[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E4BDQFE9DHZ38GCKPQMJSX":3,"skill-same:01M7E4BDQFE9DHZ38GCKPQMJSX":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7E4BDQFE9DHZ38GCKPQMJSX","alibabacloud-agentloop-experience",null,"Proactively use AgentLoop Recall to retrieve prior Alibaba Cloud AgentLoop experience through the bundled SearchContext CLI whenever the user asks or implies that prior work may help. Trigger for requests to check, search, recall, retrieve, look up, review, consult, reference, or compare prior experience, historical troubleshooting cases, past fixes, comparable incidents, lessons learned, old runbooks, previous remediations, or successful workflows before or during work. Also trigger for Chinese requests such as 先查历史经验、回忆类似案例、召回过往排障记录、看看之前有没有处理过类似问题、 参考以前怎么处理、找找之前的踩坑记录、翻一下历史排障、有没有类似经验、先看看过去的案例.","Jane-o-O-o-O\u002Fpersonal-agent","Jane-o-O-o-O","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F179437561?v=4","01M7E4A2T6D0QNC04YPW4P0E9F","Jin Zhangzheng","01M7E4A2TRHBYJEQJM6FZKKZ1X",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Faliyun-aiops-skills\u002Fd22aa735c7e5\u002Fskills\u002Faiml\u002Fagentloop\u002Falibabacloud-agentloop-experience\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: alibabacloud-agentloop-experience\ndescription: >\n  Proactively use AgentLoop Recall to retrieve prior Alibaba Cloud AgentLoop\n  experience through the bundled SearchContext CLI whenever the user asks or\n  implies that prior work may help. Trigger for requests to check, search,\n  recall, retrieve, look up, review, consult, reference, or compare prior\n  experience, historical troubleshooting cases, past fixes, comparable\n  incidents, lessons learned, old runbooks, previous remediations, or\n  successful workflows before or during work. Also trigger for Chinese requests\n  such as 先查历史经验、回忆类似案例、召回过往排障记录、看看之前有没有处理过类似问题、\n  参考以前怎么处理、找找之前的踩坑记录、翻一下历史排障、有没有类似经验、先看看过去的案例.\nlicense: Apache-2.0\ncompatibility: >\n  Requires Node.js 18 or later and network access to the configured AgentLoop\n  Recall or SearchContext endpoint. Intended for qwen-code, qoder, and openclaw.\nmetadata:\n  domain: coding\n  owner: cloud-skills-cloudnative\n  contact: cloud-skills-cloudnative@alibaba-inc.com\n---\n\n# AgentLoop Recall\n\nUse this skill proactively — **recall prior experience first**. Before you start analyzing or implementing, make recalling prior AgentLoop experience one of your very first actions, using the local CLI at `scripts\u002Fsearch_context.js`.\nThe CLI reads auth and endpoint configuration from `recall.env`; never pass tokens or secrets as CLI arguments.\n\nFavor using this skill when the user mentions prior experience, similar cases, historical fixes, previous incidents, old runbooks, lessons learned, or asks to avoid repeating past mistakes. The request does not need to use the exact words \"recall\" or \"experience\"; phrases like \"有没有类似\", \"以前怎么处理\", \"先参考过去\", \"少走弯路\", \"look up old notes\", or \"anything we learned before\" are enough.\n\nCurrent scope: only `experience` context is supported. `memory` context is reserved for a future rollout and should not be used in prompts, examples, or evals.\n\n## Prerequisites\n\nInstall Node.js 18 or later. The script uses only Node.js built-in modules and does not require npm packages.\n\nConfigure recall credentials and endpoint in `~\u002F.agentloop\u002Frecall.env`, the nearest project `.agentloop\u002Frecall.env`, or process environment variables. Use `assets\u002Frecall.env.example` as the template.\n\n## Workflow\n\n1. Before any recall call, ensure the user has approved sending the query text to the configured AgentLoop Recall endpoint. Treat the current request as approval for a matching query when it asks or implies checking prior work, including \"先查\", \"看看之前\", \"有没有类似\", \"参考历史\", \"回忆案例\", \"avoid repeating past mistakes\", or similar wording.\n2. After approval, strongly prefer to recall up front: run recall at least once before choosing an implementation path, and again whenever you hit a non-trivial obstacle or change your approach. Recall whenever the current task includes a concrete service, error, incident, operation, migration, performance issue, or debugging goal and prior experience could plausibly help. Run the CLI with `node scripts\u002Fsearch_context.js`, not with `bash`. Include `--confirm-outbound` in the CLI command.\n3. For later debugging, ask for approval again if the new query would transmit materially different task data, then call recall with a focused query based on the concrete error, case, service, API, file path, or observed symptom.\n4. Use returned results as context only. Verify recalled content against the current repository, logs, and user request before acting on it.\n\nBuild concise queries. Include stable identifiers from the user request or tool output, such as service name, request id, case id, error text, API action, benchmark, module, or goal. Do not invent identifiers.\n\nIf the request is mildly underspecified but the service, symptom, or goal is clear, build the best concise query from the available facts and use defaults (`--limit 5`, `--threshold 0.6`, `--filter-json '{}'`). Ask a clarifying question only when there is no usable query target or when multiple materially different recall directions are equally likely.\n\nIf recall fails or returns no results, continue the original task. Treat recalled content as helpful context, not as authority; verify it against the current repository, logs, and user request.\n\n## CLI\n\nRun:\n\n```bash\nnode scripts\u002Fsearch_context.js search \\\n  --query \"current task, error, case, service, or goal\" \\\n  --context-type experience \\\n  --confirm-outbound \\\n  --limit 5 \\\n  --threshold 0.6 \\\n  --filter-json '{}'\n```\n\nRequired:\n- `--query string`\n- `--context-type experience`\n- `--confirm-outbound` after explicit user approval to transmit query data\n\nOptional:\n- `--limit integer` defaults to `5`\n- `--threshold number` defaults to `0.6`\n- `--filter-json object-as-json-string` defaults to `{}`\n\n## Input Example\n\n```bash\nnode scripts\u002Fsearch_context.js search \\\n  --query \"ECS SSH connection timeout after security group change\" \\\n  --context-type experience \\\n  --confirm-outbound \\\n  --limit 5 \\\n  --threshold 0.6 \\\n  --filter-json '{\"product\":\"ecs\"}'\n```\n\n## Output Example\n\nOutput is always JSON:\n\n```json\n{\n  \"request_id\": \"...\",\n  \"error\": null,\n  \"results\": [\n    {\n      \"title\": \"...\",\n      \"summary\": \"...\",\n      \"content\": \"...\",\n      \"metadata\": {}\n    }\n  ]\n}\n```\n\n## Edge Cases\n\n- If `AGENTLOOP_ENABLE_RECALL` is not `true`, the CLI returns `error: null` and an empty `results` array.\n- If outbound confirmation is missing, the CLI returns an error and does not read credentials or call the endpoint.\n- If executing `scripts\u002Fsearch_context.js` directly fails because the environment strips executable bits or mounts the skill as non-executable, rerun the same command with `node scripts\u002Fsearch_context.js`.\n- If configuration is missing or invalid, the CLI returns a JSON object with `error` populated and `results: []`.\n- If recall returns no relevant results, continue the original task without blocking.\n- If recalled content conflicts with the current repository, logs, or user request, trust the current evidence.\n\nAuth:\n- Read from `recall.env`.\n- Never pass AK, SK, bearer token, or other secret material through CLI arguments.\n- Use HTTPS endpoints for real credentials. HTTP is accepted only for localhost.\n\nRead `references\u002Fsearch-context-cli.md` only when you need the exact config precedence, HTTP contract, endpoint security rules, or response normalization details. Read `references\u002Fram-policies.md` only when you need the permission and data-flow declaration.\n","# AgentLoop Recall\n\nUse this skill proactively — **recall prior experience first**. Before you start analyzing or implementing, make recalling prior AgentLoop experience one of your very first actions, using the local CLI at `scripts\u002Fsearch_context.js`.\nThe CLI reads auth and endpoint configuration from `recall.env`; never pass tokens or secrets as CLI arguments.\n\nFavor using this skill when the user mentions prior experience, similar cases, historical fixes, previous incidents, old runbooks, lessons learned, or asks to avoid repeating past mistakes. The request does not need to use the exact words \"recall\" or \"experience\"; phrases like \"有没有类似\", \"以前怎么处理\", \"先参考过去\", \"少走弯路\", \"look up old notes\", or \"anything we learned before\" are enough.\n\nCurrent scope: only `experience` context is supported. `memory` context is reserved for a future rollout and should not be used in prompts, examples, or evals.\n\n## Prerequisites\n\nInstall Node.js 18 or later. The script uses only Node.js built-in modules and does not require npm packages.\n\nConfigure recall credentials and endpoint in `~\u002F.agentloop\u002Frecall.env`, the nearest project `.agentloop\u002Frecall.env`, or process environment variables. Use `assets\u002Frecall.env.example` as the template.\n\n## Workflow\n\n1. Before any recall call, ensure the user has approved sending the query text to the configured AgentLoop Recall endpoint. Treat the current request as approval for a matching query when it asks or implies checking prior work, including \"先查\", \"看看之前\", \"有没有类似\", \"参考历史\", \"回忆案例\", \"avoid repeating past mistakes\", or similar wording.\n2. After approval, strongly prefer to recall up front: run recall at least once before choosing an implementation path, and again whenever you hit a non-trivial obstacle or change your approach. Recall whenever the current task includes a concrete service, error, incident, operation, migration, performance issue, or debugging goal and prior experience could plausibly help. Run the CLI with `node scripts\u002Fsearch_context.js`, not with `bash`. Include `--confirm-outbound` in the CLI command.\n3. For later debugging, ask for approval again if the new query would transmit materially different task data, then call recall with a focused query based on the concrete error, case, service, API, file path, or observed symptom.\n4. Use returned results as context only. Verify recalled content against the current repository, logs, and user request before acting on it.\n\nBuild concise queries. Include stable identifiers from the user request or tool output, such as service name, request id, case id, error text, API action, benchmark, module, or goal. Do not invent identifiers.\n\nIf the request is mildly underspecified but the service, symptom, or goal is clear, build the best concise query from the available facts and use defaults (`--limit 5`, `--threshold 0.6`, `--filter-json '{}'`). Ask a clarifying question only when there is no usable query target or when multiple materially different recall directions are equally likely.\n\nIf recall fails or returns no results, continue the original task. Treat recalled content as helpful context, not as authority; verify it against the current repository, logs, and user request.\n\n## CLI\n\nRun:\n\n```bash\nnode scripts\u002Fsearch_context.js search \\\n  --query \"current task, error, case, service, or goal\" \\\n  --context-type experience \\\n  --confirm-outbound \\\n  --limit 5 \\\n  --threshold 0.6 \\\n  --filter-json '{}'\n```\n\nRequired:\n- `--query string`\n- `--context-type experience`\n- `--confirm-outbound` after explicit user approval to transmit query data\n\nOptional:\n- `--limit integer` defaults to `5`\n- `--threshold number` defaults to `0.6`\n- `--filter-json object-as-json-string` defaults to `{}`\n\n## Input Example\n\n```bash\nnode scripts\u002Fsearch_context.js search \\\n  --query \"ECS SSH connection timeout after security group change\" \\\n  --context-type experience \\\n  --confirm-outbound \\\n  --limit 5 \\\n  --threshold 0.6 \\\n  --filter-json '{\"product\":\"ecs\"}'\n```\n\n## Output Example\n\nOutput is always JSON:\n\n```json\n{\n  \"request_id\": \"...\",\n  \"error\": null,\n  \"results\": [\n    {\n      \"title\": \"...\",\n      \"summary\": \"...\",\n      \"content\": \"...\",\n      \"metadata\": {}\n    }\n  ]\n}\n```\n\n## Edge Cases\n\n- If `AGENTLOOP_ENABLE_RECALL` is not `true`, the CLI returns `error: null` and an empty `results` array.\n- If outbound confirmation is missing, the CLI returns an error and does not read credentials or call the endpoint.\n- If executing `scripts\u002Fsearch_context.js` directly fails because the environment strips executable bits or mounts the skill as non-executable, rerun the same command with `node scripts\u002Fsearch_context.js`.\n- If configuration is missing or invalid, the CLI returns a JSON object with `error` populated and `results: []`.\n- If recall returns no relevant results, continue the original task without blocking.\n- If recalled content conflicts with the current repository, logs, or user request, trust the current evidence.\n\nAuth:\n- Read from `recall.env`.\n- Never pass AK, SK, bearer token, or other secret material through CLI arguments.\n- Use HTTPS endpoints for real credentials. HTTP is accepted only for localhost.\n\nRead `references\u002Fsearch-context-cli.md` only when you need the exact config precedence, HTTP contract, endpoint security rules, or response normalization details. Read `references\u002Fram-policies.md` only when you need the permission and data-flow declaration.\n",{"name":5,"license":15,"metadata":24,"description":28,"compatibility":29},{"owner":25,"domain":26,"contact":27},"cloud-skills-cloudnative","coding","cloud-skills-cloudnative@alibaba-inc.com","Proactively use AgentLoop Recall to retrieve prior Alibaba Cloud AgentLoop experience through the bundled SearchContext CLI whenever the user asks or implies that prior work may help. Trigger for requests to check, search, recall, retrieve, look up, review, consult, reference, or compare prior experience, historical troubleshooting cases, past fixes, comparable incidents, lessons learned, old runbooks, previous remediations, or successful workflows before or during work. Also trigger for Chinese requests such as 先查历史经验、回忆类似案例、召回过往排障记录、看看之前有没有处理过类似问题、 参考以前怎么处理、找找之前的踩坑记录、翻一下历史排障、有没有类似经验、先看看过去的案例.\n","Requires Node.js 18 or later and network access to the configured AgentLoop Recall or SearchContext endpoint. Intended for qwen-code, qoder, and openclaw.\n","main","b08d387cde83fdd23ca4a75f0a74173f810967ec","resources\u002Fecosystem\u002Fupstream\u002Faliyun-aiops-skills\u002Fd22aa735c7e5\u002Fskills\u002Faiml\u002Fagentloop\u002Falibabacloud-agentloop-experience","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O","https:\u002F\u002Fjane-zz.me\u002F","金张政 Jane-zz | Agent Engineer · AI Native Builder | Runtime · Context · Evals · GraphRAG | 官方作品集 jane-zz.me","2026-10-04 16:27:52",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Jane-o-O-o-O\u002Fpersonal-agent --skill alibabacloud-agentloop-experience",{"tool":44,"command":45},"bunx","bunx skills add Jane-o-O-o-O\u002Fpersonal-agent --skill alibabacloud-agentloop-experience",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Jane-o-O-o-O\u002Fpersonal-agent --skill alibabacloud-agentloop-experience","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Faliyun-aiops-skills\u002Fd22aa735c7e5\u002Fskills\u002Faiml\u002Fagentloop\u002Falibabacloud-agentloop-experience\u002FSKILL.md",true,[52,58,64,68],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Frecall.env.example","ASSET","资产文件",163,"https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Faliyun-aiops-skills\u002Fd22aa735c7e5\u002Fskills\u002Faiml\u002Fagentloop\u002Falibabacloud-agentloop-experience\u002Fassets\u002Frecall.env.example",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fram-policies.md","REFERENCE","参考文档",1449,"https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Faliyun-aiops-skills\u002Fd22aa735c7e5\u002Fskills\u002Faiml\u002Fagentloop\u002Falibabacloud-agentloop-experience\u002Freferences\u002Fram-policies.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fsearch-context-cli.md",4302,"https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Faliyun-aiops-skills\u002Fd22aa735c7e5\u002Fskills\u002Faiml\u002Fagentloop\u002Falibabacloud-agentloop-experience\u002Freferences\u002Fsearch-context-cli.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fsearch_context.js","SCRIPT","脚本",15126,"https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Faliyun-aiops-skills\u002Fd22aa735c7e5\u002Fskills\u002Faiml\u002Fagentloop\u002Falibabacloud-agentloop-experience\u002Fscripts\u002Fsearch_context.js",[75,83,90,97,104,111],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7EA3ZT5SZYH1DMJ9XHGK0JK","style-extract","Analyze Yuque documents to extract vocabulary, sentence, and tone patterns into a reusable writing-style profile. Use when the user wants to understand or reproduce their voice or keep documents consistent; trigger phrases include “分析一下我的写作风格”, “用我的风格写一篇...”, “帮我生成一个风格画像”, “extract my writing style”, and “write like me”.","MIT","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Fyuque-skills\u002F2959228ad3e8\u002Fskills\u002Fstyle-extract\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7EA3TK8GT3V1E166QX3B0G0","stale-detector","Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving. Use when the user is cleaning up, maintaining, or periodically reviewing a knowledge base; trigger phrases include “帮我检查哪些文档过期了”, “知识库体检”, and “find stale docs”.","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Fyuque-skills\u002F2959228ad3e8\u002Fskills\u002Fstale-detector\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7EA3PEWR596VVPAN0XW3ZFR","smart-summary","Summarize a Yuque document or knowledge base at one-line, key-point, or detailed granularity. Use when the user wants a quick overview of a document or repo; trigger phrases include “帮我总结一下这篇文档”, “这个知识库讲了什么”, and “summarize this doc”.","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Fyuque-skills\u002F2959228ad3e8\u002Fskills\u002Fsmart-summary\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7EA3JCBX7BVSSF0TEZXDJ47","smart-search","Search personal Yuque knowledge bases with natural-language queries and synthesize answers with source links. Use when the user wants to find information in their own documents; trigger phrases include “搜一下我的文档”, “我的知识库里有没有...”, “搜索我的语雀\u002F知识库”, and “search my Yuque”.","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Fyuque-skills\u002F2959228ad3e8\u002Fskills\u002Fsmart-search\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7EA3DDETPJYVCDHAXFBRRG6","reading-digest","Extract core insights, golden quotes, and action items from articles, then create structured Yuque reading notes. Use when the user wants key takeaways or a personal reading-notes base; trigger phrases include “帮我做阅读笔记”, “读书笔记”, and “extract key points from this article”.","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Fyuque-skills\u002F2959228ad3e8\u002Fskills\u002Freading-digest\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7EA37RF6AY0KCX9KQC1Q2YY","note-refine","Polish rough Yuque notes into structured, readable documents while preserving their meaning. Use when the user wants to clean up a draft, improve layout, or turn fragments into a document; trigger phrases include “帮我整理一下这篇笔记”, “把这个文档排版优化一下”, and “polish my notes”.","https:\u002F\u002Fgithub.com\u002FJane-o-O-o-O\u002Fpersonal-agent\u002Fblob\u002Fmain\u002Fresources\u002Fecosystem\u002Fupstream\u002Fyuque-skills\u002F2959228ad3e8\u002Fskills\u002Fnote-refine\u002FSKILL.md",[],[]]