[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NTRABXEBBRQAFT84CJHRAV":3,"skill-same:01M6NTRABXEBBRQAFT84CJHRAV":55},{"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":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M6NTRABXEBBRQAFT84CJHRAV","todo",null,"Track multi-step and sequential tasks via workspace TODO.md","timainge\u002Fpicobot","timainge","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2209642?v=4","01M6NTM4VK8EKZ6V0JZW7CAXHJ","Tim Ainge","01M6NTM4ZFXY9DFSKFPWB07TMD",1,"MIT","https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Ftodo\u002FSKILL.md",[],[5,19,20,21,22,23,24],"tasks","workspace","via","multi","true","track","2026-11-10 10:12:30",false,"---\nname: todo\ndescription: Track multi-step and sequential tasks via workspace TODO.md\nmetadata: '{\"picobot\": {\"always\": true}}'\n---\n\n# Todo List\n\nUse `TODO.md` in the workspace root to track tasks that span multiple turns or involve sequential steps. TODO.md is injected into your system prompt every turn, so plans written here survive context truncation.\n\n## When to use\n\n- **Multi-step tasks** (3+ steps, multiple tool calls)\n- **Sub-agent delegation** (track what was spawned and what to do with results)\n- **Sequential work** where order matters\n- **Cross-turn tasks** that may take multiple conversation turns\n- **Anything you need to remember** across context boundaries\n\nDo NOT use for one-off questions or single-step tasks.\n\n## File format\n\n```markdown\n## Task Title\n\n- [ ] First step\n- [ ] Second step (spawned: sub-agent \"label\")\n- [x] Completed step\n\n## Another Task\n\n- [ ] Independent item\n```\n\nEach task is a `## heading` with `- [ ]` checkbox items underneath.\n\n## Workflow\n\n1. **Before complex work**: Read TODO.md, add a `## heading` with broken-down steps.\n2. **Completing a step**: Change `- [ ]` to `- [x]`.\n3. **Finishing a task**: When all items are checked, remove the entire section.\n4. **Checking status**: Read TODO.md to see what's pending.\n\n## Sub-agent tracking pattern\n\nWhen spawning sub-agents, anchor each one to a TODO item:\n\n```markdown\n## Analyze projects\n\n- [ ] canvas-it (spawned: \"Analyze canvas-it\") → store summary in KB\n- [ ] contribart (spawned: \"Analyze contribart\") → store summary in KB\n- [x] crush-tabs — done, stored in KB\n```\n\nThis pattern ensures:\n- You know which sub-agents are outstanding\n- You know what to do when results arrive (the \"→ action\" note)\n- Instructions survive context truncation because TODO.md is always re-read\n\n## Planning before acting\n\nIf a task involves creating new resources (skills, KB entries, files):\n1. **Search first** — check if something similar already exists (`kb search`, `list_dir`)\n2. **Plan in TODO** — write the steps before executing\n3. **Execute** — work through items, checking them off\n4. **Clean up** — remove the TODO section when done\n\nKeep the file clean — remove completed task sections promptly.\n","# Todo List\n\nUse `TODO.md` in the workspace root to track tasks that span multiple turns or involve sequential steps. TODO.md is injected into your system prompt every turn, so plans written here survive context truncation.\n\n## When to use\n\n- **Multi-step tasks** (3+ steps, multiple tool calls)\n- **Sub-agent delegation** (track what was spawned and what to do with results)\n- **Sequential work** where order matters\n- **Cross-turn tasks** that may take multiple conversation turns\n- **Anything you need to remember** across context boundaries\n\nDo NOT use for one-off questions or single-step tasks.\n\n## File format\n\n```markdown\n## Task Title\n\n- [ ] First step\n- [ ] Second step (spawned: sub-agent \"label\")\n- [x] Completed step\n\n## Another Task\n\n- [ ] Independent item\n```\n\nEach task is a `## heading` with `- [ ]` checkbox items underneath.\n\n## Workflow\n\n1. **Before complex work**: Read TODO.md, add a `## heading` with broken-down steps.\n2. **Completing a step**: Change `- [ ]` to `- [x]`.\n3. **Finishing a task**: When all items are checked, remove the entire section.\n4. **Checking status**: Read TODO.md to see what's pending.\n\n## Sub-agent tracking pattern\n\nWhen spawning sub-agents, anchor each one to a TODO item:\n\n```markdown\n## Analyze projects\n\n- [ ] canvas-it (spawned: \"Analyze canvas-it\") → store summary in KB\n- [ ] contribart (spawned: \"Analyze contribart\") → store summary in KB\n- [x] crush-tabs — done, stored in KB\n```\n\nThis pattern ensures:\n- You know which sub-agents are outstanding\n- You know what to do when results arrive (the \"→ action\" note)\n- Instructions survive context truncation because TODO.md is always re-read\n\n## Planning before acting\n\nIf a task involves creating new resources (skills, KB entries, files):\n1. **Search first** — check if something similar already exists (`kb search`, `list_dir`)\n2. **Plan in TODO** — write the steps before executing\n3. **Execute** — work through items, checking them off\n4. **Clean up** — remove the TODO section when done\n\nKeep the file clean — remove completed task sections promptly.\n",{"name":5,"metadata":30,"description":7},"{\"picobot\": {\"always\": true}}","main","c79130fde6db4706071d5480e358a85ad1333439","picobot\u002Fskills\u002Ftodo",0,"https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot","https:\u002F\u002Ftimainge.github.io\u002Fpicobot\u002F","https:\u002F\u002Fgithub.com\u002Ftimainge","timainge.io","@timainge","2026-04-07 18:03:06",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add timainge\u002Fpicobot --skill todo",{"tool":47,"command":48},"bunx","bunx skills add timainge\u002Fpicobot --skill todo",{"tool":50,"command":51},"pnpm","pnpm dlx skills add timainge\u002Fpicobot --skill todo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Ftodo\u002FSKILL.md",true,[],[56,68,85,119,142,161],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":25},"01M6NTREXRWD018H2RFK7TN0QV","weather","Get current weather and forecasts (no API key required).","https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Fweather\u002FSKILL.md",[],[58,63,64,65,66,67],"get","curl","api","https","help",{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":25},"01M6NTQTCPWYJXP0TQYXDX5HYK","tmux","Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.","https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Ftmux\u002FSKILL.md",[],[70,75,76,77,78,79,80,81,82,83,84],"remote","darwin","for","remote-control","output","control","scraping","interactive","sessions","linux",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":99,"publishedAt":25},"01M6NTQM0HV6B8QQM3GJ9Y4HVE","test-automation","Write and run browser tests from natural language specifications. Supports functional tests, visual regression, and self-healing selectors. Use when asked to test a website, verify UI behavior, check for regressions, create a test suite, run automated tests, or validate that a page works correctly.","https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Ftest-automation\u002FSKILL.md",[91,96],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":97,"categoryName":98,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000023","Skill与智能体开发",[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,77,118],"test automation","test","automation","website","ui","suite","regression","page","write","test suite","self-healing","natural language","visual regression","browser","self","healing","run","functional","create",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":128,"publishedAt":25},"01M6NTQF3CVVD0PASYZXY99DYQ","summarize","Summarize or extract text\u002Ftranscripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube\u002Fvideo”).","https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Fsummarize\u002FSKILL.md",[125],{"categoryNo":126,"categoryName":127,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000021","资料检索与研究",[121,77,129,130,131,132,133,134,135,136,137,138,139,140,66,141],"extract","local files","transcripts","local","tap","fallback","youtube","files","install","brew","text","Video","transcribe",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":25},"01M6NTPYMP9W6MF306SJJ84X85","skill-creator","Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.","https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Fskill-creator\u002FSKILL.md",[148],{"categoryNo":97,"categoryName":98,"taxonomyType":94,"taxonomyTypeDesc":95},[150,151,152,153,154,155,156,157,118,158,159,160],"skill creator","creator","agentskills","references","use","packaging","assets","update","with scripts","with","scripts",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":25},"01M6NTPRV3GPQZJC5W6ATPW444","self-reflect","Analyze session history to extract patterns, corrections, and lessons learned","https:\u002F\u002Fgithub.com\u002Ftimainge\u002Fpicobot\u002Fblob\u002Fmain\u002Fpicobot\u002Fskills\u002Fself-reflect\u002FSKILL.md",[],[114,168,169,170,171,172,173,174,175,129,176,177],"reflect","self reflect","lessons learned","lessons","learned","session history","patterns","session","history","analyze"]