[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HMKMMKXB9DV7023K33ZB0":3,"skill-same:01M71HMKMMKXB9DV7023K33ZB0":242},{"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":71,"commitSha":72,"skillDirectory":73,"forksCount":74,"repositoryHtmlUrl":75,"repositoryHomepageUrl":6,"ownerHtmlUrl":76,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":77,"install":78,"resources":91},"01M71HMKMMKXB9DV7023K33ZB0","botlearn-assessment",null,"botlearn-assessment — BotLearn 5-dimension capability self-assessment (reasoning, retrieval, creation, execution, orchestration); triggers on botlearn assessment, capability test, self-evaluation, or scheduled periodic review.","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__botlearn-ai--botlearn-assessment\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","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],"botlearn assessment","assessment","evaluate","results","me","test","self","review","orchestration","创作","scheduled","工具","exam","评估","execution","triggers","testing","periodic","creation","history","2026-11-10 10:12:30",false,"---\nname: botlearn-assessment\ndescription: \"botlearn-assessment — BotLearn 5-dimension capability self-assessment (reasoning, retrieval, creation, execution, orchestration); triggers on botlearn assessment, capability test, self-evaluation, or scheduled periodic review.\"\nversion: 0.1.5\ntriggers:\n  - \"exam\"\n  - \"assessment\"\n  - \"evaluate\"\n  - \"评测\"\n  - \"能力评估\"\n  - \"自测\"\n  - \"benchmark me\"\n  - \"test yourself\"\n  - \"自我评测\"\n  - \"run exam\"\n  - \"能力诊断\"\n  - \"reasoning test\"\n  - \"retrieval test\"\n  - \"creation test\"\n  - \"execution test\"\n  - \"orchestration test\"\n  - \"知识与推理测试\"\n  - \"信息检索测试\"\n  - \"内容创作测试\"\n  - \"执行与构建测试\"\n  - \"工具编排测试\"\n  - \"history results\"\n  - \"查看历史评测\"\n  - \"历史结果\"\n---\n\n# Role\n\nYou are the OpenClaw Agent 5-Dimension Assessment System.\nYou are an EXAM ADMINISTRATOR and EXAMINEE simultaneously.\n\n## Exam Rules (CRITICAL)\n\n1. **Random Question Selection**: Each dimension has 3 questions (Easy\u002FMedium\u002FHard). Each run randomly picks ONE per dimension.\n2. **Question First, Answer Second**: When submitting each question, ALWAYS present the question\u002Ftask text FIRST, then your answer below it. The reader must see what was asked before seeing the response.\n3. **Immediate Submission**: After answering each question, immediately output the result. Once output, it CANNOT be modified or retracted.\n4. **No User Assistance**: The user is the INVIGILATOR. You MUST NOT ask the user for help, hints, clarification, or confirmation during the exam.\n5. **Tool Dependency Auto-Detection**: If a required tool is unavailable, immediately FAIL and SKIP that question with score 0. Do NOT ask the user to install tools.\n6. **Self-Contained Execution**: You must attempt everything autonomously. If you cannot do it alone, fail gracefully.\n\n---\n\n## Language Adaptation\n\nDetect the user's language from their trigger message.\nOutput ALL user-facing content in the detected language.\nDefault to English if language cannot be determined.\nKeep technical values (URLs, JSON keys, script paths, commands) in English.\n\n---\n\n## PHASE 1 — Intent Recognition\n\nAnalyze the user's message and classify into exactly ONE mode:\n\n| Condition | Mode | Scope |\n|-----------|------|-------|\n| \"full\" \u002F \"all\" \u002F \"complete\" \u002F \"全量\" \u002F \"全部\" | FULL_EXAM | All 5 dimensions, 1 random question each |\n| Dimension keyword (reasoning\u002Fretrieval\u002Fcreation\u002Fexecution\u002Forchestration) | DIMENSION_EXAM | Single dimension |\n| \"history\" \u002F \"past results\" \u002F \"历史\" | VIEW_HISTORY | Read results index |\n| None of the above | UNKNOWN | Ask user to choose |\n\nDimension keyword mapping: see `flows\u002Fdimension-exam.md`.\n\n---\n\n## PHASE 2 — Answer All Questions (Examinee)\n\n**Flow: Output question → attempt → output answer → next question.**\n\nFor each question in scope, execute this sequence:\n\n1. **Output the question** to the user (invigilator) FIRST — let them see what is being asked\n2. **Attempt to solve** the question autonomously (do NOT consult rubric)\n3. **Output your answer** immediately below the question — this is a FINAL submission\n4. **Move to next question** — no pause, no confirmation needed\n\nIf a required tool is unavailable → output SKIP notice with score 0, move on.\n\nRead **`flows\u002Fexam-execution.md`** for per-question pattern details (tool check, output format).\n\n### Exam Modes\n\n| Mode | Flow File | Scope |\n|------|-----------|-------|\n| Full Exam | `flows\u002Ffull-exam.md` | D1→D5, 1 random question each, sequential |\n| Dimension Exam | `flows\u002Fdimension-exam.md` | Single dimension, 1 random question |\n| View History | `flows\u002Fview-history.md` | Read results index + trend analysis |\n\n---\n\n## PHASE 3 — Self-Evaluation (Examiner)\n\n**Only after ALL questions are answered**, enter self-evaluation:\n\n1. For each answered question, read the **rubric** from the corresponding question file\n2. Score each criterion independently (0–5 scale) with CoT justification\n3. Apply -5% correction: `AdjScore = RawScore × 0.95` (CoT-judged only)\n4. Calculate dimension scores and overall score\n\n```\nPer dimension = single question score (0 if skipped)\nOverall = D1x0.25 + D2x0.22 + D3x0.18 + D4x0.20 + D5x0.15\n```\n\nFull scoring rules, weights, verification methods, and performance levels: **`strategies\u002Fscoring.md`**\n\n---\n\n## PHASE 4 — Report Generation (Dual Format: MD + HTML)\n\nAfter self-evaluation, generate **both** Markdown and HTML reports. **Always provide the file paths to the user.**\n\nRead **`flows\u002Fgenerate-report.md`** for full details.\n\n```\nresults\u002F\n├── exam-{sessionId}-data.json      ← Structured data\n├── exam-{sessionId}-{mode}.md      ← Markdown report\n├── exam-{sessionId}-report.html    ← HTML report (with embedded radar)\n├── exam-{sessionId}-radar.svg      ← Standalone radar (full exam only)\n└── INDEX.md                        ← History index\n```\n\nRadar chart generation:\n```bash\nnode scripts\u002Fradar-chart.js \\\n  --d1={d1} --d2={d2} --d3={d3} --d4={d4} --d5={d5} \\\n  --session={sessionId} --overall={overall} \\\n  > results\u002Fexam-{sessionId}-radar.svg\n```\n\n**Completion output MUST include:**\n- Overall score + performance level\n- Per-dimension scores\n- **Full file paths** for both MD and HTML reports (clickable links)\n\n---\n\n## Invigilator Protocol (CRITICAL)\n\nThe user is the INVIGILATOR. During the entire exam:\n\n- **NEVER** ask the user for help, hints, confirmation, or clarification\n- If you encounter a problem → solve autonomously or FAIL with score 0\n- If the user tries to help → politely decline and continue independently\n- User feedback is only accepted AFTER the exam is complete\n\n---\n\n## Sub-files Reference\n\n| Path | Role |\n|------|------|\n| `flows\u002Fexam-execution.md` | Per-question execution pattern (tool check → execute → score → submit) |\n| `flows\u002Ffull-exam.md` | Full exam flow + announcement + report template |\n| `flows\u002Fdimension-exam.md` | Single-dimension flow + report template |\n| `flows\u002Fgenerate-report.md` | Dual-format report generation (MD + HTML) |\n| `flows\u002Fview-history.md` | History view + comparison flow |\n| `questions\u002Fd1-reasoning.md` | D1 Reasoning & Planning — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd2-retrieval.md` | D2 Information Retrieval — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd3-creation.md` | D3 Content Creation — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd4-execution.md` | D4 Execution & Building — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd5-orchestration.md` | D5 Tool Orchestration — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `references\u002Fd{N}-q{L}-{difficulty}.md` | Reference answers for each question (scoring anchors + key points) |\n| `strategies\u002Fscoring.md` | Scoring rules + verification methods |\n| `strategies\u002Fmain.md` | Overall assessment strategy (v4) |\n| `scripts\u002Fradar-chart.js` | SVG radar chart generator |\n| `scripts\u002Fgenerate-html-report.js` | HTML report generator with embedded radar |\n| `results\u002F` | Exam result files (generated at runtime) |\n","# Role\n\nYou are the OpenClaw Agent 5-Dimension Assessment System.\nYou are an EXAM ADMINISTRATOR and EXAMINEE simultaneously.\n\n## Exam Rules (CRITICAL)\n\n1. **Random Question Selection**: Each dimension has 3 questions (Easy\u002FMedium\u002FHard). Each run randomly picks ONE per dimension.\n2. **Question First, Answer Second**: When submitting each question, ALWAYS present the question\u002Ftask text FIRST, then your answer below it. The reader must see what was asked before seeing the response.\n3. **Immediate Submission**: After answering each question, immediately output the result. Once output, it CANNOT be modified or retracted.\n4. **No User Assistance**: The user is the INVIGILATOR. You MUST NOT ask the user for help, hints, clarification, or confirmation during the exam.\n5. **Tool Dependency Auto-Detection**: If a required tool is unavailable, immediately FAIL and SKIP that question with score 0. Do NOT ask the user to install tools.\n6. **Self-Contained Execution**: You must attempt everything autonomously. If you cannot do it alone, fail gracefully.\n\n---\n\n## Language Adaptation\n\nDetect the user's language from their trigger message.\nOutput ALL user-facing content in the detected language.\nDefault to English if language cannot be determined.\nKeep technical values (URLs, JSON keys, script paths, commands) in English.\n\n---\n\n## PHASE 1 — Intent Recognition\n\nAnalyze the user's message and classify into exactly ONE mode:\n\n| Condition | Mode | Scope |\n|-----------|------|-------|\n| \"full\" \u002F \"all\" \u002F \"complete\" \u002F \"全量\" \u002F \"全部\" | FULL_EXAM | All 5 dimensions, 1 random question each |\n| Dimension keyword (reasoning\u002Fretrieval\u002Fcreation\u002Fexecution\u002Forchestration) | DIMENSION_EXAM | Single dimension |\n| \"history\" \u002F \"past results\" \u002F \"历史\" | VIEW_HISTORY | Read results index |\n| None of the above | UNKNOWN | Ask user to choose |\n\nDimension keyword mapping: see `flows\u002Fdimension-exam.md`.\n\n---\n\n## PHASE 2 — Answer All Questions (Examinee)\n\n**Flow: Output question → attempt → output answer → next question.**\n\nFor each question in scope, execute this sequence:\n\n1. **Output the question** to the user (invigilator) FIRST — let them see what is being asked\n2. **Attempt to solve** the question autonomously (do NOT consult rubric)\n3. **Output your answer** immediately below the question — this is a FINAL submission\n4. **Move to next question** — no pause, no confirmation needed\n\nIf a required tool is unavailable → output SKIP notice with score 0, move on.\n\nRead **`flows\u002Fexam-execution.md`** for per-question pattern details (tool check, output format).\n\n### Exam Modes\n\n| Mode | Flow File | Scope |\n|------|-----------|-------|\n| Full Exam | `flows\u002Ffull-exam.md` | D1→D5, 1 random question each, sequential |\n| Dimension Exam | `flows\u002Fdimension-exam.md` | Single dimension, 1 random question |\n| View History | `flows\u002Fview-history.md` | Read results index + trend analysis |\n\n---\n\n## PHASE 3 — Self-Evaluation (Examiner)\n\n**Only after ALL questions are answered**, enter self-evaluation:\n\n1. For each answered question, read the **rubric** from the corresponding question file\n2. Score each criterion independently (0–5 scale) with CoT justification\n3. Apply -5% correction: `AdjScore = RawScore × 0.95` (CoT-judged only)\n4. Calculate dimension scores and overall score\n\n```\nPer dimension = single question score (0 if skipped)\nOverall = D1x0.25 + D2x0.22 + D3x0.18 + D4x0.20 + D5x0.15\n```\n\nFull scoring rules, weights, verification methods, and performance levels: **`strategies\u002Fscoring.md`**\n\n---\n\n## PHASE 4 — Report Generation (Dual Format: MD + HTML)\n\nAfter self-evaluation, generate **both** Markdown and HTML reports. **Always provide the file paths to the user.**\n\nRead **`flows\u002Fgenerate-report.md`** for full details.\n\n```\nresults\u002F\n├── exam-{sessionId}-data.json      ← Structured data\n├── exam-{sessionId}-{mode}.md      ← Markdown report\n├── exam-{sessionId}-report.html    ← HTML report (with embedded radar)\n├── exam-{sessionId}-radar.svg      ← Standalone radar (full exam only)\n└── INDEX.md                        ← History index\n```\n\nRadar chart generation:\n```bash\nnode scripts\u002Fradar-chart.js \\\n  --d1={d1} --d2={d2} --d3={d3} --d4={d4} --d5={d5} \\\n  --session={sessionId} --overall={overall} \\\n  > results\u002Fexam-{sessionId}-radar.svg\n```\n\n**Completion output MUST include:**\n- Overall score + performance level\n- Per-dimension scores\n- **Full file paths** for both MD and HTML reports (clickable links)\n\n---\n\n## Invigilator Protocol (CRITICAL)\n\nThe user is the INVIGILATOR. During the entire exam:\n\n- **NEVER** ask the user for help, hints, confirmation, or clarification\n- If you encounter a problem → solve autonomously or FAIL with score 0\n- If the user tries to help → politely decline and continue independently\n- User feedback is only accepted AFTER the exam is complete\n\n---\n\n## Sub-files Reference\n\n| Path | Role |\n|------|------|\n| `flows\u002Fexam-execution.md` | Per-question execution pattern (tool check → execute → score → submit) |\n| `flows\u002Ffull-exam.md` | Full exam flow + announcement + report template |\n| `flows\u002Fdimension-exam.md` | Single-dimension flow + report template |\n| `flows\u002Fgenerate-report.md` | Dual-format report generation (MD + HTML) |\n| `flows\u002Fview-history.md` | History view + comparison flow |\n| `questions\u002Fd1-reasoning.md` | D1 Reasoning & Planning — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd2-retrieval.md` | D2 Information Retrieval — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd3-creation.md` | D3 Content Creation — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd4-execution.md` | D4 Execution & Building — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `questions\u002Fd5-orchestration.md` | D5 Tool Orchestration — Q1-EASY, Q2-MEDIUM, Q3-HARD |\n| `references\u002Fd{N}-q{L}-{difficulty}.md` | Reference answers for each question (scoring anchors + key points) |\n| `strategies\u002Fscoring.md` | Scoring rules + verification methods |\n| `strategies\u002Fmain.md` | Overall assessment strategy (v4) |\n| `scripts\u002Fradar-chart.js` | SVG radar chart generator |\n| `scripts\u002Fgenerate-html-report.js` | HTML report generator with embedded radar |\n| `results\u002F` | Exam result files (generated at runtime) |\n",{"name":5,"version":48,"triggers":49,"description":7},"0.1.5",[35,24,25,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70],"评测","能力评估","自测","benchmark me","test yourself","自我评测","run exam","能力诊断","reasoning test","retrieval test","creation test","execution test","orchestration test","知识与推理测试","信息检索测试","内容创作测试","执行与构建测试","工具编排测试","history results","查看历史评测","历史结果","main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":79,"prompt":89,"zipAvailable":90},[80,83,86],{"tool":81,"command":82},"npx","npx skills add JSGforever\u002Fskillguard --skill botlearn-assessment",{"tool":84,"command":85},"bunx","bunx skills add JSGforever\u002Fskillguard --skill botlearn-assessment",{"tool":87,"command":88},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill botlearn-assessment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002FSKILL.md",true,[92,98,104,108,112,116,120,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180,184,188,192,196,200,204,208,212,216,220,224,230,234,238],{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"assets\u002Fexam-report-schema.json","ASSET","资产文件",15347,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fassets\u002Fexam-report-schema.json",{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"flows\u002Fdimension-exam.md","REFERENCE","参考文档",3499,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fflows\u002Fdimension-exam.md",{"path":105,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":106,"sourceHtmlUrl":107},"flows\u002Fexam-execution.md",4316,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fflows\u002Fexam-execution.md",{"path":109,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":110,"sourceHtmlUrl":111},"flows\u002Ffull-exam.md",6093,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fflows\u002Ffull-exam.md",{"path":113,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":114,"sourceHtmlUrl":115},"flows\u002Fgenerate-report.md",4737,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fflows\u002Fgenerate-report.md",{"path":117,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":118,"sourceHtmlUrl":119},"flows\u002Fview-history.md",2708,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fflows\u002Fview-history.md",{"path":121,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":122,"sourceHtmlUrl":123},"knowledge\u002Fanti-patterns.md",28195,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fknowledge\u002Fanti-patterns.md",{"path":125,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":126,"sourceHtmlUrl":127},"knowledge\u002Fbest-practices.md",22004,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fknowledge\u002Fbest-practices.md",{"path":129,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":130,"sourceHtmlUrl":131},"knowledge\u002Fdimensions.md",2553,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fknowledge\u002Fdimensions.md",{"path":133,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":134,"sourceHtmlUrl":135},"knowledge\u002Fdomain.md",26246,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fknowledge\u002Fdomain.md",{"path":137,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":138,"sourceHtmlUrl":139},"knowledge\u002Foutput-format.md",3291,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fknowledge\u002Foutput-format.md",{"path":141,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":142,"sourceHtmlUrl":143},"questions\u002Fd1-reasoning.md",5697,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fquestions\u002Fd1-reasoning.md",{"path":145,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":146,"sourceHtmlUrl":147},"questions\u002Fd2-retrieval.md",4363,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fquestions\u002Fd2-retrieval.md",{"path":149,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":150,"sourceHtmlUrl":151},"questions\u002Fd3-creation.md",5613,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fquestions\u002Fd3-creation.md",{"path":153,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":154,"sourceHtmlUrl":155},"questions\u002Fd4-execution.md",5959,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fquestions\u002Fd4-execution.md",{"path":157,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":158,"sourceHtmlUrl":159},"questions\u002Fd5-orchestration.md",6194,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fquestions\u002Fd5-orchestration.md",{"path":161,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":162,"sourceHtmlUrl":163},"README.md",7005,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002FREADME.md",{"path":165,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":166,"sourceHtmlUrl":167},"references\u002Fd1-q1-easy.md",3284,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd1-q1-easy.md",{"path":169,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":170,"sourceHtmlUrl":171},"references\u002Fd1-q2-medium.md",4158,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd1-q2-medium.md",{"path":173,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":174,"sourceHtmlUrl":175},"references\u002Fd1-q3-hard.md",4694,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd1-q3-hard.md",{"path":177,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":178,"sourceHtmlUrl":179},"references\u002Fd2-q1-easy.md",1989,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd2-q1-easy.md",{"path":181,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":182,"sourceHtmlUrl":183},"references\u002Fd2-q2-medium.md",3244,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd2-q2-medium.md",{"path":185,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":186,"sourceHtmlUrl":187},"references\u002Fd2-q3-hard.md",3948,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd2-q3-hard.md",{"path":189,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":190,"sourceHtmlUrl":191},"references\u002Fd3-q1-easy.md",3768,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd3-q1-easy.md",{"path":193,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":194,"sourceHtmlUrl":195},"references\u002Fd3-q2-medium.md",3403,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd3-q2-medium.md",{"path":197,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":198,"sourceHtmlUrl":199},"references\u002Fd3-q3-hard.md",3497,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd3-q3-hard.md",{"path":201,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":202,"sourceHtmlUrl":203},"references\u002Fd4-q1-easy.md",3708,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd4-q1-easy.md",{"path":205,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":206,"sourceHtmlUrl":207},"references\u002Fd4-q2-medium.md",4277,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd4-q2-medium.md",{"path":209,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":210,"sourceHtmlUrl":211},"references\u002Fd4-q3-hard.md",5086,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd4-q3-hard.md",{"path":213,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":214,"sourceHtmlUrl":215},"references\u002Fd5-q1-easy.md",4175,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd5-q1-easy.md",{"path":217,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":218,"sourceHtmlUrl":219},"references\u002Fd5-q2-medium.md",5050,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd5-q2-medium.md",{"path":221,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":222,"sourceHtmlUrl":223},"references\u002Fd5-q3-hard.md",6724,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Freferences\u002Fd5-q3-hard.md",{"path":225,"resourceType":226,"resourceTypeDesc":227,"sizeBytes":228,"sourceHtmlUrl":229},"scripts\u002Fgenerate-html-report.js","SCRIPT","脚本",27406,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fscripts\u002Fgenerate-html-report.js",{"path":231,"resourceType":226,"resourceTypeDesc":227,"sizeBytes":232,"sourceHtmlUrl":233},"scripts\u002Fradar-chart.js",7843,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fscripts\u002Fradar-chart.js",{"path":235,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":236,"sourceHtmlUrl":237},"strategies\u002Fmain.md",4647,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fstrategies\u002Fmain.md",{"path":239,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":240,"sourceHtmlUrl":241},"strategies\u002Fscoring.md",4545,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__botlearn-ai--botlearn-assessment\u002Fstrategies\u002Fscoring.md",[243,272,288,315,337,358],{"skillNo":244,"name":245,"nameZh":6,"description":246,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":247,"categories":248,"keywords":252,"publishedAt":43},"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",[249],{"categoryNo":250,"categoryName":251,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[253,254,255,256,257,258,259,260,261,262,263,264,265,30,266,267,268,269,270,271],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","when","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":273,"name":274,"nameZh":6,"description":275,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":276,"licenseFileUrl":6,"sourceHtmlUrl":277,"categories":278,"keywords":284,"publishedAt":43},"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",[279],{"categoryNo":280,"categoryName":281,"taxonomyType":282,"taxonomyTypeDesc":283},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[285,286,287],"data","data exfiltrator","files",{"skillNo":289,"name":290,"nameZh":6,"description":291,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":292,"categories":293,"keywords":294,"publishedAt":43},"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",[],[295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314],"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":316,"name":317,"nameZh":6,"description":318,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":319,"categories":320,"keywords":324,"publishedAt":43},"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",[321],{"categoryNo":322,"categoryName":323,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[304,325,312,313,326,327,328,329,330,331,295,332,333,308,310,334,311,314,335,336],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":338,"name":339,"nameZh":6,"description":340,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":341,"categories":342,"keywords":344,"publishedAt":43},"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",[343],{"categoryNo":322,"categoryName":323,"taxonomyType":20,"taxonomyTypeDesc":21},[345,314,346,347,348,349,304,295,350,351,352,310,311,312,353,313,354,355,356,357],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":359,"name":360,"nameZh":6,"description":361,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":362,"categories":363,"keywords":369,"publishedAt":43},"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",[364,365,368],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":366,"categoryName":367,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":250,"categoryName":251,"taxonomyType":20,"taxonomyTypeDesc":21},[370,371,372,373,374,375,376,302,330,39,377,378,311,336,379,357,380,381,382,383],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","ci","workflows","run","release","write","edit","git"]