n### Source Patches Required\n\n**Patch 1 — RoPE cache fix** in `src\u002Fheartlib\u002Fheartmula\u002Fmodeling_heartmula.py`:\nAdd RoPE reinitialization in `setup_caches` after `reset_caches` and before `with device:`:\n```python\nfrom torchtune.models.llama3_1._position_embeddings import Llama3ScaledRoPE\nfor module in self.modules():\n    if isinstance(module, Llama3ScaledRoPE) and not module.is_cache_built:\n        module.rope_init()\n        module.to(device)\n```\n\n**Patch 2 — HeartCodec loading fix** in `src\u002Fheartlib\u002Fpipelines\u002Fmusic_generation.py`:\nAdd `ignore_mismatched_sizes=True` to ALL `HeartCodec.from_pretrained()` calls.\n\n### Usage\n\n```bash\ncd heartlib && . .venv\u002Fbin\u002Factivate\npython .\u002Fexamples\u002Frun_music_generation.py \\\n  --model_path=.\u002Fckpt \\\n  --version=\"3B\" \\\n  --lyrics=\".\u002Fassets\u002Flyrics.txt\" \\\n  --tags=\".\u002Fassets\u002Ftags.txt\" \\\n  --save_path=\".\u002Fassets\u002Foutput.mp3\" \\\n  --lazy_load true\n```\n\n**Tags** (comma-separated, no spaces): `piano,happy,wedding,synthesizer,romantic`\n**Lyrics** use bracketed structural tags: `[Intro]`, `[Verse]`, `[Chorus]`, `[Bridge]`, `[Outro]`\n\n### Key Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `--max_audio_length_ms` | 240000 | Max length (240s = 4 min) |\n| `--temperature` | 1.0 | Sampling temperature |\n| `--cfg_scale` | 1.5 | Classifier-free guidance scale |\n| `--lazy_load` | false | Load\u002Funload models on demand |\n\n**Pitfall:** Do NOT use bf16 for HeartCodec — degrades audio quality. Use fp32.\n\n### Links\n- Repo: https:\u002F\u002Fgithub.com\u002FHeartMuLa\u002Fheartlib\n- Models: https:\u002F\u002Fhuggingface.co\u002FHeartMuLa\n- Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2601.10547\n- License: Apache-2.0\n\n---\n\n## AudioCraft — Text-to-Music and Text-to-Sound\n\nMeta's AudioCraft framework covers MusicGen (text-to-music), AudioGen (text-to-sound), and EnCodec (neural audio codec).\n\n### Quick Start\n\n```bash\npip install audiocraft\n# Or for latest: pip install git+https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Faudiocraft.git\n```\n\n### Model Variants\n\n| Model | Size | Use Case |\n|-------|------|----------|\n| `musicgen-small` | 300M | Quick generation |\n| `musicgen-medium` | 1.5B | Balanced quality\u002Fspeed |\n| `musicgen-large` | 3.3B | Best quality |\n| `musicgen-melody` | 1.5B | Melody-conditioned generation |\n| `musicgen-stereo-medium` | 1.5B | Stereo output |\n| `musicgen-style` | 1.5B | Style transfer from reference audio |\n| `audiogen-medium` | 1.5B | Sound effects generation |\n\n### Basic Text-to-Music\n\n```python\nfrom audiocraft.models import MusicGen\nimport torchaudio\n\nmodel = MusicGen.get_pretrained('facebook\u002Fmusicgen-medium')\nmodel.set_generation_params(duration=30, top_k=250, temperature=1.0, cfg_coef=3.0)\nwav = model.generate([\"upbeat electronic dance music with synths\"])\ntorchaudio.save(\"output.wav\", wav[0].cpu(), sample_rate=32000)\n```\n\n### Text-to-Sound (AudioGen)\n\n```python\nfrom audiocraft.models import AudioGen\nmodel = AudioGen.get_pretrained('facebook\u002Faudiogen-medium')\nmodel.set_generation_params(duration=5)\nwav = model.generate([\"dog barking in a park with birds chirping\"])\ntorchaudio.save(\"sound.wav\", wav[0].cpu(), sample_rate=16000)\n```\n\n### Melody Conditioning\n\n```python\nfrom audiocraft.models import MusicGen\nmodel = MusicGen.get_pretrained('facebook\u002Fmusicgen-melody')\nmodel.set_generation_params(duration=30)\nmelody, sr = torchaudio.load(\"melody.wav\")\nwav = model.generate_with_chroma([\"acoustic guitar folk song\"], melody, sr)\n```\n\n### Generation Parameters\n\n| Parameter | Default | Description |\n|-----------|---------|-------------|\n| `duration` | 8.0 | Length in seconds (1-120) |\n| `top_k` | 250 | Top-k sampling |\n| `top_p` | 0.0 | Nucleus sampling |\n| `temperature` | 1.0 | Sampling temperature |\n| `cfg_coef` | 3.0 | Classifier-free guidance |\n\n### Performance\n\n| Model | FP32 VRAM | FP16 VRAM | Generation Time (30s) |\n|-------|-----------|-----------|----------------------|\n| musicgen-small | ~4GB | ~2GB | ~5s |\n| musicgen-medium | ~8GB | ~4GB | ~15s |\n| musicgen-large | ~16GB | ~8GB | ~30s |\n\n### Advanced Usage\n\nSee `references\u002Faudiocraft-advanced-usage.md` for fine-tuning, MultiBand Diffusion, API server deployment, batch processing, LangChain integration, and evaluation.\n\n### Troubleshooting\n\nSee `references\u002Faudiocraft-troubleshooting.md` for common installation, model loading, generation, memory, and format issues.\n\n### Links\n- GitHub: https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Faudiocraft\n- Paper (MusicGen): https:\u002F\u002Farxiv.org\u002Fabs\u002F2306.05284\n- Paper (AudioGen): https:\u002F\u002Farxiv.org\u002Fabs\u002F2209.15352\n- HuggingFace: https:\u002F\u002Fhuggingface.co\u002Ffacebook\u002Fmusicgen-small\n\n---\n\n## Songwriting Craft & Prompt Engineering\n\nFor songwriting craft, lyric structure, rhyme schemes, Suno AI metatag engineering, and phonetic tricks for AI vocalists, see the `songwriting-and-ai-music` skill. That skill covers:\n\n- Song structure (verse\u002Fchorus\u002Fbridge patterns)\n- Rhyme types and meter\n- Emotional arc and dynamics\n- Suno AI style prompt engineering\n- Metatags for vocal and dynamic control\n- Parody and adaptation techniques\n\nFor audio analysis and spectrogram visualization, see the `songsee` skill.",{"name":5,"tags":48,"author":54,"version":55,"description":7},[25,49,27,50,51,52,35,53,32,31],"audio","ai","open-source","heartmula","musicgen","Hermes Agent","1.0.0","master","8ec37df6d71fb664ea19d32c079e7d3ff931a8e0","skills\u002Fcontent\u002Fopen-source-music-generation",3,"https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit","https:\u002F\u002Fweblyfe.ai","https:\u002F\u002Fgithub.com\u002FS3YED","2026-08-27 01:54:02",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add S3YED\u002Fappie-kit --skill open-source-music-generation",{"tool":70,"command":71},"bunx","bunx skills add S3YED\u002Fappie-kit --skill open-source-music-generation",{"tool":73,"command":74},"pnpm","pnpm dlx skills add S3YED\u002Fappie-kit --skill open-source-music-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fcontent\u002Fopen-source-music-generation\u002FSKILL.md",true,[78,84],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Faudiocraft-advanced-usage.md","REFERENCE","参考文档",16953,"https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fcontent\u002Fopen-source-music-generation\u002Freferences\u002Faudiocraft-advanced-usage.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Faudiocraft-troubleshooting.md",11412,"https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fcontent\u002Fopen-source-music-generation\u002Freferences\u002Faudiocraft-troubleshooting.md",[89,114,149,172,203,227],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":102,"publishedAt":43},"01M6JFD4M6N4DSGC7TXEJ5R3J2","ai-music","AI music generation and audio tools: HeartMuLa lyrics-to-music generation, songwriting craft (+ Suno prompts), and audio spectrogram\u002Ffeature visualization.","https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fwethlete\u002Fai-music\u002FSKILL.md",[95,98,101],{"categoryNo":96,"categoryName":97,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":99,"categoryName":100,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[25,103,104,105,42,41,106,107,108,109,110,111,52,112,27,113,37,29],"ai music","humanizer","visualization","hermes","hermes agent","songwriting","suno","lyrics","prompts","craft","feature",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":128,"publishedAt":43},"01M6JFCZE4XNFQFMNZDHKHT5V5","agentic-webdesign-design-system-ingestion","Use v0 Design Systems 2.0, Bolt Design System Agents, or Lovable to generate production UI from a client's real design system components — not generic Tailwind. Use when building a client website where brand consistency matters.","https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fweb-design\u002Fagentic-webdesign-design-system-ingestion\u002FSKILL.md",[120,123],{"categoryNo":121,"categoryName":122,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148],"design","agentic","design system","system","ingestion","webdesign","agentic webdesign design system ingestion","components","generate","design systems","website","ui","Tailwind","bolt","lovable","v0","design-system","wed","design system components","appie",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":157,"publishedAt":43},"01M6JFCVPX3913CFAS6QQJ33ZB","agentic-webdesign-agent-elements","Use 21st.dev Agent Elements — 25 shadcn\u002Fui components purpose-built for AI agent UIs. Tool cards (Bash, Edit, Search, Plan, Subagent, MCP), chat, input, streaming. Open source, shadcn-registry install, no runtime lock-in.","https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fweb-design\u002Fagentic-webdesign-agent-elements\u002FSKILL.md",[155,156],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},[130,158,134,159,160,161,136,162,163,164,28,24,165,166,167,168,169,170,171,26],"elements","agentic webdesign agent elements","MCP","ai agent","registry","search","streaming","Bash","plan","subagent","edit","install","input","lock",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":182,"publishedAt":43},"01M6JFCQC7H65M9QJ6TRE71BS1","vercel-deployment","Deploy static sites and frontends to Vercel — handles both CLI and REST API paths, including the CLI token sanitization workaround.","https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fsoftware-development\u002Fvercel-deployment\u002FSKILL.md",[178,181],{"categoryNo":179,"categoryName":180,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202],"deployment","vercel deployment","vercel","macos","cli","linux","windows","deploy","vercel deploy","REST","api","site","deploy to vercel","token","rest api","host","sites","paths","sanitization","static site",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":210,"publishedAt":43},"01M6JFCM4SMTXBM5A01BK2YQG1","software-quality-workflows","Umbrella workflow for TDD, debugging, code simplification, spikes, pre-commit review, and debugger-assisted investigation.","https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fsoftware-development\u002Fsoftware-quality-workflows\u002FSKILL.md",[209],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,33],"workflows","quality","software","software quality workflows","review","tdd","workflow","commit","debugging","code","debugger","pre-commit","investigation","code simplification","user","simplification",{"skillNo":228,"name":229,"nameZh":6,"description":230,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":231,"categories":232,"keywords":240,"publishedAt":43},"01M6JFCGD0M6CEATY01W7YN6DB","react-component-refactoring","Safely refactor large React components into smaller, maintainable pieces using proven patterns","https:\u002F\u002Fgithub.com\u002FS3YED\u002Fappie-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fsoftware-development\u002Freact-component-refactoring\u002FSKILL.md",[233,236,239],{"categoryNo":234,"categoryName":235,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":237,"categoryName":238,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[241,242,243,244,245,246,247,248,186,249,250,136,251,189,252,220,253,254,255,256],"react","component","refactoring","component refactoring","react component","react component refactoring","frontend","writing","safe","typescript","react components","modular","refactor","simplify","patterns","test-driven-development"]