[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C2SWQZ6FTDVTZSAJ5J6T7M":3,"skill-same:01M6C2SWQZ6FTDVTZSAJ5J6T7M":74},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M6C2SWQZ6FTDVTZSAJ5J6T7M","thinclaw",null,"Use thinclaw MCP server — thin inference-less bridge to OpenClaw Gateway for executing tools","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\u002F2026-08-27-historical-zero-use\u002Fthinclaw\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32],"MCP","openclaw","inference","mcp server","gateway","server","Tools","bridge","use","for","2026-11-10 10:12:30",false,"---\nname: thinclaw\ndescription: Use thinclaw MCP server — thin inference-less bridge to OpenClaw Gateway for executing tools\ntype: skill\n---\n\n# thinclaw — Thin Inference-Less MCP Server\n\n## What thinclaw is\n\nthinclaw is a **zero-inference MCP server** that acts as a bridge between Claude Desktop\u002FCowork and the OpenClaw Gateway. It performs ZERO inference — only HTTP relay.\n\n```\n┌─────────────────┐  MCP stdio   ┌──────────────┐  HTTP REST  ┌──────────────────┐\n│  Claude Desktop │ ───────────► │   thinclaw   │ ──────────► │  OpenClaw         │\n│  Claude Cowork  │   zero LLM   │   (bridge)   │  \u002Ftools\u002F    │  Gateway         │\n│  Perplexity     │ ◄─────────── │  Node.js     │  invoke     │  localhost:18789 │\n└─────────────────┘  tool result└──────────────┘ ◄────────── └──────────────────┘\n```\n\n**All reasoning happens in the calling AI.** thinclaw only proxies tool calls to the Gateway.\n\n---\n\n## Available Tools\n\nUse these tools in Claude Desktop after thinclaw is installed and Claude Desktop is restarted.\n\n### 1. openclaw_execute\n\nUniversal proxy — call ANY OpenClaw tool by name.\n\n```\nTool: openclaw_execute\nArguments: {\n  \"tool\": \"bash\",\n  \"params\": { \"command\": \"ls -la\", \"cwd\": \"\u002Ftmp\" }\n}\n```\n\nSupported tool names: `bash`, `read_file`, `grep`, `todo_list_write`, `slack_postMessage`, `whatsapp_send`, `memory_search`, etc.\n\n### 2. run_shell\n\nShorthand for executing shell commands.\n\n```\nTool: run_shell\nArguments: {\n  \"command\": \"find . -name '*.js' | head -10\"\n}\n```\n\n### 3. send_whatsapp\n\nSend a WhatsApp message (requires `whatsapp_send` tool registered in Gateway).\n\n```\nTool: send_whatsapp\nArguments: {\n  \"to\": \"+1234567890\",\n  \"message\": \"Hello from thinclaw!\"\n}\n```\n\n### 4. schedule_cron\n\nSchedule a recurring task via Gateway cron.\n\n```\nTool: schedule_cron\nArguments: {\n  \"schedule\": \"*\u002F5 * * * *\",\n  \"task\": \"check-deployments\"\n}\n```\n\n### 5. trigger_cowork_workflow\n\nTrigger a Claude Cowork workflow by writing a flag file to `~\u002FAI_Bridge\u002Finbox\u002F`.\n\n```\nTool: trigger_cowork_workflow\nArguments: {\n  \"workflow\": \"daily-standup\",\n  \"context\": { \"channel\": \"#engineering\", \"time\": \"09:30\" }\n}\n```\n\nThis creates `~\u002FAI_Bridge\u002Finbox\u002Ftrigger-\u003Ctimestamp>.json`. Cowork monitors this folder.\n\n---\n\n## Architecture Notes\n\n- **Gateway must be running** at `http:\u002F\u002Flocalhost:18789`\n- **Token** auto-read from `~\u002F.openclaw\u002Fopenclaw.json` or set via `GATEWAY_TOKEN`\n- **AI_Bridge folder**: `~\u002FAI_Bridge\u002F{inbox,outbox,processed}` for cron → Cowork handoff\n- **No inference** — thinclaw is a pure HTTP relay, zero LLM calls\n\n---\n\n## Troubleshooting\n\n| Issue | Fix |\n|-------|-----|\n| Gateway not responding | Start Gateway: `openclaw gateway start` |\n| Token missing | Check: `cat ~\u002F.openclaw\u002Fopenclaw.json \\| jq '.gateway.auth.token'` |\n| Health check | `curl http:\u002F\u002Flocalhost:18789\u002Fhealth` |\n| Tools not showing | Restart Claude Desktop after installing thinclaw |\n\n---\n\n## Installation (for reference)\n\nthinclaw is installed via Claude Desktop config at `~\u002FLibrary\u002FApplication Support\u002FClaude\u002Fclaude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"thinclaw\": {\n      \"command\": \"node\",\n      \"args\": [\"$HOME\u002Fthinclaw\u002Fserver.js\"],\n      \"env\": { \"GATEWAY_TOKEN\": \"...\" }\n    }\n  }\n}\n```\n","# thinclaw — Thin Inference-Less MCP Server\n\n## What thinclaw is\n\nthinclaw is a **zero-inference MCP server** that acts as a bridge between Claude Desktop\u002FCowork and the OpenClaw Gateway. It performs ZERO inference — only HTTP relay.\n\n```\n┌─────────────────┐  MCP stdio   ┌──────────────┐  HTTP REST  ┌──────────────────┐\n│  Claude Desktop │ ───────────► │   thinclaw   │ ──────────► │  OpenClaw         │\n│  Claude Cowork  │   zero LLM   │   (bridge)   │  \u002Ftools\u002F    │  Gateway         │\n│  Perplexity     │ ◄─────────── │  Node.js     │  invoke     │  localhost:18789 │\n└─────────────────┘  tool result└──────────────┘ ◄────────── └──────────────────┘\n```\n\n**All reasoning happens in the calling AI.** thinclaw only proxies tool calls to the Gateway.\n\n---\n\n## Available Tools\n\nUse these tools in Claude Desktop after thinclaw is installed and Claude Desktop is restarted.\n\n### 1. openclaw_execute\n\nUniversal proxy — call ANY OpenClaw tool by name.\n\n```\nTool: openclaw_execute\nArguments: {\n  \"tool\": \"bash\",\n  \"params\": { \"command\": \"ls -la\", \"cwd\": \"\u002Ftmp\" }\n}\n```\n\nSupported tool names: `bash`, `read_file`, `grep`, `todo_list_write`, `slack_postMessage`, `whatsapp_send`, `memory_search`, etc.\n\n### 2. run_shell\n\nShorthand for executing shell commands.\n\n```\nTool: run_shell\nArguments: {\n  \"command\": \"find . -name '*.js' | head -10\"\n}\n```\n\n### 3. send_whatsapp\n\nSend a WhatsApp message (requires `whatsapp_send` tool registered in Gateway).\n\n```\nTool: send_whatsapp\nArguments: {\n  \"to\": \"+1234567890\",\n  \"message\": \"Hello from thinclaw!\"\n}\n```\n\n### 4. schedule_cron\n\nSchedule a recurring task via Gateway cron.\n\n```\nTool: schedule_cron\nArguments: {\n  \"schedule\": \"*\u002F5 * * * *\",\n  \"task\": \"check-deployments\"\n}\n```\n\n### 5. trigger_cowork_workflow\n\nTrigger a Claude Cowork workflow by writing a flag file to `~\u002FAI_Bridge\u002Finbox\u002F`.\n\n```\nTool: trigger_cowork_workflow\nArguments: {\n  \"workflow\": \"daily-standup\",\n  \"context\": { \"channel\": \"#engineering\", \"time\": \"09:30\" }\n}\n```\n\nThis creates `~\u002FAI_Bridge\u002Finbox\u002Ftrigger-\u003Ctimestamp>.json`. Cowork monitors this folder.\n\n---\n\n## Architecture Notes\n\n- **Gateway must be running** at `http:\u002F\u002Flocalhost:18789`\n- **Token** auto-read from `~\u002F.openclaw\u002Fopenclaw.json` or set via `GATEWAY_TOKEN`\n- **AI_Bridge folder**: `~\u002FAI_Bridge\u002F{inbox,outbox,processed}` for cron → Cowork handoff\n- **No inference** — thinclaw is a pure HTTP relay, zero LLM calls\n\n---\n\n## Troubleshooting\n\n| Issue | Fix |\n|-------|-----|\n| Gateway not responding | Start Gateway: `openclaw gateway start` |\n| Token missing | Check: `cat ~\u002F.openclaw\u002Fopenclaw.json \\| jq '.gateway.auth.token'` |\n| Health check | `curl http:\u002F\u002Flocalhost:18789\u002Fhealth` |\n| Tools not showing | Restart Claude Desktop after installing thinclaw |\n\n---\n\n## Installation (for reference)\n\nthinclaw is installed via Claude Desktop config at `~\u002FLibrary\u002FApplication Support\u002FClaude\u002Fclaude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"thinclaw\": {\n      \"command\": \"node\",\n      \"args\": [\"$HOME\u002Fthinclaw\u002Fserver.js\"],\n      \"env\": { \"GATEWAY_TOKEN\": \"...\" }\n    }\n  }\n}\n```\n",{"name":5,"type":38,"description":7},"skill","main","42ccd02cbf5e8e47839dc3eab6fc754dc6b339cf",".claude\u002Fskills_archive\u002F2026-08-27-historical-zero-use\u002Fthinclaw",0,"https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills","https:\u002F\u002Fgithub.com\u002Fjleechanorg","2026-11-11 22:19:36",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add jleechanorg\u002Fjleechan-skills --skill thinclaw",{"tool":52,"command":53},"bunx","bunx skills add jleechanorg\u002Fjleechan-skills --skill thinclaw",{"tool":55,"command":56},"pnpm","pnpm dlx skills add jleechanorg\u002Fjleechan-skills --skill thinclaw","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002F2026-08-27-historical-zero-use\u002Fthinclaw\u002FSKILL.md",true,[60,66,70],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"evals\u002Fbenchmark.json","REFERENCE","参考文档",3901,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Freview-work-item\u002Fevals\u002Fbenchmark.json",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"evals\u002Fevals.json",3615,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Freview-work-item\u002Fevals\u002Fevals.json",{"path":71,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":72,"sourceHtmlUrl":73},"evals\u002Ffiles\u002Ffull-review-flow\u002Fwork-item.md",3495,"https:\u002F\u002Fgithub.com\u002Fatomicinnovation\u002Faccelerator\u002Fblob\u002Fmain\u002Fskills\u002Fwork\u002Freview-work-item\u002Fevals\u002Ffiles\u002Ffull-review-flow\u002Fwork-item.md",[75,92,113,127,141,157],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":33},"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",[],[77,82,83,84,85,31,86,87,88,89,90,91],"user","when","replies","check","identity","whatsapp","gmail","read","message","ask",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":33},"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",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[94,104,105,106,32,107,108,109,110,111,112],"resume","compatibility","provenance","history","produce","alias","briefing","state","fresh",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":33},"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",[119],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[107,104,121,122,82,123,110,124,32,125,126,111,112],"history resume","branch","analysis","repository","worktree","sources",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":33},"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",[],[129,134,135,136,32,137,109,138,139,140],"dot","bot","workflow","canonical","conversation","browser","grokbot",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":33},"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",[],[148,149,150,31,151,32,152,153,154,155,156],"codexa bench","work","split","default","duplicate","task","compare","normal","codex",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":161,"licenseFileUrl":162,"sourceHtmlUrl":163,"categories":164,"keywords":174,"publishedAt":33},"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",[165,168,171],{"categoryNo":166,"categoryName":167,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":169,"categoryName":170,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":172,"categoryName":173,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000032","设计师",[175,176,177,31,178,179,180,82,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,83,199],"frontend","design","frontend design","generic","ui design","react","html","components","code","artifacts","ui","aesthetics","Production","web components","landing","applications","quality","web","css","create","examples","with","react components","web ui","pages"]