[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79794754P45ZVSJGFH71BQF":3,"skill-same:01M79794754P45ZVSJGFH71BQF":44},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M79794754P45ZVSJGFH71BQF","web-research",null,"Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.","cantwakeup\u002FTongAgent4pre","cantwakeup","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F150812264?v=4","01M797770TZEZP30VCFT7J1S6G","Ye Song","01M797771E0VKYGCT74GSSKR61",0,"MIT","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcli\u002Fexamples\u002Fskills\u002Fweb-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: web-research\ndescription: Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.\n---\n\n# Web Research Skill\n\n## Research Process\n\n### Step 1: Create and Save Research Plan\n\nBefore delegating to subagents, you MUST:\n\n1. **Create a research folder** - Organize all research files in a dedicated folder relative to the current working directory:\n   ```\n   mkdir research_[topic_name]\n   ```\n   This keeps files organized and prevents clutter in the working directory.\n\n2. **Analyze the research question** - Break it down into distinct, non-overlapping subtopics\n\n3. **Write a research plan file** - Use the `write_file` tool to create `research_[topic_name]\u002Fresearch_plan.md` containing:\n   - The main research question\n   - 2-5 specific subtopics to investigate\n   - Expected information from each subtopic\n   - How results will be synthesized\n\n**Planning Guidelines:**\n- **Simple fact-finding**: 1-2 subtopics\n- **Comparative analysis**: 1 subtopic per comparison element (max 3)\n- **Complex investigations**: 3-5 subtopics\n\n### Step 2: Delegate to Research Subagents\n\nFor each subtopic in your plan:\n\n1. **Use the `task` tool** to spawn a research subagent with:\n   - Clear, specific research question (no acronyms)\n   - Instructions to write findings to a file: `research_[topic_name]\u002Ffindings_[subtopic].md`\n   - Budget: 3-5 web searches maximum\n\n2. **Run up to 3 subagents in parallel** for efficient research\n\n**Subagent Instructions Template:**\n```\nResearch [SPECIFIC TOPIC]. Use the web_search tool to gather information.\nAfter completing your research, use write_file to save your findings to research_[topic_name]\u002Ffindings_[subtopic].md.\nInclude key facts, relevant quotes, and source URLs.\nUse 3-5 web searches maximum.\n```\n\n### Step 3: Synthesize Findings\n\nAfter all subagents complete:\n\n1. **Review the findings files** that were saved locally:\n   - First run `list_files research_[topic_name]` to see what files were created\n   - Then use `read_file` with the **file paths** (e.g., `research_[topic_name]\u002Ffindings_*.md`)\n   - **Important**: Use `read_file` for LOCAL files only, not URLs\n\n2. **Synthesize the information** - Create a comprehensive response that:\n   - Directly answers the original question\n   - Integrates insights from all subtopics\n   - Cites specific sources with URLs (from the findings files)\n   - Identifies any gaps or limitations\n\n3. **Write final report** (optional) - Use `write_file` to create `research_[topic_name]\u002Fresearch_report.md` if requested\n\n**Note**: If you need to fetch additional information from URLs, use the `fetch_url` tool, not `read_file`.\n\n## Best Practices\n\n- **Plan before delegating** - Always write research_plan.md first\n- **Clear subtopics** - Ensure each subagent has distinct, non-overlapping scope\n- **File-based communication** - Have subagents save findings to files, not return them directly\n- **Systematic synthesis** - Read all findings files before creating final response\n- **Stop appropriately** - Don't over-research; 3-5 searches per subtopic is usually sufficient\n","# Web Research Skill\n\n## Research Process\n\n### Step 1: Create and Save Research Plan\n\nBefore delegating to subagents, you MUST:\n\n1. **Create a research folder** - Organize all research files in a dedicated folder relative to the current working directory:\n   ```\n   mkdir research_[topic_name]\n   ```\n   This keeps files organized and prevents clutter in the working directory.\n\n2. **Analyze the research question** - Break it down into distinct, non-overlapping subtopics\n\n3. **Write a research plan file** - Use the `write_file` tool to create `research_[topic_name]\u002Fresearch_plan.md` containing:\n   - The main research question\n   - 2-5 specific subtopics to investigate\n   - Expected information from each subtopic\n   - How results will be synthesized\n\n**Planning Guidelines:**\n- **Simple fact-finding**: 1-2 subtopics\n- **Comparative analysis**: 1 subtopic per comparison element (max 3)\n- **Complex investigations**: 3-5 subtopics\n\n### Step 2: Delegate to Research Subagents\n\nFor each subtopic in your plan:\n\n1. **Use the `task` tool** to spawn a research subagent with:\n   - Clear, specific research question (no acronyms)\n   - Instructions to write findings to a file: `research_[topic_name]\u002Ffindings_[subtopic].md`\n   - Budget: 3-5 web searches maximum\n\n2. **Run up to 3 subagents in parallel** for efficient research\n\n**Subagent Instructions Template:**\n```\nResearch [SPECIFIC TOPIC]. Use the web_search tool to gather information.\nAfter completing your research, use write_file to save your findings to research_[topic_name]\u002Ffindings_[subtopic].md.\nInclude key facts, relevant quotes, and source URLs.\nUse 3-5 web searches maximum.\n```\n\n### Step 3: Synthesize Findings\n\nAfter all subagents complete:\n\n1. **Review the findings files** that were saved locally:\n   - First run `list_files research_[topic_name]` to see what files were created\n   - Then use `read_file` with the **file paths** (e.g., `research_[topic_name]\u002Ffindings_*.md`)\n   - **Important**: Use `read_file` for LOCAL files only, not URLs\n\n2. **Synthesize the information** - Create a comprehensive response that:\n   - Directly answers the original question\n   - Integrates insights from all subtopics\n   - Cites specific sources with URLs (from the findings files)\n   - Identifies any gaps or limitations\n\n3. **Write final report** (optional) - Use `write_file` to create `research_[topic_name]\u002Fresearch_report.md` if requested\n\n**Note**: If you need to fetch additional information from URLs, use the `fetch_url` tool, not `read_file`.\n\n## Best Practices\n\n- **Plan before delegating** - Always write research_plan.md first\n- **Clear subtopics** - Ensure each subagent has distinct, non-overlapping scope\n- **File-based communication** - Have subagents save findings to files, not return them directly\n- **Systematic synthesis** - Read all findings files before creating final response\n- **Stop appropriately** - Don't over-research; 3-5 searches per subtopic is usually sufficient\n",{"name":5,"description":7},"main","a3b2db2cea7e34c75671308ff00219c6147b01f0","libs\u002Fcli\u002Fexamples\u002Fskills\u002Fweb-research","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre","https:\u002F\u002Fgithub.com\u002Fcantwakeup","2026-08-31 20:25:48",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add cantwakeup\u002FTongAgent4pre --skill web-research",{"tool":36,"command":37},"bunx","bunx skills add cantwakeup\u002FTongAgent4pre --skill web-research",{"tool":39,"command":40},"pnpm","pnpm dlx skills add cantwakeup\u002FTongAgent4pre --skill web-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcli\u002Fexamples\u002Fskills\u002Fweb-research\u002FSKILL.md",true,[],[45,50,57,64,71,76],{"skillNo":46,"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":47,"categories":48,"keywords":49,"publishedAt":19},"01M797A07KAHW35Y5BZ68TZV5S","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcode\u002Fexamples\u002Fskills\u002Fweb-research\u002FSKILL.md",[],[],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7979SNHSG1AA13NCTSXDBZ7","skill-creator","Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\".","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcode\u002Fexamples\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7979NTRPV8KA01M0WBW0CHB","langgraph-docs","Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcode\u002Fexamples\u002Fskills\u002Flanggraph-docs\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7979KMBR1C1WXYQQT2N1996","arxiv-search","Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcode\u002Fexamples\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":72,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7979DBC6YGADWB7XRVY49T6","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcode\u002Fdeepagents_code\u002Fbuilt_in_skills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M79799CAJ1S8SGE9X9RARTQ3","remember","Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.","https:\u002F\u002Fgithub.com\u002Fcantwakeup\u002FTongAgent4pre\u002Fblob\u002Fmain\u002Flibs\u002Fcode\u002Fdeepagents_code\u002Fbuilt_in_skills\u002Fremember\u002FSKILL.md",[],[]]