[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71R5N3KJEZH9F7H8KBDJDAQ":3,"skill-same:01M71R5N3KJEZH9F7H8KBDJDAQ":53},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M71R5N3KJEZH9F7H8KBDJDAQ","goal",null,"Create one durable objective that continues across scheduled turns until evidence proves it is done.","human-plus-machine\u002Fmonkeybot","human-plus-machine","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F280167390?v=4","01M71R5340DFF1C4XV5B369MPN","human plus machine","01M71R5357ZTPM4CKBNH5XNSFY",3,"MIT","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fcli\u002Fsrc\u002Fmonkeybot_cli\u002Fscaffold_defaults\u002Fgoal\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26],"create","evidence","done","across","it","scheduled","objective","one","2026-11-10 13:02:02",false,"---\nname: goal\ndescription: Create one durable objective that continues across scheduled turns until evidence proves it is done.\n---\n\n# Goal\n\nUse this skill only when the user explicitly invokes `\u002Fgoal` with an objective\nthat may require multiple turns.\n\nA goal is complete only when current evidence proves every requirement of the\nobjective. Stopping a turn, running out of time, or having a plausible answer\ndoes not finish it.\n\nThere is no deadline that finishes the work. The goal stays active across turns\nuntil the end state is true, or until a budget pause or a persistent failure\nstops the ticks. A budget pause is not completion. The objective stays intact\nand the user can resume it.\n\n## Start\n\n1. Preserve the user's complete objective without narrowing its scope.\n2. Call `create_goal` exactly once with that objective.\n3. Do the first concrete increment of work in the same turn.\n4. Keep the returned goal id. Every `update_goal` call must include it.\n\n## Continue\n\n- Goal continuations are scheduled automatically. A webhook can also wake the goal.\n- Treat the stored objective as authoritative. Do not shrink it to work already done.\n- Make measurable progress. Verify results before you even consider completion.\n- Temporary session-busy deferrals are normal and are not goal failures.\n- Persistent execution failures stop the goal after the retry limit.\n- Using up the tick or runtime budget pauses the goal. It does not complete it.\n\n## Waiting\n\nIf you are blocked on a person or an external event (review, approval, CI, a\npublish), call `update_goal` with `status=\"waiting\"`, the goal id, and a\n`reason`. Pass `recheck_after` (for example `2h`) only when you should look\nagain even if no event arrives. Do not keep waking on the timer while blocked.\nYou cannot pause a goal. That is the user's control.\n\n## Complete\n\nBefore `update_goal` with `status=\"complete\"`, completion is unproven. In a\nseparate step, after the evidence tool calls:\n\n1. Pull concrete requirements out of the objective and anything it points at\n   (files, plans, specs, issues, instructions). Do not shrink the original scope.\n2. For each requirement, name the evidence that would prove it, then look at\n   the current state: files, command output, tests, pull-request state, rendered\n   UI, runtime behavior.\n3. Judge each item as `proved`, `contradicted`, `incomplete`, `too_weak`, or\n   `missing`. A green test counts only if it covers that requirement. Uncertain\n   or indirect evidence is not done.\n4. The audit has to prove completion. Failing to notice leftover work is not enough.\n\nIntent, partial progress, memory of earlier turns, and a reasonable-sounding\nanswer are not proof.\n\nCall `update_goal` with `status=\"complete\"` and an `audit` array only after\nevery item is `proved` and no required work remains. The call must be its own\nstep so the transcript already contains the evidence. Ending the turn does not\ncall `update_goal`. The goal stays active and the full objective stays intact.\n\n`status=\"active\"` is only for resuming a goal the user paused.\n","# Goal\n\nUse this skill only when the user explicitly invokes `\u002Fgoal` with an objective\nthat may require multiple turns.\n\nA goal is complete only when current evidence proves every requirement of the\nobjective. Stopping a turn, running out of time, or having a plausible answer\ndoes not finish it.\n\nThere is no deadline that finishes the work. The goal stays active across turns\nuntil the end state is true, or until a budget pause or a persistent failure\nstops the ticks. A budget pause is not completion. The objective stays intact\nand the user can resume it.\n\n## Start\n\n1. Preserve the user's complete objective without narrowing its scope.\n2. Call `create_goal` exactly once with that objective.\n3. Do the first concrete increment of work in the same turn.\n4. Keep the returned goal id. Every `update_goal` call must include it.\n\n## Continue\n\n- Goal continuations are scheduled automatically. A webhook can also wake the goal.\n- Treat the stored objective as authoritative. Do not shrink it to work already done.\n- Make measurable progress. Verify results before you even consider completion.\n- Temporary session-busy deferrals are normal and are not goal failures.\n- Persistent execution failures stop the goal after the retry limit.\n- Using up the tick or runtime budget pauses the goal. It does not complete it.\n\n## Waiting\n\nIf you are blocked on a person or an external event (review, approval, CI, a\npublish), call `update_goal` with `status=\"waiting\"`, the goal id, and a\n`reason`. Pass `recheck_after` (for example `2h`) only when you should look\nagain even if no event arrives. Do not keep waking on the timer while blocked.\nYou cannot pause a goal. That is the user's control.\n\n## Complete\n\nBefore `update_goal` with `status=\"complete\"`, completion is unproven. In a\nseparate step, after the evidence tool calls:\n\n1. Pull concrete requirements out of the objective and anything it points at\n   (files, plans, specs, issues, instructions). Do not shrink the original scope.\n2. For each requirement, name the evidence that would prove it, then look at\n   the current state: files, command output, tests, pull-request state, rendered\n   UI, runtime behavior.\n3. Judge each item as `proved`, `contradicted`, `incomplete`, `too_weak`, or\n   `missing`. A green test counts only if it covers that requirement. Uncertain\n   or indirect evidence is not done.\n4. The audit has to prove completion. Failing to notice leftover work is not enough.\n\nIntent, partial progress, memory of earlier turns, and a reasonable-sounding\nanswer are not proof.\n\nCall `update_goal` with `status=\"complete\"` and an `audit` array only after\nevery item is `proved` and no required work remains. The call must be its own\nstep so the transcript already contains the evidence. Ending the turn does not\ncall `update_goal`. The goal stays active and the full objective stays intact.\n\n`status=\"active\"` is only for resuming a goal the user paused.\n",{"name":5,"description":7},"develop","3f4ce06b117cf078c4edf4cd8041134d301404ac","cli\u002Fsrc\u002Fmonkeybot_cli\u002Fscaffold_defaults\u002Fgoal",2,"https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine","2026-11-13 06:42:26",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add human-plus-machine\u002Fmonkeybot --skill goal",{"tool":45,"command":46},"bunx","bunx skills add human-plus-machine\u002Fmonkeybot --skill goal",{"tool":48,"command":49},"pnpm","pnpm dlx skills add human-plus-machine\u002Fmonkeybot --skill goal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fcli\u002Fsrc\u002Fmonkeybot_cli\u002Fscaffold_defaults\u002Fgoal\u002FSKILL.md",true,[],[54,72,78,91,98,124],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":65,"publishedAt":27},"01M71R6545453TAC4Y71JM2362","browser","Smoke-test browser skill fixture.","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fregression\u002Ft4\u002Fagent\u002Fskills\u002Fbrowser\u002FSKILL.md",[60],{"categoryNo":61,"categoryName":62,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[56,66,67,68,69,70,71],"skill fixture","fixture","test","test browser","smoke","Browser Skill",{"skillNo":73,"name":74,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":27},"01M71R63F3CPF727VZAXTPWJNW","plain","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fregression\u002Ffixtures\u002Fskills\u002Fplain\u002FSKILL.md",[],[74],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":27},"01M71R60VVZE567ZPHWTFHM58S","diagnostics","Inspect a failing run and report the first error.","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fregression\u002Ffixtures\u002Fskills\u002Fdiagnostics\u002FSKILL.md",[],[80,85,86,87,88,89,90],"error","first","run","inspect","report","failing",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":27},"01M71R5Z5JTN6H8NSDE755H9TB","nested","Nested skills must not be discovered.","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fregression\u002Ffixtures\u002Fskills\u002Fa\u002Fnested\u002FSKILL.md",[],[93],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":107,"publishedAt":27},"01M71R5XACZGNRRQ7DH1CA170Y","image-generator","Generate images with Gemini image models (Nano Banana Pro) and display them in chat.","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fexamples\u002Fskills\u002Fimage-generator\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000016","图像与多媒体",[108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"image","generator","image generator","pro","banana","nano banana","images","models","gemini","nano banana pro","nano","display","chat","with","gemini image","generate",{"skillNo":125,"name":80,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":27},"01M71R5VJ9QHZT480VSWGP6B37","Run deployment health checks (env, runtime, computation) and return JSON status.","https:\u002F\u002Fgithub.com\u002Fhuman-plus-machine\u002Fmonkeybot\u002Fblob\u002Fdevelop\u002Fexamples\u002Fskills\u002Fdiagnostics\u002FSKILL.md",[],[80,130,131,87,132,133,134,135,136],"health","runtime","computation","json","deployment","status","env"]