[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HCS8AJ1YVVT9XMR76VF99":3,"skill-same:01M71HCS8AJ1YVVT9XMR76VF99":66},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M71HCS8AJ1YVVT9XMR76VF99","segment-image",null,"This skill should be used when the user asks to \"segment an image\", \"identify objects\", \"extract objects\", \"generate masks\", \"find objects in image\", or needs AI-powered image segmentation.","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--segment-image\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],"segment","segment image","image","segmentation","generate","find","objects","when","Image Segmentation","extract","user","2026-11-10 10:12:30",false,"---\nname: segment-image\ndescription: This skill should be used when the user asks to \"segment an image\", \"identify objects\", \"extract objects\", \"generate masks\", \"find objects in image\", or needs AI-powered image segmentation.\n---\n\n# Segment Image\n\nSegment and identify objects in images using Gemini's vision capabilities.\n\n## When to Use\n\nUse this skill when the user asks to:\n- Identify objects in an image\n- Generate masks for specific objects\n- Segment an image into regions\n- Extract objects from an image\n\n## Usage\n\n```bash\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts \u003Cinput-image> [options]\n```\n\n### Options\n\n- `--prompt \u003Ctext>` - Custom segmentation prompt\n- `--output \u003Cdir>` - Output directory for mask files\n\n### Examples\n\n```bash\n# Segment all objects\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts photo.jpg\n\n# Segment with custom prompt\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts photo.jpg --prompt \"identify all people and vehicles\"\n\n# Save masks to directory\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts photo.jpg --output .\u002Fmasks\n```\n\n## Context Discipline\n\n**Do not read generated mask images back into context.** The script outputs file paths. Ask the user to visually inspect the masks. To inspect programmatically, optimize the images first (via the optimize-images skill).\n\n## Model\n\nUses `gemini-3-flash-preview` (Gemini 3 Flash) for image segmentation.\n\n> Last verified: February 2026. If a newer generation exists, STOP and suggest a PR to `b-open-io\u002Fgemskills`. See the ask-gemini skill's `references\u002Fgemini-api.md` for current models and Google's official `gemini-api-dev` skill for the canonical source.\n","# Segment Image\n\nSegment and identify objects in images using Gemini's vision capabilities.\n\n## When to Use\n\nUse this skill when the user asks to:\n- Identify objects in an image\n- Generate masks for specific objects\n- Segment an image into regions\n- Extract objects from an image\n\n## Usage\n\n```bash\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts \u003Cinput-image> [options]\n```\n\n### Options\n\n- `--prompt \u003Ctext>` - Custom segmentation prompt\n- `--output \u003Cdir>` - Output directory for mask files\n\n### Examples\n\n```bash\n# Segment all objects\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts photo.jpg\n\n# Segment with custom prompt\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts photo.jpg --prompt \"identify all people and vehicles\"\n\n# Save masks to directory\nbun run ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fsegment-image\u002Fscripts\u002Fsegment.ts photo.jpg --output .\u002Fmasks\n```\n\n## Context Discipline\n\n**Do not read generated mask images back into context.** The script outputs file paths. Ask the user to visually inspect the masks. To inspect programmatically, optimize the images first (via the optimize-images skill).\n\n## Model\n\nUses `gemini-3-flash-preview` (Gemini 3 Flash) for image segmentation.\n\n> Last verified: February 2026. If a newer generation exists, STOP and suggest a PR to `b-open-io\u002Fgemskills`. See the ask-gemini skill's `references\u002Fgemini-api.md` for current models and Google's official `gemini-api-dev` skill for the canonical source.\n",{"name":5,"description":7},"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--segment-image",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add JSGforever\u002Fskillguard --skill segment-image",{"tool":52,"command":53},"bunx","bunx skills add JSGforever\u002Fskillguard --skill segment-image",{"tool":55,"command":56},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill segment-image","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--segment-image\u002FSKILL.md",true,[60],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fsegment.ts","SCRIPT","脚本",3144,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__b-open-io--segment-image\u002Fscripts\u002Fsegment.ts",[67,96,112,139,161,182],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":76,"publishedAt":34},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[77,78,79,80,81,82,83,84,85,86,87,88,30,89,90,91,92,93,94,95],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":100,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":108,"publishedAt":34},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[109,110,111],"data","data exfiltrator","files",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":34},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":148,"publishedAt":34},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[128,149,136,137,150,151,152,153,154,155,119,156,157,132,134,158,135,138,159,160],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":34},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[167],{"categoryNo":146,"categoryName":147,"taxonomyType":20,"taxonomyTypeDesc":21},[169,138,170,171,172,173,128,119,174,175,176,134,135,136,177,137,178,179,180,181],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":195,"publishedAt":34},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[188,191,194],{"categoryNo":189,"categoryName":190,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":192,"categoryName":193,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":74,"categoryName":75,"taxonomyType":20,"taxonomyTypeDesc":21},[196,197,198,199,200,201,202,126,154,203,204,205,135,160,206,181,207,208,209,210],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]