[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FJB13263RHG85FHBVC1VDX":3,"skill-same:01M6FJB13263RHG85FHBVC1VDX":92},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6FJB13263RHG85FHBVC1VDX","voice-note-to-midi",null,"Convert voice notes, humming, and melodic audio recordings to quantized MIDI files using ML-based pitch detection and intelligent post-processing","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdanbennettuk\u002Fvoice-note-to-midi\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","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],"note","voice","voice note to midi","midi","files","post-processing","processing","machine","post","pitch","transcription","notes","recordings","convert","music","learning","Audio","machine-learning","detection","ml","2026-11-10 10:12:30",false,"---\nname: voice-note-to-midi\ndescription: Convert voice notes, humming, and melodic audio recordings to quantized MIDI files using ML-based pitch detection and intelligent post-processing\nauthor: Clawd\ntags: [audio, midi, music, transcription, machine-learning]\n---\n\n# ? Voice Note to MIDI\n\nTransform your voice memos, humming, and melodic recordings into clean, quantized MIDI files ready for your DAW.\n\n## What It Does\n\nThis skill provides a complete audio-to-MIDI conversion pipeline that:\n\n1. **Stem Separation** - Uses HPSS (Harmonic-Percussive Source Separation) to isolate melodic content from drums, noise, and background sounds\n2. **ML-Powered Pitch Detection** - Leverages Spotify's Basic Pitch model for accurate fundamental frequency extraction\n3. **Key Detection** - Automatically detects the musical key of your recording using Krumhansl-Kessler key profiles\n4. **Intelligent Quantization** - Snaps notes to a configurable timing grid with optional key-aware pitch correction\n5. **Post-Processing** - Applies octave pruning, overlap-based harmonic removal, and legato note merging for clean output\n\n### Pipeline Architecture\n\n```\nAudio Input (WAV\u002FM4A\u002FMP3)\n    ↓\n┌─────────────────────────────────────┐\n│ Step 1: Stem Separation (HPSS)     │\n│ - Isolate harmonic content          │\n│ - Remove drums\u002Fpercussion           │\n│ - Noise gating                      │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│ Step 2: Pitch Detection             │\n│ - Basic Pitch ML model (Spotify)    │\n│ - Polyphonic note detection         │\n│ - Onset\u002Foffset estimation           │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│ Step 3: Analysis                    │\n│ - Pitch class distribution          │\n│ - Key detection                     │\n│ - Dominant note identification      │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│ Step 4: Quantization & Cleanup      │\n│ - Timing grid snap                  │\n│ - Key-aware pitch correction        │\n│ - Octave pruning (harmonic removal) │\n│ - Overlap-based pruning             │\n│ - Note merging (legato)             │\n│ - Velocity normalization            │\n└─────────────────────────────────────┘\n    ↓\nMIDI Output (Standard MIDI File)\n```\n\n## Setup\n\n### Prerequisites\n\n- Python 3.11+ (Python 3.14+ recommended)\n- FFmpeg (for audio format support)\n- pip\n\n### Installation\n\n**Quick Install (Recommended):**\n\n```bash\ncd \u002Fpath\u002Fto\u002Fvoice-note-to-midi\n.\u002Fsetup.sh\n```\n\nThis automated script will:\n- Check Python 3.11+ is installed\n- Create the `~\u002Fmelody-pipeline` directory\n- Set up the virtual environment\n- Install all dependencies (basic-pitch, librosa, music21, etc.)\n- Download and configure the hum2midi script\n- Add melody-pipeline to your PATH\n\n**Manual Install:**\n\nIf you prefer manual setup:\n\n```bash\nmkdir -p ~\u002Fmelody-pipeline\ncd ~\u002Fmelody-pipeline\npython3 -m venv venv-bp\nsource venv-bp\u002Fbin\u002Factivate\npip install basic-pitch librosa soundfile mido music21\nchmod +x ~\u002Fmelody-pipeline\u002Fhum2midi\n```\n\n5. **Add to your PATH (optional):**\n\n```bash\necho 'export PATH=\"$HOME\u002Fmelody-pipeline:$PATH\"' >> ~\u002F.bashrc\nsource ~\u002F.bashrc\n```\n\n### Verify Installation\n\n```bash\ncd ~\u002Fmelody-pipeline\n.\u002Fhum2midi --help\n```\n\n## Usage\n\n### Basic Usage\n\nConvert a voice memo to MIDI:\n\n```bash\n.\u002Fhum2midi my_humming.wav\n```\n\nThis creates `my_humming.mid` with 16th-note quantization.\n\n### Specify Output File\n\n```bash\n.\u002Fhum2midi input.wav output.mid\n```\n\n### Command-Line Options\n\n| Option | Description | Default |\n|--------|-------------|---------|\n| `--grid \u003Cvalue>` | Quantization grid: `1\u002F4`, `1\u002F8`, `1\u002F16`, `1\u002F32` | `1\u002F16` |\n| `--min-note \u003Cms>` | Minimum note duration in milliseconds | `50` |\n| `--no-quantize` | Skip quantization (output raw Basic Pitch MIDI) | disabled |\n| `--key-aware` | Enable key-aware pitch correction | disabled |\n| `--no-analysis` | Skip pitch analysis and key detection | disabled |\n\n### Usage Examples\n\n#### Quantize to eighth notes\n```bash\n.\u002Fhum2midi melody.wav --grid 1\u002F8\n```\n\n#### Key-aware quantization (recommended for tonal music)\n```bash\n.\u002Fhum2midi song.wav --key-aware\n```\n\n#### Require longer minimum notes\n```bash\n.\u002Fhum2midi humming.wav --min-note 100\n```\n\n#### Skip analysis for faster processing\n```bash\n.\u002Fhum2midi quick.wav --no-analysis\n```\n\n#### Combine options\n```bash\n.\u002Fhum2midi recording.wav output.mid --grid 1\u002F8 --key-aware --min-note 80\n```\n\n### Processing MIDI Input\n\nYou can also process existing MIDI files through the quantization pipeline:\n\n```bash\n.\u002Fhum2midi input.mid output.mid --grid 1\u002F16 --key-aware\n```\n\nThis skips the audio processing steps and goes directly to analysis and quantization.\n\n## Sample Output\n\n```\n═══════════════════════════════════════════════════════════════\n  hum2midi - Melody-to-MIDI Pipeline (Basic Pitch Edition)\n  [Key-Aware Mode Enabled]\n═══════════════════════════════════════════════════════════════\n\nInput:  my_humming.wav\nOutput: my_humming.mid\n\n→ Step 1: Stem Separation (HPSS)\n  Isolating melodic content...\n  Loaded: 5.23s @ 44100Hz\n  ✓ Melody stem extracted → 5.23s\n\n→ Step 2: Audio-to-MIDI Conversion (Basic Pitch)\n  Running Spotify's Basic Pitch ML model on melody stem...\n  ✓ Raw MIDI generated (Basic Pitch)\n\n→ Step 3: Pitch Analysis & Key Detection\n  Notes detected: 42 total, 7 unique\n  Note range: C3 - G4\n  Pitch classes: C3, E3, G3, A3, C4, D4, G4\n  Dominant note: G3 (23.8% of notes)\n  Detected key: G major\n\n→ Step 4: Quantization & Cleanup\n  Octave pruning: removed 3 harmonic notes above 67 (median+12)\n  Overlap pruning: removed 2 harmonic notes at overlapping positions\n  Note merging: merged 5 staccato chunks into legato notes (gap\u003C=60 ticks)\n  Grid:   240 ticks (1\u002F16)\n  Notes:  38 notes\n  Key:    G major\n  Key-aware: 2 notes corrected to scale\n  Tempo:  120 BPM\n  ✓ Quantized MIDI saved\n\n═══════════════════════════════════════════════════════════════\n  ✓ Done! Output: my_humming.mid\n═══════════════════════════════════════════════════════════════\n\n? ANALYSIS SUMMARY\n─────────────────────────────────────────────────────────────\n  Detected Notes: C3, E3, G3, A3, C4, D4, G4\n  Detected Key:   G major\n  Quantization:   Key-aware mode (notes snapped to scale)\n\nMIDI Info: 38 notes, 7 unique pitches, 120 BPM\nPitches: C3, E3, G3, A3, C4, D4, G4\n```\n\n## Notes & Limitations\n\n### Audio Quality Matters\n\n- **Clear, loud melody** produces the best results\n- **Background noise** can cause false note detection\n- **Reverb and effects** may confuse pitch detection\n- **Close-mic'd vocals** work significantly better than room recordings\n\n### Musical Considerations\n\n- **Monophonic sources** work best (single melody line)\n- **Polyphonic audio** (chords, multiple instruments) will produce messy results\n- **Vibrato and pitch bends** may be quantized to stepped pitches\n- **Rapid note passages** may be missed or merged\n\n### Technical Limitations\n\n- **Tempo is fixed** at 120 BPM in output (time positions are preserved, but tempo may need adjustment in your DAW)\n- **Note velocities** are normalized but may need manual adjustment\n- **Very short notes** (\u003C50ms) may be filtered out by default\n- **Extreme pitch ranges** may cause octave detection issues\n\n### Post-Processing Recommendations\n\nAfter generating MIDI, you may want to:\n\n1. **Import into your DAW** and adjust tempo to match your original recording\n2. **Quantize further** if stricter timing is needed\n3. **Adjust note velocities** for dynamics\n4. **Apply swing\u002Fgroove** templates if the rigid grid sounds too mechanical\n5. **Edit individual notes** that were misdetected (common with fast runs)\n\n### Supported Audio Formats\n\nInput formats supported via FFmpeg:\n- WAV, AIFF, FLAC (uncompressed, best quality)\n- MP3, M4A, AAC (compressed, acceptable)\n- OGG, OPUS (open source formats)\n- Most other formats FFmpeg supports\n\n## Troubleshooting\n\n### No notes detected\n- Check that input file isn't silent or corrupted\n- Try increasing `--min-note` threshold\n- Verify audio has clear melodic content (not just noise)\n\n### Too many notes \u002F messy output\n- Enable octave pruning and overlap pruning (on by default)\n- Use `--key-aware` to constrain to musical scale\n- Check for background noise in source audio\n\n### Wrong key detected\n- Key detection works best with at least 8-10 measures of music\n- Chromatic passages may confuse the detector\n- Manually review and adjust in your DAW if needed\n\n### Notes in wrong octave\n- Basic Pitch sometimes detects harmonics instead of fundamentals\n- The pipeline includes pruning, but some may slip through\n- Use your DAW's transpose function for simple octave shifts\n\n## References\n\n- [Basic Pitch](https:\u002F\u002Fgithub.com\u002Fspotify\u002Fbasic-pitch) - Spotify's polyphonic pitch detection model\n- [librosa HPSS](https:\u002F\u002Flibrosa.org\u002Fdoc\u002Flatest\u002Fgenerated\u002Flibrosa.decompose.hpss.html) - Harmonic-Percussive Source Separation\n- [Krumhansl-Kessler Key Profiles](https:\u002F\u002Frnhart.net\u002Farticles\u002Fkey-finding\u002F) - Key detection algorithm\n\n## License\n\nThis skill integrates Basic Pitch by Spotify, which is licensed under Apache 2.0. The pipeline script and documentation are provided under MIT license.\n","# ? Voice Note to MIDI\n\nTransform your voice memos, humming, and melodic recordings into clean, quantized MIDI files ready for your DAW.\n\n## What It Does\n\nThis skill provides a complete audio-to-MIDI conversion pipeline that:\n\n1. **Stem Separation** - Uses HPSS (Harmonic-Percussive Source Separation) to isolate melodic content from drums, noise, and background sounds\n2. **ML-Powered Pitch Detection** - Leverages Spotify's Basic Pitch model for accurate fundamental frequency extraction\n3. **Key Detection** - Automatically detects the musical key of your recording using Krumhansl-Kessler key profiles\n4. **Intelligent Quantization** - Snaps notes to a configurable timing grid with optional key-aware pitch correction\n5. **Post-Processing** - Applies octave pruning, overlap-based harmonic removal, and legato note merging for clean output\n\n### Pipeline Architecture\n\n```\nAudio Input (WAV\u002FM4A\u002FMP3)\n    ↓\n┌─────────────────────────────────────┐\n│ Step 1: Stem Separation (HPSS)     │\n│ - Isolate harmonic content          │\n│ - Remove drums\u002Fpercussion           │\n│ - Noise gating                      │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│ Step 2: Pitch Detection             │\n│ - Basic Pitch ML model (Spotify)    │\n│ - Polyphonic note detection         │\n│ - Onset\u002Foffset estimation           │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│ Step 3: Analysis                    │\n│ - Pitch class distribution          │\n│ - Key detection                     │\n│ - Dominant note identification      │\n└─────────────────────────────────────┘\n    ↓\n┌─────────────────────────────────────┐\n│ Step 4: Quantization & Cleanup      │\n│ - Timing grid snap                  │\n│ - Key-aware pitch correction        │\n│ - Octave pruning (harmonic removal) │\n│ - Overlap-based pruning             │\n│ - Note merging (legato)             │\n│ - Velocity normalization            │\n└─────────────────────────────────────┘\n    ↓\nMIDI Output (Standard MIDI File)\n```\n\n## Setup\n\n### Prerequisites\n\n- Python 3.11+ (Python 3.14+ recommended)\n- FFmpeg (for audio format support)\n- pip\n\n### Installation\n\n**Quick Install (Recommended):**\n\n```bash\ncd \u002Fpath\u002Fto\u002Fvoice-note-to-midi\n.\u002Fsetup.sh\n```\n\nThis automated script will:\n- Check Python 3.11+ is installed\n- Create the `~\u002Fmelody-pipeline` directory\n- Set up the virtual environment\n- Install all dependencies (basic-pitch, librosa, music21, etc.)\n- Download and configure the hum2midi script\n- Add melody-pipeline to your PATH\n\n**Manual Install:**\n\nIf you prefer manual setup:\n\n```bash\nmkdir -p ~\u002Fmelody-pipeline\ncd ~\u002Fmelody-pipeline\npython3 -m venv venv-bp\nsource venv-bp\u002Fbin\u002Factivate\npip install basic-pitch librosa soundfile mido music21\nchmod +x ~\u002Fmelody-pipeline\u002Fhum2midi\n```\n\n5. **Add to your PATH (optional):**\n\n```bash\necho 'export PATH=\"$HOME\u002Fmelody-pipeline:$PATH\"' >> ~\u002F.bashrc\nsource ~\u002F.bashrc\n```\n\n### Verify Installation\n\n```bash\ncd ~\u002Fmelody-pipeline\n.\u002Fhum2midi --help\n```\n\n## Usage\n\n### Basic Usage\n\nConvert a voice memo to MIDI:\n\n```bash\n.\u002Fhum2midi my_humming.wav\n```\n\nThis creates `my_humming.mid` with 16th-note quantization.\n\n### Specify Output File\n\n```bash\n.\u002Fhum2midi input.wav output.mid\n```\n\n### Command-Line Options\n\n| Option | Description | Default |\n|--------|-------------|---------|\n| `--grid \u003Cvalue>` | Quantization grid: `1\u002F4`, `1\u002F8`, `1\u002F16`, `1\u002F32` | `1\u002F16` |\n| `--min-note \u003Cms>` | Minimum note duration in milliseconds | `50` |\n| `--no-quantize` | Skip quantization (output raw Basic Pitch MIDI) | disabled |\n| `--key-aware` | Enable key-aware pitch correction | disabled |\n| `--no-analysis` | Skip pitch analysis and key detection | disabled |\n\n### Usage Examples\n\n#### Quantize to eighth notes\n```bash\n.\u002Fhum2midi melody.wav --grid 1\u002F8\n```\n\n#### Key-aware quantization (recommended for tonal music)\n```bash\n.\u002Fhum2midi song.wav --key-aware\n```\n\n#### Require longer minimum notes\n```bash\n.\u002Fhum2midi humming.wav --min-note 100\n```\n\n#### Skip analysis for faster processing\n```bash\n.\u002Fhum2midi quick.wav --no-analysis\n```\n\n#### Combine options\n```bash\n.\u002Fhum2midi recording.wav output.mid --grid 1\u002F8 --key-aware --min-note 80\n```\n\n### Processing MIDI Input\n\nYou can also process existing MIDI files through the quantization pipeline:\n\n```bash\n.\u002Fhum2midi input.mid output.mid --grid 1\u002F16 --key-aware\n```\n\nThis skips the audio processing steps and goes directly to analysis and quantization.\n\n## Sample Output\n\n```\n═══════════════════════════════════════════════════════════════\n  hum2midi - Melody-to-MIDI Pipeline (Basic Pitch Edition)\n  [Key-Aware Mode Enabled]\n═══════════════════════════════════════════════════════════════\n\nInput:  my_humming.wav\nOutput: my_humming.mid\n\n→ Step 1: Stem Separation (HPSS)\n  Isolating melodic content...\n  Loaded: 5.23s @ 44100Hz\n  ✓ Melody stem extracted → 5.23s\n\n→ Step 2: Audio-to-MIDI Conversion (Basic Pitch)\n  Running Spotify's Basic Pitch ML model on melody stem...\n  ✓ Raw MIDI generated (Basic Pitch)\n\n→ Step 3: Pitch Analysis & Key Detection\n  Notes detected: 42 total, 7 unique\n  Note range: C3 - G4\n  Pitch classes: C3, E3, G3, A3, C4, D4, G4\n  Dominant note: G3 (23.8% of notes)\n  Detected key: G major\n\n→ Step 4: Quantization & Cleanup\n  Octave pruning: removed 3 harmonic notes above 67 (median+12)\n  Overlap pruning: removed 2 harmonic notes at overlapping positions\n  Note merging: merged 5 staccato chunks into legato notes (gap\u003C=60 ticks)\n  Grid:   240 ticks (1\u002F16)\n  Notes:  38 notes\n  Key:    G major\n  Key-aware: 2 notes corrected to scale\n  Tempo:  120 BPM\n  ✓ Quantized MIDI saved\n\n═══════════════════════════════════════════════════════════════\n  ✓ Done! Output: my_humming.mid\n═══════════════════════════════════════════════════════════════\n\n? ANALYSIS SUMMARY\n─────────────────────────────────────────────────────────────\n  Detected Notes: C3, E3, G3, A3, C4, D4, G4\n  Detected Key:   G major\n  Quantization:   Key-aware mode (notes snapped to scale)\n\nMIDI Info: 38 notes, 7 unique pitches, 120 BPM\nPitches: C3, E3, G3, A3, C4, D4, G4\n```\n\n## Notes & Limitations\n\n### Audio Quality Matters\n\n- **Clear, loud melody** produces the best results\n- **Background noise** can cause false note detection\n- **Reverb and effects** may confuse pitch detection\n- **Close-mic'd vocals** work significantly better than room recordings\n\n### Musical Considerations\n\n- **Monophonic sources** work best (single melody line)\n- **Polyphonic audio** (chords, multiple instruments) will produce messy results\n- **Vibrato and pitch bends** may be quantized to stepped pitches\n- **Rapid note passages** may be missed or merged\n\n### Technical Limitations\n\n- **Tempo is fixed** at 120 BPM in output (time positions are preserved, but tempo may need adjustment in your DAW)\n- **Note velocities** are normalized but may need manual adjustment\n- **Very short notes** (\u003C50ms) may be filtered out by default\n- **Extreme pitch ranges** may cause octave detection issues\n\n### Post-Processing Recommendations\n\nAfter generating MIDI, you may want to:\n\n1. **Import into your DAW** and adjust tempo to match your original recording\n2. **Quantize further** if stricter timing is needed\n3. **Adjust note velocities** for dynamics\n4. **Apply swing\u002Fgroove** templates if the rigid grid sounds too mechanical\n5. **Edit individual notes** that were misdetected (common with fast runs)\n\n### Supported Audio Formats\n\nInput formats supported via FFmpeg:\n- WAV, AIFF, FLAC (uncompressed, best quality)\n- MP3, M4A, AAC (compressed, acceptable)\n- OGG, OPUS (open source formats)\n- Most other formats FFmpeg supports\n\n## Troubleshooting\n\n### No notes detected\n- Check that input file isn't silent or corrupted\n- Try increasing `--min-note` threshold\n- Verify audio has clear melodic content (not just noise)\n\n### Too many notes \u002F messy output\n- Enable octave pruning and overlap pruning (on by default)\n- Use `--key-aware` to constrain to musical scale\n- Check for background noise in source audio\n\n### Wrong key detected\n- Key detection works best with at least 8-10 measures of music\n- Chromatic passages may confuse the detector\n- Manually review and adjust in your DAW if needed\n\n### Notes in wrong octave\n- Basic Pitch sometimes detects harmonics instead of fundamentals\n- The pipeline includes pruning, but some may slip through\n- Use your DAW's transpose function for simple octave shifts\n\n## References\n\n- [Basic Pitch](https:\u002F\u002Fgithub.com\u002Fspotify\u002Fbasic-pitch) - Spotify's polyphonic pitch detection model\n- [librosa HPSS](https:\u002F\u002Flibrosa.org\u002Fdoc\u002Flatest\u002Fgenerated\u002Flibrosa.decompose.hpss.html) - Harmonic-Percussive Source Separation\n- [Krumhansl-Kessler Key Profiles](https:\u002F\u002Frnhart.net\u002Farticles\u002Fkey-finding\u002F) - Key detection algorithm\n\n## License\n\nThis skill integrates Basic Pitch by Spotify, which is licensed under Apache 2.0. The pipeline script and documentation are provided under MIT license.\n",{"name":5,"tags":48,"author":50,"description":7},[49,26,37,33,40],"audio","Clawd","main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fdanbennettuk\u002Fvoice-note-to-midi",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add kbarbel640-del\u002Fskills --skill voice-note-to-midi",{"tool":64,"command":65},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill voice-note-to-midi",{"tool":67,"command":68},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill voice-note-to-midi","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdanbennettuk\u002Fvoice-note-to-midi\u002FSKILL.md",true,[72,78,82,86],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"_meta.json","REFERENCE","参考文档",294,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdanbennettuk\u002Fvoice-note-to-midi\u002F_meta.json",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"QUICKSTART.md",1847,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdanbennettuk\u002Fvoice-note-to-midi\u002FQUICKSTART.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"README.md",4066,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdanbennettuk\u002Fvoice-note-to-midi\u002FREADME.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"setup.sh","SCRIPT","脚本",3813,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdanbennettuk\u002Fvoice-note-to-midi\u002Fsetup.sh",[93,124,151,172,178,198],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":104,"publishedAt":43},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":133,"publishedAt":43},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[130],{"categoryNo":131,"categoryName":132,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[134,107,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,112,150],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":43},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[161,162,163,164,165,166,167,108,168,148,150,169,107,170,171],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":173,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":177,"publishedAt":43},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[176],{"categoryNo":158,"categoryName":159,"taxonomyType":20,"taxonomyTypeDesc":21},[164,163,162,161,171,166,167,108,165,148,150,168,169,107,170],{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":43},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[185,186,187,188,189,190,191,192,193,194,195,196,197],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":208,"publishedAt":43},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[204,205],{"categoryNo":131,"categoryName":132,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":206,"categoryName":207,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000037","律师与法务",[209,210,211,212,108,213,214,51,215,169,216,217,218,219,220,121,221,222,223],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]