[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADVQPFHGEWS27TM4MMT0AC":3,"skill-same:01M6ADVQPFHGEWS27TM4MMT0AC":99},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":69,"commitSha":70,"skillDirectory":71,"forksCount":72,"repositoryHtmlUrl":73,"repositoryHomepageUrl":74,"ownerHtmlUrl":75,"ownerBlogUrl":76,"ownerDescription":77,"updatedAt":78,"install":79,"resources":92},"01M6ADVQPFHGEWS27TM4MMT0AC","multimodal-whisper",null,"OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fmultimodal-whisper\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"multimodal","multimodal whisper","whisper","speech recognition","for","orchestra","Audio Processing","processing","identification","english","translation","multilingual","general","research","model","text","Audio","ASR","Transformers","speech","openai","2026-11-10 10:12:30",false,"---\nname: multimodal-whisper\ndescription: OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Orchestra Research\n  tags: [Whisper, Speech Recognition, ASR, Multimodal, Multilingual, OpenAI, Speech-To-Text, Transcription, Translation, Audio Processing]\n  dependencies: [openai-whisper, transformers, torch]\n---\n\n# Whisper - Robust Speech Recognition\n\nOpenAI's multilingual speech recognition model.\n\n## When to use Whisper\n\n**Use when:**\n- Speech-to-text transcription (99 languages)\n- Podcast\u002Fvideo transcription\n- Meeting notes automation\n- Translation to English\n- Noisy audio transcription\n- Multilingual audio processing\n\n**Metrics**:\n- **72,900+ GitHub stars**\n- 99 languages supported\n- Trained on 680,000 hours of audio\n- MIT License\n\n**Use alternatives instead**:\n- **AssemblyAI**: Managed API, speaker diarization\n- **Deepgram**: Real-time streaming ASR\n- **Google Speech-to-Text**: Cloud-based\n\n## Quick start\n\n### Installation\n\n```bash\n# Requires Python 3.8-3.11\npip install -U openai-whisper\n\n# Requires ffmpeg\n# macOS: brew install ffmpeg\n# Ubuntu: sudo apt install ffmpeg\n# Windows: choco install ffmpeg\n```\n\n### Basic transcription\n\n```python\nimport whisper\n\n# Load model\nmodel = whisper.load_model(\"base\")\n\n# Transcribe\nresult = model.transcribe(\"audio.mp3\")\n\n# Print text\nprint(result[\"text\"])\n\n# Access segments\nfor segment in result[\"segments\"]:\n    print(f\"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}\")\n```\n\n## Model sizes\n\n```python\n# Available models\nmodels = [\"tiny\", \"base\", \"small\", \"medium\", \"large\", \"turbo\"]\n\n# Load specific model\nmodel = whisper.load_model(\"turbo\")  # Fastest, good quality\n```\n\n| Model | Parameters | English-only | Multilingual | Speed | VRAM |\n|-------|------------|--------------|--------------|-------|------|\n| tiny | 39M | ✓ | ✓ | ~32x | ~1 GB |\n| base | 74M | ✓ | ✓ | ~16x | ~1 GB |\n| small | 244M | ✓ | ✓ | ~6x | ~2 GB |\n| medium | 769M | ✓ | ✓ | ~2x | ~5 GB |\n| large | 1550M | ✗ | ✓ | 1x | ~10 GB |\n| turbo | 809M | ✗ | ✓ | ~8x | ~6 GB |\n\n**Recommendation**: Use `turbo` for best speed\u002Fquality, `base` for prototyping\n\n## Transcription options\n\n### Language specification\n\n```python\n# Auto-detect language\nresult = model.transcribe(\"audio.mp3\")\n\n# Specify language (faster)\nresult = model.transcribe(\"audio.mp3\", language=\"en\")\n\n# Supported: en, es, fr, de, it, pt, ru, ja, ko, zh, and 89 more\n```\n\n### Task selection\n\n```python\n# Transcription (default)\nresult = model.transcribe(\"audio.mp3\", task=\"transcribe\")\n\n# Translation to English\nresult = model.transcribe(\"spanish.mp3\", task=\"translate\")\n# Input: Spanish audio → Output: English text\n```\n\n### Initial prompt\n\n```python\n# Improve accuracy with context\nresult = model.transcribe(\n    \"audio.mp3\",\n    initial_prompt=\"This is a technical podcast about machine learning and AI.\"\n)\n\n# Helps with:\n# - Technical terms\n# - Proper nouns\n# - Domain-specific vocabulary\n```\n\n### Timestamps\n\n```python\n# Word-level timestamps\nresult = model.transcribe(\"audio.mp3\", word_timestamps=True)\n\nfor segment in result[\"segments\"]:\n    for word in segment[\"words\"]:\n        print(f\"{word['word']} ({word['start']:.2f}s - {word['end']:.2f}s)\")\n```\n\n### Temperature fallback\n\n```python\n# Retry with different temperatures if confidence low\nresult = model.transcribe(\n    \"audio.mp3\",\n    temperature=(0.0, 0.2, 0.4, 0.6, 0.8, 1.0)\n)\n```\n\n## Command line usage\n\n```bash\n# Basic transcription\nwhisper audio.mp3\n\n# Specify model\nwhisper audio.mp3 --model turbo\n\n# Output formats\nwhisper audio.mp3 --output_format txt     # Plain text\nwhisper audio.mp3 --output_format srt     # Subtitles\nwhisper audio.mp3 --output_format vtt     # WebVTT\nwhisper audio.mp3 --output_format json    # JSON with timestamps\n\n# Language\nwhisper audio.mp3 --language Spanish\n\n# Translation\nwhisper spanish.mp3 --task translate\n```\n\n## Batch processing\n\n```python\nimport os\n\naudio_files = [\"file1.mp3\", \"file2.mp3\", \"file3.mp3\"]\n\nfor audio_file in audio_files:\n    print(f\"Transcribing {audio_file}...\")\n    result = model.transcribe(audio_file)\n\n    # Save to file\n    output_file = audio_file.replace(\".mp3\", \".txt\")\n    with open(output_file, \"w\") as f:\n        f.write(result[\"text\"])\n```\n\n## Real-time transcription\n\n```python\n# For streaming audio, use faster-whisper\n# pip install faster-whisper\n\nfrom faster_whisper import WhisperModel\n\nmodel = WhisperModel(\"base\", device=\"cuda\", compute_type=\"float16\")\n\n# Transcribe with streaming\nsegments, info = model.transcribe(\"audio.mp3\", beam_size=5)\n\nfor segment in segments:\n    print(f\"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}\")\n```\n\n## GPU acceleration\n\n```python\nimport whisper\n\n# Automatically uses GPU if available\nmodel = whisper.load_model(\"turbo\")\n\n# Force CPU\nmodel = whisper.load_model(\"turbo\", device=\"cpu\")\n\n# Force GPU\nmodel = whisper.load_model(\"turbo\", device=\"cuda\")\n\n# 10-20× faster on GPU\n```\n\n## Integration with other tools\n\n### Subtitle generation\n\n```bash\n# Generate SRT subtitles\nwhisper video.mp4 --output_format srt --language English\n\n# Output: video.srt\n```\n\n### With LangChain\n\n```python\nfrom langchain.document_loaders import WhisperTranscriptionLoader\n\nloader = WhisperTranscriptionLoader(file_path=\"audio.mp3\")\ndocs = loader.load()\n\n# Use transcription in RAG\nfrom langchain_chroma import Chroma\nfrom langchain_openai import OpenAIEmbeddings\n\nvectorstore = Chroma.from_documents(docs, OpenAIEmbeddings())\n```\n\n### Extract audio from video\n\n```bash\n# Use ffmpeg to extract audio\nffmpeg -i video.mp4 -vn -acodec pcm_s16le audio.wav\n\n# Then transcribe\nwhisper audio.wav\n```\n\n## Best practices\n\n1. **Use turbo model** - Best speed\u002Fquality for English\n2. **Specify language** - Faster than auto-detect\n3. **Add initial prompt** - Improves technical terms\n4. **Use GPU** - 10-20× faster\n5. **Batch process** - More efficient\n6. **Convert to WAV** - Better compatibility\n7. **Split long audio** - \u003C30 min chunks\n8. **Check language support** - Quality varies by language\n9. **Use faster-whisper** - 4× faster than openai-whisper\n10. **Monitor VRAM** - Scale model size to hardware\n\n## Performance\n\n| Model | Real-time factor (CPU) | Real-time factor (GPU) |\n|-------|------------------------|------------------------|\n| tiny | ~0.32 | ~0.01 |\n| base | ~0.16 | ~0.01 |\n| turbo | ~0.08 | ~0.01 |\n| large | ~1.0 | ~0.05 |\n\n*Real-time factor: 0.1 = 10× faster than real-time*\n\n## Language support\n\nTop-supported languages:\n- English (en)\n- Spanish (es)\n- French (fr)\n- German (de)\n- Italian (it)\n- Portuguese (pt)\n- Russian (ru)\n- Japanese (ja)\n- Korean (ko)\n- Chinese (zh)\n\nFull list: 99 languages total\n\n## Limitations\n\n1. **Hallucinations** - May repeat or invent text\n2. **Long-form accuracy** - Degrades on >30 min audio\n3. **Speaker identification** - No diarization\n4. **Accents** - Quality varies\n5. **Background noise** - Can affect accuracy\n6. **Real-time latency** - Not suitable for live captioning\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper ⭐ 72,900+\n- **Paper**: https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.04356\n- **Model Card**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper\u002Fblob\u002Fmain\u002Fmodel-card.md\n- **Colab**: Available in repo\n- **License**: MIT\n\n\n","# Whisper - Robust Speech Recognition\n\nOpenAI's multilingual speech recognition model.\n\n## When to use Whisper\n\n**Use when:**\n- Speech-to-text transcription (99 languages)\n- Podcast\u002Fvideo transcription\n- Meeting notes automation\n- Translation to English\n- Noisy audio transcription\n- Multilingual audio processing\n\n**Metrics**:\n- **72,900+ GitHub stars**\n- 99 languages supported\n- Trained on 680,000 hours of audio\n- MIT License\n\n**Use alternatives instead**:\n- **AssemblyAI**: Managed API, speaker diarization\n- **Deepgram**: Real-time streaming ASR\n- **Google Speech-to-Text**: Cloud-based\n\n## Quick start\n\n### Installation\n\n```bash\n# Requires Python 3.8-3.11\npip install -U openai-whisper\n\n# Requires ffmpeg\n# macOS: brew install ffmpeg\n# Ubuntu: sudo apt install ffmpeg\n# Windows: choco install ffmpeg\n```\n\n### Basic transcription\n\n```python\nimport whisper\n\n# Load model\nmodel = whisper.load_model(\"base\")\n\n# Transcribe\nresult = model.transcribe(\"audio.mp3\")\n\n# Print text\nprint(result[\"text\"])\n\n# Access segments\nfor segment in result[\"segments\"]:\n    print(f\"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}\")\n```\n\n## Model sizes\n\n```python\n# Available models\nmodels = [\"tiny\", \"base\", \"small\", \"medium\", \"large\", \"turbo\"]\n\n# Load specific model\nmodel = whisper.load_model(\"turbo\")  # Fastest, good quality\n```\n\n| Model | Parameters | English-only | Multilingual | Speed | VRAM |\n|-------|------------|--------------|--------------|-------|------|\n| tiny | 39M | ✓ | ✓ | ~32x | ~1 GB |\n| base | 74M | ✓ | ✓ | ~16x | ~1 GB |\n| small | 244M | ✓ | ✓ | ~6x | ~2 GB |\n| medium | 769M | ✓ | ✓ | ~2x | ~5 GB |\n| large | 1550M | ✗ | ✓ | 1x | ~10 GB |\n| turbo | 809M | ✗ | ✓ | ~8x | ~6 GB |\n\n**Recommendation**: Use `turbo` for best speed\u002Fquality, `base` for prototyping\n\n## Transcription options\n\n### Language specification\n\n```python\n# Auto-detect language\nresult = model.transcribe(\"audio.mp3\")\n\n# Specify language (faster)\nresult = model.transcribe(\"audio.mp3\", language=\"en\")\n\n# Supported: en, es, fr, de, it, pt, ru, ja, ko, zh, and 89 more\n```\n\n### Task selection\n\n```python\n# Transcription (default)\nresult = model.transcribe(\"audio.mp3\", task=\"transcribe\")\n\n# Translation to English\nresult = model.transcribe(\"spanish.mp3\", task=\"translate\")\n# Input: Spanish audio → Output: English text\n```\n\n### Initial prompt\n\n```python\n# Improve accuracy with context\nresult = model.transcribe(\n    \"audio.mp3\",\n    initial_prompt=\"This is a technical podcast about machine learning and AI.\"\n)\n\n# Helps with:\n# - Technical terms\n# - Proper nouns\n# - Domain-specific vocabulary\n```\n\n### Timestamps\n\n```python\n# Word-level timestamps\nresult = model.transcribe(\"audio.mp3\", word_timestamps=True)\n\nfor segment in result[\"segments\"]:\n    for word in segment[\"words\"]:\n        print(f\"{word['word']} ({word['start']:.2f}s - {word['end']:.2f}s)\")\n```\n\n### Temperature fallback\n\n```python\n# Retry with different temperatures if confidence low\nresult = model.transcribe(\n    \"audio.mp3\",\n    temperature=(0.0, 0.2, 0.4, 0.6, 0.8, 1.0)\n)\n```\n\n## Command line usage\n\n```bash\n# Basic transcription\nwhisper audio.mp3\n\n# Specify model\nwhisper audio.mp3 --model turbo\n\n# Output formats\nwhisper audio.mp3 --output_format txt     # Plain text\nwhisper audio.mp3 --output_format srt     # Subtitles\nwhisper audio.mp3 --output_format vtt     # WebVTT\nwhisper audio.mp3 --output_format json    # JSON with timestamps\n\n# Language\nwhisper audio.mp3 --language Spanish\n\n# Translation\nwhisper spanish.mp3 --task translate\n```\n\n## Batch processing\n\n```python\nimport os\n\naudio_files = [\"file1.mp3\", \"file2.mp3\", \"file3.mp3\"]\n\nfor audio_file in audio_files:\n    print(f\"Transcribing {audio_file}...\")\n    result = model.transcribe(audio_file)\n\n    # Save to file\n    output_file = audio_file.replace(\".mp3\", \".txt\")\n    with open(output_file, \"w\") as f:\n        f.write(result[\"text\"])\n```\n\n## Real-time transcription\n\n```python\n# For streaming audio, use faster-whisper\n# pip install faster-whisper\n\nfrom faster_whisper import WhisperModel\n\nmodel = WhisperModel(\"base\", device=\"cuda\", compute_type=\"float16\")\n\n# Transcribe with streaming\nsegments, info = model.transcribe(\"audio.mp3\", beam_size=5)\n\nfor segment in segments:\n    print(f\"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}\")\n```\n\n## GPU acceleration\n\n```python\nimport whisper\n\n# Automatically uses GPU if available\nmodel = whisper.load_model(\"turbo\")\n\n# Force CPU\nmodel = whisper.load_model(\"turbo\", device=\"cpu\")\n\n# Force GPU\nmodel = whisper.load_model(\"turbo\", device=\"cuda\")\n\n# 10-20× faster on GPU\n```\n\n## Integration with other tools\n\n### Subtitle generation\n\n```bash\n# Generate SRT subtitles\nwhisper video.mp4 --output_format srt --language English\n\n# Output: video.srt\n```\n\n### With LangChain\n\n```python\nfrom langchain.document_loaders import WhisperTranscriptionLoader\n\nloader = WhisperTranscriptionLoader(file_path=\"audio.mp3\")\ndocs = loader.load()\n\n# Use transcription in RAG\nfrom langchain_chroma import Chroma\nfrom langchain_openai import OpenAIEmbeddings\n\nvectorstore = Chroma.from_documents(docs, OpenAIEmbeddings())\n```\n\n### Extract audio from video\n\n```bash\n# Use ffmpeg to extract audio\nffmpeg -i video.mp4 -vn -acodec pcm_s16le audio.wav\n\n# Then transcribe\nwhisper audio.wav\n```\n\n## Best practices\n\n1. **Use turbo model** - Best speed\u002Fquality for English\n2. **Specify language** - Faster than auto-detect\n3. **Add initial prompt** - Improves technical terms\n4. **Use GPU** - 10-20× faster\n5. **Batch process** - More efficient\n6. **Convert to WAV** - Better compatibility\n7. **Split long audio** - \u003C30 min chunks\n8. **Check language support** - Quality varies by language\n9. **Use faster-whisper** - 4× faster than openai-whisper\n10. **Monitor VRAM** - Scale model size to hardware\n\n## Performance\n\n| Model | Real-time factor (CPU) | Real-time factor (GPU) |\n|-------|------------------------|------------------------|\n| tiny | ~0.32 | ~0.01 |\n| base | ~0.16 | ~0.01 |\n| turbo | ~0.08 | ~0.01 |\n| large | ~1.0 | ~0.05 |\n\n*Real-time factor: 0.1 = 10× faster than real-time*\n\n## Language support\n\nTop-supported languages:\n- English (en)\n- Spanish (es)\n- French (fr)\n- German (de)\n- Italian (it)\n- Portuguese (pt)\n- Russian (ru)\n- Japanese (ja)\n- Korean (ko)\n- Chinese (zh)\n\nFull list: 99 languages total\n\n## Limitations\n\n1. **Hallucinations** - May repeat or invent text\n2. **Long-form accuracy** - Degrades on >30 min audio\n3. **Speaker identification** - No diarization\n4. **Accents** - Quality varies\n5. **Background noise** - Can affect accuracy\n6. **Real-time latency** - Not suitable for live captioning\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper ⭐ 72,900+\n- **Paper**: https:\u002F\u002Farxiv.org\u002Fabs\u002F2212.04356\n- **Model Card**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper\u002Fblob\u002Fmain\u002Fmodel-card.md\n- **Colab**: Available in repo\n- **License**: MIT\n\n\n",{"name":5,"license":15,"metadata":53,"description":7},{"tags":54,"author":63,"version":64,"dependencies":65},[55,56,44,57,58,59,60,61,62,33],"Whisper","Speech Recognition","Multimodal","Multilingual","OpenAI","Speech-To-Text","Transcription","Translation","Orchestra Research","1.0.0",[66,67,68],"openai-whisper","transformers","torch","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fmultimodal-whisper",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":80,"prompt":90,"zipAvailable":91},[81,84,87],{"tool":82,"command":83},"npx","npx skills add davila7\u002Fclaude-code-templates --skill multimodal-whisper",{"tool":85,"command":86},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill multimodal-whisper",{"tool":88,"command":89},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill multimodal-whisper","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fmultimodal-whisper\u002FSKILL.md",true,[93],{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Flanguages.md","REFERENCE","参考文档",4786,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Fmultimodal-whisper\u002Freferences\u002Flanguages.md",[100,127,154,187,222,246],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":48},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[106],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[108,109,110,111,112,31,113,114,115,116,117,118,119,120,121,122,123,124,125,126],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":48},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[133],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137,138,139,140,141,142,143,144,145,116,146,147,148,149,150,151,152,153],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":169,"publishedAt":48},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[160,163,164],{"categoryNo":161,"categoryName":162,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":165,"categoryName":166,"taxonomyType":167,"taxonomyTypeDesc":168},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[170,171,172,173,174,175,176,31,177,178,179,180,181,182,183,115,184,185,116,186],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":191,"licenseFileUrl":192,"sourceHtmlUrl":193,"categories":194,"keywords":198,"publishedAt":48},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[195],{"categoryNo":196,"categoryName":197,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,31,221],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":191,"licenseFileUrl":226,"sourceHtmlUrl":227,"categories":228,"keywords":233,"publishedAt":48},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[229,232],{"categoryNo":230,"categoryName":231,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":196,"categoryName":197,"taxonomyType":21,"taxonomyTypeDesc":22},[234,235,236,237,238,200,239,209,210,240,241,242,243,31,244,118,245],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":247,"name":248,"nameZh":6,"description":249,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":191,"licenseFileUrl":250,"sourceHtmlUrl":251,"categories":252,"keywords":260,"publishedAt":48},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[253,256,257],{"categoryNo":254,"categoryName":255,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":258,"categoryName":259,"taxonomyType":167,"taxonomyTypeDesc":168},"01JBSEEDCAT000000000000036","内容创作者",[261,262,263,264,265,266,267,268,202,269,212,146,270,271,272,273,274,182,275,116,276,277,278,279,280,124,281],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]