[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C2WBG7CD43WES0N4QQWADB":3,"skill-same:01M6C2WBG7CD43WES0N4QQWADB":62},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6C2WBG7CD43WES0N4QQWADB","dice-real-mode-tests",null,"Validate dice integrity end to end with real services through the MCP dice test suite.","jleechanorg\u002Fjleechan-skills","jleechanorg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221404966?v=4","01M6C1VJ99XG950X1DWPEBCBGX","01M6C1VJDK5YVDNT3362RT5WSB",6,"MIT","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-09-01-superseded-legacy\u002Fdice-real-mode-tests\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],"dice real mode tests","tests","dice","mode","MCP","test","validate","services","integrity","test suite","end","with","suite","2026-11-10 10:12:30",false,"---\nname: dice-real-mode-tests\ndescription: Validate dice integrity end to end with real services through the MCP dice test suite.\n---\n\n# Dice Real-Mode Tests (MCP)\n\nUse this when validating **dice integrity** end-to-end with real services.\n\n## Script Location\n\n- `testing_mcp\u002Ftest_dice_rolls_comprehensive.py`\n\n## Required Standards\n\n- **Evidence**: Follow `.claude\u002Fskills\u002Fevidence-standards.md` (Three-Evidence Rule)\n- **Authenticity**: Follow `.claude\u002Fskills\u002Fdice-authenticity-standards.md` (Chi-squared + RNG verification)\n\n## Preview Server (real mode)\n\n```bash\npython testing_mcp\u002Ftest_dice_rolls_comprehensive.py \\\n  --server-url https:\u002F\u002F\u003Cpreview-app>.run.app\u002Fmcp \\\n  --evidence \\\n  --evidence-dir \u002Ftmp\u002F\u003Crun-id> \\\n  --models gemini-3-flash-preview,qwen-3-235b-a22b-instruct-2507\n```\n\nNotes:\n- Distribution tests will skip if `roll_dice` tool is unavailable on preview.\n- Qwen\u002Fnative_two_phase uses **server tool_results** as authoritative; mismatches are overridden.\n- Use a unique `\u002Ftmp\u002F\u003Crun-id>\u002F` (timestamp or UUID) per run to avoid collisions.\n\n## Local MCP (real services)\n\n```bash\npython testing_mcp\u002Ftest_dice_rolls_comprehensive.py \\\n  --start-local --real-services --evidence --enable-dice-tool \\\n  --models gemini-3-flash-preview,qwen-3-235b-a22b-instruct-2507 \\\n  --evidence-dir \u002Ftmp\u002F\u003Crun-id>\n```\n\nOutputs:\n- `run.json` (scenario results, tool_results, dice_audit_events, warnings)\n- `local_mcp_*.log` (server logs)\n- `raw_*.txt` (raw model responses when enabled)\n\n## What This Covers\n\n- **Gemini code_execution** path (dice_audit_events source=code_execution).\n- **native_two_phase** path (Qwen\u002FCerebras tool_results).\n- **Distribution** tests (1d6 \u002F 1d20) when roll_dice tool is available.\n- **Edge cases** (invalid notation, 1d0+5).\n\n## Common Expectations\n\n- `DICE_ROLLS_MISMATCH` \u002F `DICE_AUDIT_MISMATCH` warnings can appear; server overrides with tool_results.\n- Final `run.json` should show aligned totals across `dice_rolls`, `dice_audit_events`, and `tool_results`.\n\n## Chi-Squared Validation\n\nAfter running distribution tests, validate authenticity:\n\n| Chi-Squared | Sample Size | Verdict |\n|-------------|-------------|---------|\n| \u003C 30 | 100+ | PASS |\n| 30-50 | 100+ | WARNING - Investigate |\n| > 50 | 100+ | FAIL - Likely fabrication |\n\n**Reference**: PR #2551 detected fabrication with chi-squared = 411.81\n\n## Troubleshooting\n\n- If native_two_phase fails: ensure tool_results are present in responses.\n- If mismatch errors appear in `run.json`: check the log and confirm override occurred.\n- If distribution tests skip on preview: expected unless `roll_dice` tool is exposed.\n- If chi-squared > 50: Check `rng_verified` field in evidence - may indicate fabrication.\n","# Dice Real-Mode Tests (MCP)\n\nUse this when validating **dice integrity** end-to-end with real services.\n\n## Script Location\n\n- `testing_mcp\u002Ftest_dice_rolls_comprehensive.py`\n\n## Required Standards\n\n- **Evidence**: Follow `.claude\u002Fskills\u002Fevidence-standards.md` (Three-Evidence Rule)\n- **Authenticity**: Follow `.claude\u002Fskills\u002Fdice-authenticity-standards.md` (Chi-squared + RNG verification)\n\n## Preview Server (real mode)\n\n```bash\npython testing_mcp\u002Ftest_dice_rolls_comprehensive.py \\\n  --server-url https:\u002F\u002F\u003Cpreview-app>.run.app\u002Fmcp \\\n  --evidence \\\n  --evidence-dir \u002Ftmp\u002F\u003Crun-id> \\\n  --models gemini-3-flash-preview,qwen-3-235b-a22b-instruct-2507\n```\n\nNotes:\n- Distribution tests will skip if `roll_dice` tool is unavailable on preview.\n- Qwen\u002Fnative_two_phase uses **server tool_results** as authoritative; mismatches are overridden.\n- Use a unique `\u002Ftmp\u002F\u003Crun-id>\u002F` (timestamp or UUID) per run to avoid collisions.\n\n## Local MCP (real services)\n\n```bash\npython testing_mcp\u002Ftest_dice_rolls_comprehensive.py \\\n  --start-local --real-services --evidence --enable-dice-tool \\\n  --models gemini-3-flash-preview,qwen-3-235b-a22b-instruct-2507 \\\n  --evidence-dir \u002Ftmp\u002F\u003Crun-id>\n```\n\nOutputs:\n- `run.json` (scenario results, tool_results, dice_audit_events, warnings)\n- `local_mcp_*.log` (server logs)\n- `raw_*.txt` (raw model responses when enabled)\n\n## What This Covers\n\n- **Gemini code_execution** path (dice_audit_events source=code_execution).\n- **native_two_phase** path (Qwen\u002FCerebras tool_results).\n- **Distribution** tests (1d6 \u002F 1d20) when roll_dice tool is available.\n- **Edge cases** (invalid notation, 1d0+5).\n\n## Common Expectations\n\n- `DICE_ROLLS_MISMATCH` \u002F `DICE_AUDIT_MISMATCH` warnings can appear; server overrides with tool_results.\n- Final `run.json` should show aligned totals across `dice_rolls`, `dice_audit_events`, and `tool_results`.\n\n## Chi-Squared Validation\n\nAfter running distribution tests, validate authenticity:\n\n| Chi-Squared | Sample Size | Verdict |\n|-------------|-------------|---------|\n| \u003C 30 | 100+ | PASS |\n| 30-50 | 100+ | WARNING - Investigate |\n| > 50 | 100+ | FAIL - Likely fabrication |\n\n**Reference**: PR #2551 detected fabrication with chi-squared = 411.81\n\n## Troubleshooting\n\n- If native_two_phase fails: ensure tool_results are present in responses.\n- If mismatch errors appear in `run.json`: check the log and confirm override occurred.\n- If distribution tests skip on preview: expected unless `roll_dice` tool is exposed.\n- If chi-squared > 50: Check `rng_verified` field in evidence - may indicate fabrication.\n",{"name":5,"description":7},"main","42ccd02cbf5e8e47839dc3eab6fc754dc6b339cf",".claude\u002Fskills_archive\u002F2026-09-01-superseded-legacy\u002Fdice-real-mode-tests",0,"https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills","https:\u002F\u002Fgithub.com\u002Fjleechanorg","2026-11-14 14:55:35",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add jleechanorg\u002Fjleechan-skills --skill dice-real-mode-tests",{"tool":54,"command":55},"bunx","bunx skills add jleechanorg\u002Fjleechan-skills --skill dice-real-mode-tests",{"tool":57,"command":58},"pnpm","pnpm dlx skills add jleechanorg\u002Fjleechan-skills --skill dice-real-mode-tests","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-09-01-superseded-legacy\u002Fdice-real-mode-tests\u002FSKILL.md",true,[],[63,81,103,117,131,147],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":36},"01M716Y5MTJ6GYJZ2ATXCJK8G4","instinct","Use when the user invokes \u002Finstinct or \u002Fin, or asks to \"message Instinct\", \"ask Instinct\", \"tell Instinct\", \"check Instinct\", or read replies from the configured peer assistant. iMessage first, WhatsApp Web as fallback.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finstinct\u002FSKILL.md",[],[65,70,71,72,73,74,75,76,77,78,79,80],"user","when","replies","check","use","identity","whatsapp","gmail","read","message","ask",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":92,"publishedAt":36},"01M716Y4HF7FVVMJSA2CCVN5VF","hr","Compatibility alias for history-resume; produce the same fresh-state, provenance-aware resume briefing.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhr\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[83,93,94,95,96,97,98,99,100,101,102],"resume","compatibility","provenance","for","history","produce","alias","briefing","state","fresh",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":110,"publishedAt":36},"01M716Y1FFNFKFJYYKF8HQA6T8","history-resume","Resume briefing for the current repository branch or worktree using fresh state and admitted history sources.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhistory-resume\u002FSKILL.md",[109],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[97,93,111,112,70,113,100,114,96,115,116,101,102],"history resume","branch","analysis","repository","worktree","sources",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":36},"01M716XWXJ8EPHK4RH9T14TR85","grok","Alias for the canonical grokbot browser conversation workflow; \u002Fgrok talks to the Grok bot the same way \u002Fdot talks to Dot.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrok\u002FSKILL.md",[],[119,124,125,126,96,127,99,128,129,130],"dot","bot","workflow","canonical","conversation","browser","grokbot",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":36},"01M70N9Q07DTE0EW5KFXMMMSJ0","codexa-bench","Compare `codexa` and normal `codex` on a fair split of comparable work by default; use `--strict` for duplicate runs of the exact same task.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcodexa-bench\u002FSKILL.md",[],[138,139,140,74,141,96,142,143,144,145,146],"codexa bench","work","split","default","duplicate","task","compare","normal","codex",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":151,"licenseFileUrl":152,"sourceHtmlUrl":153,"categories":154,"keywords":164,"publishedAt":36},"01M6C24S2X60SP8BBFGAEKPEGW","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FSKILL.md",[155,158,161],{"categoryNo":156,"categoryName":157,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":162,"categoryName":163,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000032","设计师",[165,166,167,74,168,169,170,70,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,34,186,187,71,188],"frontend","design","frontend design","generic","ui design","react","html","components","code","artifacts","ui","aesthetics","Production","web components","landing","applications","quality","web","css","create","examples","react components","web ui","pages"]