[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XCSDR7R5RKB4Q1MVZVZQHG":3,"skill-same:01M6XCSDR7R5RKB4Q1MVZVZQHG":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":48,"commitSha":49,"skillDirectory":50,"forksCount":13,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6XCSDR7R5RKB4Q1MVZVZQHG","auto-skill-generator",null,"Generate skills from web research. Given a topic like \"how to use Stripe API\" or \"Prisma ORM\", this skill searches for authoritative documentation, crawls the best source, and generates a ready-to-use .md skill file. Use when: (1) User wants to create a skill about a library\u002Ftool\u002FAPI, (2) User says \"create a skill for X\", \"make a skill about X\", or \"generate skill for X\", (3) User wants to capture documentation as a reusable skill.","Waaaalnut\u002Fskillsbench","Waaaalnut","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F103995656?v=4","01M6XCS9K1V51EY3JMB7DGMX24","01M6XCS9Q4WPW88W62C55G1H44",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdocs-to-skill\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],"skill generator","auto skill generator","generator","auto","api","tool","orm","use","file","ready","research","reusable","prisma","as","how to","create","prisma orm","for","when","documentation","2026-11-10 10:12:30",false,"---\nname: auto-skill-generator\ndescription: >\n  Generate skills from web research. Given a topic like \"how to use Stripe API\"\n  or \"Prisma ORM\", this skill searches for authoritative documentation, crawls the best source,\n  and generates a ready-to-use .md skill file. Use when: (1) User wants to create a skill\n  about a library\u002Ftool\u002FAPI, (2) User says \"create a skill for X\", \"make a skill about X\",\n  or \"generate skill for X\", (3) User wants to capture documentation as a reusable skill.\n---\n\n# Auto Skill Generator\n\nGenerate skills by researching and crawling authoritative documentation.\n\n## Tool: fetch_docs.py\n\n```bash\n# Search - returns all URLs with snippets\npython scripts\u002Ffetch_docs.py search \"Modal GPU Python documentation\"\n\n# Crawl - with domain\u002Fpath filtering to stay focused\npython scripts\u002Ffetch_docs.py crawl \\\n  --url https:\u002F\u002Fmodal.com\u002Fdocs\u002Fguide\u002Fgpu \\\n  --no-external \\\n  --select-paths \"\u002Fdocs\u002F.*\" \\\n  --instructions \"Focus on GPU setup and code examples\" \\\n  --limit 30\n```\n\n## Workflow\n\n### 1. Search for Documentation\n\n```bash\npython scripts\u002Ffetch_docs.py search \"{topic} documentation\"\n```\n\nReturns JSON with all URLs, titles, scores, and content snippets.\n\n### 2. Select Best URL\n\nReview search results and select based on:\n- **Official docs**: `*.com\u002Fdocs\u002F`, `docs.*.com`, `*.readthedocs.io`\n- **Content relevance**: Check snippets for API docs, code examples\n- **Avoid**: Blog posts, changelogs, marketing, glossaries\n\n### 3. Crawl with Filtering\n\n```bash\npython scripts\u002Ffetch_docs.py crawl \\\n  --url {selected_url} \\\n  --no-external \\\n  --select-paths \"\u002Fdocs\u002F.*\" \"\u002Fguide\u002F.*\" \\\n  --instructions \"Focus on API methods and code examples\"\n```\n\n**Core Parameters:**\n| Parameter | Description |\n|-----------|-------------|\n| `--url` | Required. URL to crawl |\n| `--instructions` | Natural language guidance for crawler |\n| `--limit` | Total pages (default: 50) |\n| `--max-depth` | Link depth (default: 2) |\n\n**Domain\u002FPath Filtering (Critical):**\n| Parameter | Description |\n|-----------|-------------|\n| `--no-external` | Block external domains |\n| `--select-paths` | Regex patterns to include (e.g., `\u002Fdocs\u002F.*`) |\n| `--exclude-paths` | Regex patterns to exclude (e.g., `\u002Fblog\u002F.*`) |\n| `--select-domains` | Regex for allowed domains |\n| `--exclude-domains` | Regex for blocked domains |\n\n**Quality Options:**\n| Parameter | Description |\n|-----------|-------------|\n| `--extract-depth` | `basic` (1 credit\u002F5 URLs) or `advanced` (2 credits\u002F5 URLs) |\n| `--format` | `markdown` or `text` |\n| `--timeout` | Seconds (10-150, default: 150) |\n\n### 4. Generate Skill File\n\nFrom crawled content, create:\n\n```markdown\n---\nname: {topic-slug}ß\ndescription: >\n  {What the skill does}. Use when: {specific triggers}.\n---\n\n# {Topic Name}\n\n## Quick Start\n## Core API\n## Common Patterns\n```\n\n## Output\n\n- Location: `~\u002F.claude\u002Fskills\u002F{topic-slug}\u002FSKILL.md`\n- Extract ALL code blocks from crawled content\n- Keep SKILL.md under 500 lines; split to `references\u002F` if longer\n","# Auto Skill Generator\n\nGenerate skills by researching and crawling authoritative documentation.\n\n## Tool: fetch_docs.py\n\n```bash\n# Search - returns all URLs with snippets\npython scripts\u002Ffetch_docs.py search \"Modal GPU Python documentation\"\n\n# Crawl - with domain\u002Fpath filtering to stay focused\npython scripts\u002Ffetch_docs.py crawl \\\n  --url https:\u002F\u002Fmodal.com\u002Fdocs\u002Fguide\u002Fgpu \\\n  --no-external \\\n  --select-paths \"\u002Fdocs\u002F.*\" \\\n  --instructions \"Focus on GPU setup and code examples\" \\\n  --limit 30\n```\n\n## Workflow\n\n### 1. Search for Documentation\n\n```bash\npython scripts\u002Ffetch_docs.py search \"{topic} documentation\"\n```\n\nReturns JSON with all URLs, titles, scores, and content snippets.\n\n### 2. Select Best URL\n\nReview search results and select based on:\n- **Official docs**: `*.com\u002Fdocs\u002F`, `docs.*.com`, `*.readthedocs.io`\n- **Content relevance**: Check snippets for API docs, code examples\n- **Avoid**: Blog posts, changelogs, marketing, glossaries\n\n### 3. Crawl with Filtering\n\n```bash\npython scripts\u002Ffetch_docs.py crawl \\\n  --url {selected_url} \\\n  --no-external \\\n  --select-paths \"\u002Fdocs\u002F.*\" \"\u002Fguide\u002F.*\" \\\n  --instructions \"Focus on API methods and code examples\"\n```\n\n**Core Parameters:**\n| Parameter | Description |\n|-----------|-------------|\n| `--url` | Required. URL to crawl |\n| `--instructions` | Natural language guidance for crawler |\n| `--limit` | Total pages (default: 50) |\n| `--max-depth` | Link depth (default: 2) |\n\n**Domain\u002FPath Filtering (Critical):**\n| Parameter | Description |\n|-----------|-------------|\n| `--no-external` | Block external domains |\n| `--select-paths` | Regex patterns to include (e.g., `\u002Fdocs\u002F.*`) |\n| `--exclude-paths` | Regex patterns to exclude (e.g., `\u002Fblog\u002F.*`) |\n| `--select-domains` | Regex for allowed domains |\n| `--exclude-domains` | Regex for blocked domains |\n\n**Quality Options:**\n| Parameter | Description |\n|-----------|-------------|\n| `--extract-depth` | `basic` (1 credit\u002F5 URLs) or `advanced` (2 credits\u002F5 URLs) |\n| `--format` | `markdown` or `text` |\n| `--timeout` | Seconds (10-150, default: 150) |\n\n### 4. Generate Skill File\n\nFrom crawled content, create:\n\n```markdown\n---\nname: {topic-slug}ß\ndescription: >\n  {What the skill does}. Use when: {specific triggers}.\n---\n\n# {Topic Name}\n\n## Quick Start\n## Core API\n## Common Patterns\n```\n\n## Output\n\n- Location: `~\u002F.claude\u002Fskills\u002F{topic-slug}\u002FSKILL.md`\n- Extract ALL code blocks from crawled content\n- Keep SKILL.md under 500 lines; split to `references\u002F` if longer\n",{"name":5,"description":7},"main","7eeb258ada72b7f58119b0e7a2c00ea89d9beedd",".claude\u002Fskills\u002Fdocs-to-skill","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench","https:\u002F\u002Fgithub.com\u002FWaaaalnut","student of Zhejiang University","2026-04-21 23:16:23",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Waaaalnut\u002Fskillsbench --skill auto-skill-generator",{"tool":61,"command":62},"bunx","bunx skills add Waaaalnut\u002Fskillsbench --skill auto-skill-generator",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Waaaalnut\u002Fskillsbench --skill auto-skill-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdocs-to-skill\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Ffetch_docs.py","SCRIPT","脚本",5939,"https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdocs-to-skill\u002Fscripts\u002Ffetch_docs.py",[76,90,105,128,150,168],{"skillNo":77,"name":78,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":86,"publishedAt":43},"01M6XEWMJ6VY3ZC53MPDCPG3GH","data-reconciliation","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fxlsx-recover-data\u002Fenvironment\u002Fskills\u002Fdata-reconciliation\u002FSKILL.md",[81],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[87,88,89],"data reconciliation","reconciliation","data",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":43},"01M6XEW8MNPMF1KRXV6ATGFRQF","speech-to-text","Transcribe video to timestamped text using Whisper tiny model (pre-installed).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-tutorial-indexer\u002Fenvironment\u002Fskills\u002Fspeech-to-text\u002FSKILL.md",[],[97,98,99,100,101,102,103,104],"speech","text","speech to text","transcribe video","whisper","model","Video","transcribe",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":114,"publishedAt":43},"01M6XEW3FQZP0T1RKQQJFXVY9T","video-processor","Process videos by removing segments and concatenating remaining parts. Use when you need to remove detected pauses\u002Fopenings from videos, create highlight reels, or batch process segment removals using ffmpeg filter_complex.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fvideo-processor\u002FSKILL.md",[111],{"categoryNo":112,"categoryName":113,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[103,115,116,117,38,118,41,119,120,121,122,123,124,125,126,30,127],"processor","video processor","batch","reels","parts","segments","process","videos","you","segment","filter","ffmpeg","remove",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":43},"01M6XEVXJ5KZ0NTY3XZKRY4AS1","silence-detector","Detect initial silence segments in audio\u002Fvideo using energy-based analysis. Use when you need to find low-energy periods at the start of recordings (title slides, setup time, pre-roll silence).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsilence-detector\u002FSKILL.md",[134],{"categoryNo":112,"categoryName":113,"taxonomyType":20,"taxonomyTypeDesc":21},[136,137,138,139,41,123,140,141,142,143,144,120,145,146,103,147,148,149,30],"detector","silence detector","title","slides","time","energy","at","recordings","detect","find","Audio","analysis","start","setup",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":43},"01M6XEVT3NGRN1FT7JPMAPXS6M","segment-combiner","Combine multiple segment detection results into a unified list. Use when you need to merge segments from different detectors, prepare removal lists for video processing, or consolidate detection outputs.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsegment-combiner\u002FSKILL.md",[],[124,157,103,158,159,160,161,40,41,162,163,120,123,164,165,30,166,167],"segment combiner","detection","prepare","merge","video processing","outputs","combine","processing","consolidate","results","list",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":177,"publishedAt":43},"01M6XEVMPVASGS2KX86QK4FMT7","report-generator","Generate compression reports for video processing. Use when you need to create structured JSON reports with duration statistics, compression ratios, and segment details after video processing.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Freport-generator\u002FSKILL.md",[174],{"categoryNo":175,"categoryName":176,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000034","行政与办公人员",[25,178,179,124,41,40,123,180,164,181,182,183,30,161,184,103,185,186,38],"report generator","report","with","statistics","structured","reports","json","compression","generate"]