[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XCSV50KD41EZVGEYCGVPRF":3,"skill-same:01M6XCSV50KD41EZVGEYCGVPRF":62},{"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":17,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":13,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M6XCSV50KD41EZVGEYCGVPRF","skillsbench",null,"SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.","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\u002Fskillsbench\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28,29],"workflow","tasks","benchmark","repo","use","task","structure","contribution","for","prs","submission","when","2026-11-10 10:12:30",false,"---\nname: skillsbench\ndescription: \"SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.\"\n---\n\n# SkillsBench\n\nBenchmark evaluating how well AI agents use skills.\n\n## Official Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fbenchflow-ai\u002Fskillsbench\n- **Harbor Docs**: https:\u002F\u002Fharborframework.com\u002Fdocs\n- **Terminal-Bench Task Guide**: https:\u002F\u002Fwww.tbench.ai\u002Fdocs\u002Ftask-quickstart\n\n## Repo Structure\n\n```\ntasks\u002F\u003Ctask-id>\u002F          # Benchmark tasks\n.claude\u002Fskills\u002F           # Contributor skills (harbor, skill-creator)\nCONTRIBUTING.md           # Full contribution guide\n```\n\n## Local Workspace & API Keys\n\n- **`.local-workspace\u002F`** - Git-ignored directory for cloning PRs, temporary files, external repos, etc.\n- **`.local-workspace\u002F.env`** - May contain `ANTHROPIC_API_KEY` and other API credentials. Check and use when running harbor with API access.\n\n## Quick Workflow\n\n```bash\n# 1. Install harbor and initialize a task\nuv tool install harbor\nharbor tasks init tasks\u002F\u003Ctask-name>\n\n# 2. Write files (see harbor skill for templates)\n\n# 3. Validate\nharbor tasks check tasks\u002Fmy-task\nharbor run -p tasks\u002Fmy-task -a oracle  # Must pass 100%\n\n# 4. Test with agent\n# you can test agents with your claude code\u002Fcursor\u002Fcodex\u002Fvscode\u002FGitHub copilot subscriptions, etc.\n# you can also trigger harbor run with your own API keys.\n# for PR we only need some idea of how sota level models and agents perform on the task with and without skills.\nharbor run -p tasks\u002Fmy-task -a claude-code -m 'anthropic\u002Fclaude-opus-4-5'\n\n# 5. Submit PR\n# please see our PR template for more details.\n```\n\n## Task Requirements\n\n- Things people actually do\n- Agent should be more performant with skills than without skills.\n- task.toml and solve.sh must be human-authored\n- Prioritize verifiable tasks. LLM-as-judge or agent-as-a-judge is not priority right now. But we are open to these ideas and will brainstorm if we can make these tasks easier to verify.\n\n## References\n\n- Full guide: [CONTRIBUTING.md](..\u002F..\u002F..\u002F..\u002FCONTRIBUTING.md)\n- Harbor commands: See harbor skill\n- Task ideas: [references\u002Ftask-ideas.md](references\u002Ftask-ideas.md)\n","# SkillsBench\n\nBenchmark evaluating how well AI agents use skills.\n\n## Official Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fbenchflow-ai\u002Fskillsbench\n- **Harbor Docs**: https:\u002F\u002Fharborframework.com\u002Fdocs\n- **Terminal-Bench Task Guide**: https:\u002F\u002Fwww.tbench.ai\u002Fdocs\u002Ftask-quickstart\n\n## Repo Structure\n\n```\ntasks\u002F\u003Ctask-id>\u002F          # Benchmark tasks\n.claude\u002Fskills\u002F           # Contributor skills (harbor, skill-creator)\nCONTRIBUTING.md           # Full contribution guide\n```\n\n## Local Workspace & API Keys\n\n- **`.local-workspace\u002F`** - Git-ignored directory for cloning PRs, temporary files, external repos, etc.\n- **`.local-workspace\u002F.env`** - May contain `ANTHROPIC_API_KEY` and other API credentials. Check and use when running harbor with API access.\n\n## Quick Workflow\n\n```bash\n# 1. Install harbor and initialize a task\nuv tool install harbor\nharbor tasks init tasks\u002F\u003Ctask-name>\n\n# 2. Write files (see harbor skill for templates)\n\n# 3. Validate\nharbor tasks check tasks\u002Fmy-task\nharbor run -p tasks\u002Fmy-task -a oracle  # Must pass 100%\n\n# 4. Test with agent\n# you can test agents with your claude code\u002Fcursor\u002Fcodex\u002Fvscode\u002FGitHub copilot subscriptions, etc.\n# you can also trigger harbor run with your own API keys.\n# for PR we only need some idea of how sota level models and agents perform on the task with and without skills.\nharbor run -p tasks\u002Fmy-task -a claude-code -m 'anthropic\u002Fclaude-opus-4-5'\n\n# 5. Submit PR\n# please see our PR template for more details.\n```\n\n## Task Requirements\n\n- Things people actually do\n- Agent should be more performant with skills than without skills.\n- task.toml and solve.sh must be human-authored\n- Prioritize verifiable tasks. LLM-as-judge or agent-as-a-judge is not priority right now. But we are open to these ideas and will brainstorm if we can make these tasks easier to verify.\n\n## References\n\n- Full guide: [CONTRIBUTING.md](..\u002F..\u002F..\u002F..\u002FCONTRIBUTING.md)\n- Harbor commands: See harbor skill\n- Task ideas: [references\u002Ftask-ideas.md](references\u002Ftask-ideas.md)\n",{"name":5,"description":7},"main","7eeb258ada72b7f58119b0e7a2c00ea89d9beedd",".claude\u002Fskills\u002Fskillsbench","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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add Waaaalnut\u002Fskillsbench --skill skillsbench",{"tool":48,"command":49},"bunx","bunx skills add Waaaalnut\u002Fskillsbench --skill skillsbench",{"tool":51,"command":52},"pnpm","pnpm dlx skills add Waaaalnut\u002Fskillsbench --skill skillsbench","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskillsbench\u002FSKILL.md",true,[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftask-ideas.md","REFERENCE","参考文档",23118,"https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskillsbench\u002Freferences\u002Ftask-ideas.md",[63,77,92,118,140,158],{"skillNo":64,"name":65,"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":66,"categories":67,"keywords":73,"publishedAt":30},"01M6XEWMJ6VY3ZC53MPDCPG3GH","data-reconciliation","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fxlsx-recover-data\u002Fenvironment\u002Fskills\u002Fdata-reconciliation\u002FSKILL.md",[68],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[74,75,76],"data reconciliation","reconciliation","data",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":30},"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",[],[84,85,86,87,88,89,90,91],"speech","text","speech to text","transcribe video","whisper","model","Video","transcribe",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":30},"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",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[90,104,105,106,107,108,29,109,110,111,112,113,114,115,116,22,117],"processor","video processor","batch","create","reels","parts","segments","process","videos","you","segment","filter","ffmpeg","remove",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":125,"publishedAt":30},"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",[124],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[126,127,128,129,29,113,130,131,132,133,134,110,135,136,90,137,138,139,22],"detector","silence detector","title","slides","time","energy","at","recordings","detect","find","Audio","analysis","start","setup",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":30},"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",[],[114,147,90,148,149,150,151,26,29,152,153,110,113,154,155,22,156,157],"segment combiner","detection","prepare","merge","video processing","outputs","combine","processing","consolidate","results","list",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":167,"publishedAt":30},"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",[164],{"categoryNo":165,"categoryName":166,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000034","行政与办公人员",[168,169,170,114,29,26,113,171,154,172,173,174,22,151,175,90,176,177,107],"generator","report generator","report","with","statistics","structured","reports","json","compression","generate"]