[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FJTYP28XT035KK0X7VZ550":3,"skill-same:01M6FJTYP28XT035KK0X7VZ550":56},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M6FJTYP28XT035KK0X7VZ550","auto-review-loop-llm",null,"ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",67,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fwanshuiyin\u002FAuto-claude-code-research-in-sleep\u002Fauto-review-loop-llm\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],"review","loop","review loop","auto","auto review loop llm","auto review loop","2026-11-10 10:12:30",false,"# Auto Review Loop (Generic LLM): Autonomous Research Improvement\n\nAutonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.\n\n## Context: $ARGUMENTS\n\n## Constants\n\n- MAX_ROUNDS = 4\n- POSITIVE_THRESHOLD: score >= 6\u002F10, or verdict contains \"accept\", \"sufficient\", \"ready for submission\"\n- REVIEW_DOC: `AUTO_REVIEW.md` in project root (cumulative log)\n\n## LLM Configuration\n\nThis skill uses **any OpenAI-compatible API** for external review via the `llm-chat` MCP server.\n\n### Configuration via MCP Server (Recommended)\n\nAdd to `~\u002F.claude\u002Fsettings.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"llm-chat\": {\n      \"command\": \"\u002Fusr\u002Fbin\u002Fpython3\",\n      \"args\": [\"\u002FUsers\u002Fyourname\u002F.claude\u002Fmcp-servers\u002Fllm-chat\u002Fserver.py\"],\n      \"env\": {\n        \"LLM_API_KEY\": \"your-api-key\",\n        \"LLM_BASE_URL\": \"https:\u002F\u002Fapi.deepseek.com\u002Fv1\",\n        \"LLM_MODEL\": \"deepseek-chat\"\n      }\n    }\n  }\n}\n```\n\n### Supported Providers\n\n| Provider | LLM_BASE_URL | LLM_MODEL |\n|----------|--------------|-----------|\n| **OpenAI** | `https:\u002F\u002Fapi.openai.com\u002Fv1` | `gpt-4o`, `o3` |\n| **DeepSeek** | `https:\u002F\u002Fapi.deepseek.com\u002Fv1` | `deepseek-chat`, `deepseek-reasoner` |\n| **MiniMax** | `https:\u002F\u002Fapi.minimax.chat\u002Fv1` | `MiniMax-M2.5` |\n| **Kimi (Moonshot)** | `https:\u002F\u002Fapi.moonshot.cn\u002Fv1` | `moonshot-v1-8k`, `moonshot-v1-32k` |\n| **ZhiPu (GLM)** | `https:\u002F\u002Fopen.bigmodel.cn\u002Fapi\u002Fpaas\u002Fv4` | `glm-4`, `glm-4-plus` |\n| **SiliconFlow** | `https:\u002F\u002Fapi.siliconflow.cn\u002Fv1` | `Qwen\u002FQwen2.5-72B-Instruct` |\n| **阿里云百炼** | `https:\u002F\u002Fdashscope.aliyuncs.com\u002Fcompatible-mode\u002Fv1` | `qwen-max` |\n| **零一万物** | `https:\u002F\u002Fapi.lingyiwanwu.com\u002Fv1` | `yi-large` |\n\n## API Call Method\n\n**Primary: MCP Tool**\n\n```\nmcp__llm-chat__chat:\n  prompt: |\n    [Review prompt content]\n  model: \"deepseek-chat\"\n  system: \"You are a senior ML reviewer...\"\n```\n\n**Fallback: curl**\n\n```bash\ncurl -s \"${LLM_BASE_URL}\u002Fchat\u002Fcompletions\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer ${LLM_API_KEY}\" \\\n  -d '{\n    \"model\": \"${LLM_MODEL}\",\n    \"messages\": [\n      {\"role\": \"system\", \"content\": \"You are a senior ML reviewer...\"},\n      {\"role\": \"user\", \"content\": \"[review prompt]\"}\n    ],\n    \"max_tokens\": 4096\n  }'\n```\n\n## State Persistence (Compact Recovery)\n\nPersist state to `REVIEW_STATE.json` after each round:\n\n```json\n{\n  \"round\": 2,\n  \"status\": \"in_progress\",\n  \"last_score\": 5.0,\n  \"last_verdict\": \"not ready\",\n  \"pending_experiments\": [],\n  \"timestamp\": \"2026-03-15T10:00:00\"\n}\n```\n\n**Write this file at the end of every Phase E** (after documenting the round).\n\n**On completion**, set `\"status\": \"completed\"`.\n\n## Workflow\n\n### Initialization\n\n1. **Check `REVIEW_STATE.json`** for recovery\n2. Read project context and prior reviews\n3. Initialize round counter\n\n### Loop (up to MAX_ROUNDS)\n\n#### Phase A: Review\n\n**If MCP available:**\n```\nmcp__llm-chat__chat:\n  system: \"You are a senior ML reviewer (NeurIPS\u002FICML level).\"\n  prompt: |\n    [Round N\u002FMAX_ROUNDS of autonomous review loop]\n\n    [Full research context: claims, methods, results, known weaknesses]\n    [Changes since last round, if any]\n\n    1. Score this work 1-10 for a top venue\n    2. List remaining critical weaknesses (ranked by severity)\n    3. For each weakness, specify the MINIMUM fix\n    4. State clearly: is this READY for submission? Yes\u002FNo\u002FAlmost\n\n    Be brutally honest. If the work is ready, say so clearly.\n```\n\n**If MCP NOT available:**\n```bash\ncurl -s \"${LLM_BASE_URL}\u002Fchat\u002Fcompletions\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer ${LLM_API_KEY}\" \\\n  -d '{\n    \"model\": \"${LLM_MODEL}\",\n    \"messages\": [\n      {\"role\": \"system\", \"content\": \"You are a senior ML reviewer (NeurIPS\u002FICML level).\"},\n      {\"role\": \"user\", \"content\": \"[Full review prompt]\"}\n    ],\n    \"max_tokens\": 4096\n  }'\n```\n\n#### Phase B: Parse Assessment\n\n**CRITICAL: Save the FULL raw response** verbatim. Then extract:\n- **Score** (numeric 1-10)\n- **Verdict** (\"ready\" \u002F \"almost\" \u002F \"not ready\")\n- **Action items** (ranked list of fixes)\n\n**STOP**: If score >= 6 AND verdict contains \"ready\u002Falmost\"\n\n#### Phase C: Implement Fixes\n\nPriority: metric additions > reframing > new experiments\n\n#### Phase D: Wait for Results\n\nMonitor remote experiments\n\n#### Phase E: Document Round\n\nAppend to `AUTO_REVIEW.md`:\n\n```markdown\n## Round N (timestamp)\n\n### Assessment (Summary)\n- Score: X\u002F10\n- Verdict: [ready\u002Falmost\u002Fnot ready]\n- Key criticisms: [bullet list]\n\n### Reviewer Raw Response\n\n\u003Cdetails>\n\u003Csummary>Click to expand full reviewer response\u003C\u002Fsummary>\n\n[Paste the COMPLETE raw response here — verbatim, unedited.]\n\n\u003C\u002Fdetails>\n\n### Actions Taken\n- [what was implemented\u002Fchanged]\n\n### Results\n- [experiment outcomes, if any]\n\n### Status\n- [continuing to round N+1 \u002F stopping]\n```\n\n**Write `REVIEW_STATE.json`** with current state.\n\n### Termination\n\n1. Set `REVIEW_STATE.json` status to \"completed\"\n2. Write final summary\n\n## Key Rules\n\n- **Large file handling**: If the Write tool fails due to file size, immediately retry using Bash (`cat \u003C\u003C 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.\n\n- Be honest about weaknesses\n- Implement fixes BEFORE re-reviewing\n- Document everything\n- Include previous context in round 2+ prompts\n- Prefer MCP tool over curl when available\n\n## Prompt Template for Round 2+\n\n```\nmcp__llm-chat__chat:\n  system: \"You are a senior ML reviewer (NeurIPS\u002FICML level).\"\n  prompt: |\n    [Round N\u002FMAX_ROUNDS of autonomous review loop]\n\n    ## Previous Review Summary (Round N-1)\n    - Previous Score: X\u002F10\n    - Previous Verdict: [ready\u002Falmost\u002Fnot ready]\n    - Previous Key Weaknesses: [list]\n\n    ## Changes Since Last Review\n    1. [Action 1]: [result]\n    2. [Action 2]: [result]\n\n    ## Updated Results\n    [paste updated metrics\u002Ftables]\n\n    Please re-score and re-assess:\n    1. Score this work 1-10 for a top venue\n    2. List remaining critical weaknesses (ranked by severity)\n    3. For each weakness, specify the MINIMUM fix\n    4. State clearly: is this READY for submission? Yes\u002FNo\u002FAlmost\n\n    Be brutally honest. If the work is ready, say so clearly.\n```\n",{},"main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Fwanshuiyin\u002FAuto-claude-code-research-in-sleep\u002Fauto-review-loop-llm",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":7,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill auto-review-loop-llm",{"tool":48,"command":49},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill auto-review-loop-llm",{"tool":51,"command":52},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill auto-review-loop-llm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fwanshuiyin\u002FAuto-claude-code-research-in-sleep\u002Fauto-review-loop-llm\u002FSKILL.md",true,[],[57,67,77,86,92,99],{"skillNo":58,"name":59,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":63,"publishedAt":29},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[62],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[64,65,66],"model","model hierarchy","model hierarchy skill",{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":73,"publishedAt":29},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[72],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[74,75,76],"MCP","zoom","zoom mcp",{"skillNo":78,"name":79,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":29},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[83,84,85,75],"sdk","zoom apps sdk","apps",{"skillNo":87,"name":88,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":29},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[88],{"skillNo":93,"name":94,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":98,"publishedAt":29},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[97],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[94],{"skillNo":100,"name":101,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":29},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[101]]