[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FVMW0KB7J6R8BNSYSXGFHT":3,"skill-same:01M6FVMW0KB7J6R8BNSYSXGFHT":102},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":74,"repositoryHtmlUrl":75,"repositoryHomepageUrl":6,"ownerHtmlUrl":76,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":77,"install":78,"resources":91},"01M6FVMW0KB7J6R8BNSYSXGFHT","clawdo",null,"The missing todo list for AI agents. Your agent has memory, cron jobs, and chat — but no way to say 'do this when you get to it.' clawdo is a persistent task queue that works in heartbeats, cron, pipes, and conversations. add → inbox → start → done.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Flepetitpince\u002Fclawdo\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"get","agent todo","heartbeat tasks","persistent tasks","agent tasks","task-management","conversations","you","todo list","ai agents","me","done","todo","autonomous","task management","inbox","tasks","workflow","memory","2026-11-10 10:12:30",false,"---\nname: clawdo\nversion: 1.1.3\nauthor: LePetitPince \u003Clepetitpince@proton.me>\nhomepage: https:\u002F\u002Fgithub.com\u002FLePetitPince\u002Fclawdo\ndescription: \"The missing todo list for AI agents. Your agent has memory, cron jobs, and chat — but no way to say 'do this when you get to it.' clawdo is a persistent task queue that works in heartbeats, cron, pipes, and conversations. add → inbox → start → done.\"\ntags:\n  - todo\n  - task-queue\n  - task-management\n  - agent-tools\n  - productivity\n  - heartbeat\n  - workflow\n  - autonomous\nkeywords:\n  - todo list\n  - task queue\n  - todo\n  - tasks\n  - agent tasks\n  - persistent tasks\n  - heartbeat tasks\n  - agent todo\n  - task management\n  - agent workflow\n  - autonomous execution\n  - agent collaboration\ncategories:\n  - productivity\n  - agent-tools\n  - workflow\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"?\",\n        \"requires\": { \"bins\": [\"clawdo\"] },\n        \"install\":\n          [\n            {\n              \"id\": \"npm\",\n              \"kind\": \"npm\",\n              \"package\": \"clawdo\",\n              \"bins\": [\"clawdo\"],\n              \"label\": \"Install clawdo (npm global)\",\n            },\n          ],\n      },\n  }\n---\n\n# ? clawdo — The missing todo list for AI agents\n\nYour agent has memory files, cron jobs, and chat. It has no todo list.\n\nNo way to say **\"do this when you get to it.\"** Not \"do this at 14:00 UTC.\" Not \"do this right now in this conversation.\" Just... remember to do it. Track it. Pick it up when there's a gap.\n\nThat's clawdo.\n\n## Install\n\n```bash\nclawhub install clawdo    # installs skill + docs into your workspace\nnpm install -g clawdo     # install the CLI binary\n```\n\n**Requirements:** Node.js ≥18\n\n## Quick Start\n\n```bash\n# Capture a task\nclawdo add \"update dependencies\" --urgency soon\n\n# Agent checks its queue (heartbeat, cron, conversation — wherever)\nclawdo inbox --format json\n\n# Agent works it\nclawdo start a3f2\nclawdo done a3f2 --json\n```\n\n`add → inbox → start → done`. Persistent state in SQLite. Every command has `--json` so agents parse structured output, not terminal art.\n\n## Where it fits\n\nclawdo works everywhere agents work:\n\n- **Heartbeat loops** — \"anything in my queue? let me do it between checks\"\n- **Cron jobs** — \"every hour, process one task\"\n- **Conversations** — \"J mentioned fixing the auth module, let me capture that\"\n- **Pipes and sub-agents** — non-TTY safe, no interactive prompts\n\n### Heartbeat integration example\n\n```bash\n# In HEARTBEAT.md — runs every ~30 minutes\nTASKS=$(clawdo inbox --format json)\nAUTO=$(echo \"$TASKS\" | jq '.autoReady | length')\n\nif [ \"$AUTO\" -gt 0 ]; then\n  TASK=$(clawdo next --auto --json | jq -r '.task.id')\n  clawdo start \"$TASK\" --json\n  # ... do the work ...\n  clawdo done \"$TASK\" --json\nfi\n```\n\n## Autonomy levels\n\nTasks can be tagged with permission tiers that control what the agent is allowed to do unsupervised:\n\n| Level | Time Limit | What it means |\n|-------|------------|---------------|\n| **auto** | 10 min | Agent does it silently. Fix a typo, run tests. |\n| **auto-notify** | 30 min | Agent does it, tells the human when done. |\n| **collab** | Unlimited | Human required. Complex, risky, or ambiguous. |\n\nDefault: `collab` (safe).\n\n**Key rule:** Autonomy is a permission, not a suggestion. Once set, agents can't change it. If an agent fails 3 times, autonomy *demotes* to `collab`. Safety only moves down, never up.\n\n**Agents propose, humans approve.** Agent tasks always start as `proposed`. The human runs `clawdo confirm \u003Cid>` or it doesn't happen.\n\n## Usage\n\n### For humans\n\n```bash\n# Add tasks — inline metadata parsing\nclawdo add \"deploy new API +backend auto-notify now\"\n#           └── text ──────┘ └project┘ └─level──┘ └urg┘\n\n# View\nclawdo list                       # active tasks\nclawdo list --status proposed     # agent suggestions\nclawdo next                       # highest priority\n\n# Review agent proposals\nclawdo confirm \u003Cid>               # approve\nclawdo reject \u003Cid>                # reject\n\n# Work\nclawdo start \u003Cid>\nclawdo done \u003Cid>\nclawdo done abc,def,ghi           # complete several\n```\n\n### For agents\n\n```bash\n# Check inbox (structured)\nclawdo inbox --format json\n\n# Propose work\nclawdo propose \"add input validation\" --level auto --json\n\n# Execute\nTASK=$(clawdo next --auto --json | jq -r '.task.id \u002F\u002F empty')\nif [ -n \"$TASK\" ]; then\n  clawdo start \"$TASK\" --json\n  # ... do the work ...\n  clawdo done \"$TASK\" --json\nfi\n```\n\nThe inbox returns: `autoReady`, `autoNotifyReady`, `urgent`, `overdue`, `proposed`, `stale`, `blocked`.\n\n## Inline syntax\n\n```bash\nclawdo add \"fix auth bug +backend @code auto soon\"\n```\n\n- `+word` → project\n- `@word` → context\n- `auto` \u002F `auto-notify` \u002F `collab` → autonomy level\n- `now` \u002F `soon` \u002F `whenever` \u002F `someday` → urgency\n- `due:YYYY-MM-DD` → due date\n\n## Security\n\n- **Immutable autonomy** — agents cannot escalate permissions\n- **Proposal limits** — max 5 active, 60s cooldown\n- **Prompt injection defense** — input sanitization, parameterized SQL\n- **Audit trail** — append-only log of every state change\n- **Secure IDs** — `crypto.randomInt()`, no modulo bias\n\n## Resources\n\n- **GitHub:** https:\u002F\u002Fgithub.com\u002FLePetitPince\u002Fclawdo\n- **npm:** https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fclawdo\n- **Full docs:** `clawdo --help`\n\n## License\n\nMIT\n","# ? clawdo — The missing todo list for AI agents\n\nYour agent has memory files, cron jobs, and chat. It has no todo list.\n\nNo way to say **\"do this when you get to it.\"** Not \"do this at 14:00 UTC.\" Not \"do this right now in this conversation.\" Just... remember to do it. Track it. Pick it up when there's a gap.\n\nThat's clawdo.\n\n## Install\n\n```bash\nclawhub install clawdo    # installs skill + docs into your workspace\nnpm install -g clawdo     # install the CLI binary\n```\n\n**Requirements:** Node.js ≥18\n\n## Quick Start\n\n```bash\n# Capture a task\nclawdo add \"update dependencies\" --urgency soon\n\n# Agent checks its queue (heartbeat, cron, conversation — wherever)\nclawdo inbox --format json\n\n# Agent works it\nclawdo start a3f2\nclawdo done a3f2 --json\n```\n\n`add → inbox → start → done`. Persistent state in SQLite. Every command has `--json` so agents parse structured output, not terminal art.\n\n## Where it fits\n\nclawdo works everywhere agents work:\n\n- **Heartbeat loops** — \"anything in my queue? let me do it between checks\"\n- **Cron jobs** — \"every hour, process one task\"\n- **Conversations** — \"J mentioned fixing the auth module, let me capture that\"\n- **Pipes and sub-agents** — non-TTY safe, no interactive prompts\n\n### Heartbeat integration example\n\n```bash\n# In HEARTBEAT.md — runs every ~30 minutes\nTASKS=$(clawdo inbox --format json)\nAUTO=$(echo \"$TASKS\" | jq '.autoReady | length')\n\nif [ \"$AUTO\" -gt 0 ]; then\n  TASK=$(clawdo next --auto --json | jq -r '.task.id')\n  clawdo start \"$TASK\" --json\n  # ... do the work ...\n  clawdo done \"$TASK\" --json\nfi\n```\n\n## Autonomy levels\n\nTasks can be tagged with permission tiers that control what the agent is allowed to do unsupervised:\n\n| Level | Time Limit | What it means |\n|-------|------------|---------------|\n| **auto** | 10 min | Agent does it silently. Fix a typo, run tests. |\n| **auto-notify** | 30 min | Agent does it, tells the human when done. |\n| **collab** | Unlimited | Human required. Complex, risky, or ambiguous. |\n\nDefault: `collab` (safe).\n\n**Key rule:** Autonomy is a permission, not a suggestion. Once set, agents can't change it. If an agent fails 3 times, autonomy *demotes* to `collab`. Safety only moves down, never up.\n\n**Agents propose, humans approve.** Agent tasks always start as `proposed`. The human runs `clawdo confirm \u003Cid>` or it doesn't happen.\n\n## Usage\n\n### For humans\n\n```bash\n# Add tasks — inline metadata parsing\nclawdo add \"deploy new API +backend auto-notify now\"\n#           └── text ──────┘ └project┘ └─level──┘ └urg┘\n\n# View\nclawdo list                       # active tasks\nclawdo list --status proposed     # agent suggestions\nclawdo next                       # highest priority\n\n# Review agent proposals\nclawdo confirm \u003Cid>               # approve\nclawdo reject \u003Cid>                # reject\n\n# Work\nclawdo start \u003Cid>\nclawdo done \u003Cid>\nclawdo done abc,def,ghi           # complete several\n```\n\n### For agents\n\n```bash\n# Check inbox (structured)\nclawdo inbox --format json\n\n# Propose work\nclawdo propose \"add input validation\" --level auto --json\n\n# Execute\nTASK=$(clawdo next --auto --json | jq -r '.task.id \u002F\u002F empty')\nif [ -n \"$TASK\" ]; then\n  clawdo start \"$TASK\" --json\n  # ... do the work ...\n  clawdo done \"$TASK\" --json\nfi\n```\n\nThe inbox returns: `autoReady`, `autoNotifyReady`, `urgent`, `overdue`, `proposed`, `stale`, `blocked`.\n\n## Inline syntax\n\n```bash\nclawdo add \"fix auth bug +backend @code auto soon\"\n```\n\n- `+word` → project\n- `@word` → context\n- `auto` \u002F `auto-notify` \u002F `collab` → autonomy level\n- `now` \u002F `soon` \u002F `whenever` \u002F `someday` → urgency\n- `due:YYYY-MM-DD` → due date\n\n## Security\n\n- **Immutable autonomy** — agents cannot escalate permissions\n- **Proposal limits** — max 5 active, 60s cooldown\n- **Prompt injection defense** — input sanitization, parameterized SQL\n- **Audit trail** — append-only log of every state change\n- **Secure IDs** — `crypto.randomInt()`, no modulo bias\n\n## Resources\n\n- **GitHub:** https:\u002F\u002Fgithub.com\u002FLePetitPince\u002Fclawdo\n- **npm:** https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fclawdo\n- **Full docs:** `clawdo --help`\n\n## License\n\nMIT\n",{"name":5,"tags":47,"author":52,"version":53,"homepage":54,"keywords":55,"metadata":60,"categories":70,"description":7},[35,48,28,49,50,51,40,36],"task-queue","agent-tools","productivity","heartbeat","LePetitPince \u003Clepetitpince@proton.me>","1.1.3","https:\u002F\u002Fgithub.com\u002FLePetitPince\u002Fclawdo",[31,56,35,39,27,26,25,24,37,57,58,59],"task queue","agent workflow","autonomous execution","agent collaboration",{"openclaw":61},{"emoji":62,"install":63,"requires":68},"?",[64],{"id":65,"bins":66,"kind":65,"label":67,"package":5},"npm",[5],"Install clawdo (npm global)",{"bins":69},[5],[50,49,40],"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Flepetitpince\u002Fclawdo",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":79,"prompt":89,"zipAvailable":90},[80,83,86],{"tool":81,"command":82},"npx","npx skills add kbarbel640-del\u002Fskills --skill clawdo",{"tool":84,"command":85},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill clawdo",{"tool":87,"command":88},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill clawdo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Flepetitpince\u002Fclawdo\u002FSKILL.md",true,[92,98],{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"_meta.json","REFERENCE","参考文档",309,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Flepetitpince\u002Fclawdo\u002F_meta.json",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"README.md",1167,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Flepetitpince\u002Fclawdo\u002FREADME.md",[103,132,157,178,184,203],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":114,"publishedAt":42},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[109],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[115,116,117,118,119,120,121,122,123,124,125,126,127,128,50,129,130,131,32],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","marketplace","https","content",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":42},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[138],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[140,117,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,122,156],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":166,"publishedAt":42},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[163],{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[167,168,169,170,171,172,173,118,174,154,156,175,117,176,177],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":179,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":42},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[182],{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},[170,169,168,167,177,172,173,118,171,154,156,174,175,117,176],{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":42},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[191,192,193,194,195,196,197,198,199,200,201,23,202],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","branches",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":213,"publishedAt":42},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[209,210],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":211,"categoryName":212,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000037","律师与法务",[214,215,216,217,118,218,219,71,220,175,221,222,223,224,225,130,226,227,228],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]