[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KWWC7NDTKT0WKW9XMW73JP":3,"skill-same:01M6KWWC7NDTKT0WKW9XMW73JP":59},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":58},"01M6KWWC7NDTKT0WKW9XMW73JP","loop-me",null,"Experimental: find the recurring work worth delegating, and grill you into workflow specs for it.","dougborg\u002Fharness-kit","dougborg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1261222?v=4","01M6KWS4PB51EYD4ZDJJSGNGB2","Doug Borg","01M6KWS4T8ZZW6SX5QZS9B5BN2",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fclaude-skills\u002Floop-me\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"loop me","loop","me","workflow","work","find","recurring","grill","it","you","true","for","2026-11-10 10:12:30",false,"---\nname: loop-me\ndescription: \"Experimental: find the recurring work worth delegating, and grill you into workflow specs for it.\"\ndisable-model-invocation: true\n---\n\n# Loop Me\n\nExperimental: ported from an upstream skill still in progress, so expect the\nshape to change.\n\nRun a stateful interview whose only output is **workflow** specs. Call the\nSkill tool with \"grilling\" and aim it at the vocabulary and goal below.\nCreate, edit, and delete specs as the grilling settles things.\n\n## The loop lens\n\nA **loop** is a recurring pattern in the user's life: their career, their\nweek, their morning, one repeated activity. Seeing a life as loops within\nloops shows how predictable its activities are, and predictable work is worth\n**delegating**. Use the lens to find loops worth specifying, and propose ones\nthe user hasn't noticed.\n\nA **workflow** is the spec of one loop. You run a workflow on a loop: the\nloop is its running instance.\n\n## Vocabulary\n\nReach for these only when a workflow needs them; they are a shared language,\nnot a checklist. A workflow needs no AI, no checkpoint, and no schedule\nunless the grilling shows it does.\n\n- **Trigger**: what starts each run, an **event** (a new email, a new issue)\n  or a **schedule** (every morning). An event trigger is usually the more\n  efficient.\n- **Checkpoint**: a point where the user verifies or decides. Some workflows\n  run with none.\n- **Push right**: put the checkpoint as late as it will go, so the user is\n  asked once, with everything prepared.\n- **Brief**: what a checkpoint shows, a decision-ready summary (what was\n  produced, why, and a link to the thing itself), never the raw output.\n  Review speed is the point.\n\n## The workspace\n\nThe current directory is the workspace.\n\n- `workflows\u002F*.md`: one spec per workflow, the source of truth.\n- `NOTES.md`: the user's world: the tools they use, the channels they\n  process, and their own names for both. Record each fuzzy term as its\n  canonical name as it is sharpened.\n\n## Run a session\n\n1. **Map the user's world.** Read `NOTES.md`. When it is empty or thin,\n   interview the user about their tools and channels before specifying\n   anything. Done when `NOTES.md` names the tools and channels the candidate\n   loops run through.\n2. **Find the loops.** If the user named a workflow, start there. Otherwise\n   use the loop lens to list candidates, including ones the user hasn't\n   noticed, and let them pick. Done when the user has chosen the loop to\n   specify.\n3. **Write the spec.** Grill the chosen loop into `workflows\u002F\u003Cname>.md`,\n   editing or deleting existing specs as answers change them. Done when an\n   agent could build the workflow without asking a single question.\n\nBuilding and scheduling the workflow is a separate job; this skill stops at\nthe spec.\n","# Loop Me\n\nExperimental: ported from an upstream skill still in progress, so expect the\nshape to change.\n\nRun a stateful interview whose only output is **workflow** specs. Call the\nSkill tool with \"grilling\" and aim it at the vocabulary and goal below.\nCreate, edit, and delete specs as the grilling settles things.\n\n## The loop lens\n\nA **loop** is a recurring pattern in the user's life: their career, their\nweek, their morning, one repeated activity. Seeing a life as loops within\nloops shows how predictable its activities are, and predictable work is worth\n**delegating**. Use the lens to find loops worth specifying, and propose ones\nthe user hasn't noticed.\n\nA **workflow** is the spec of one loop. You run a workflow on a loop: the\nloop is its running instance.\n\n## Vocabulary\n\nReach for these only when a workflow needs them; they are a shared language,\nnot a checklist. A workflow needs no AI, no checkpoint, and no schedule\nunless the grilling shows it does.\n\n- **Trigger**: what starts each run, an **event** (a new email, a new issue)\n  or a **schedule** (every morning). An event trigger is usually the more\n  efficient.\n- **Checkpoint**: a point where the user verifies or decides. Some workflows\n  run with none.\n- **Push right**: put the checkpoint as late as it will go, so the user is\n  asked once, with everything prepared.\n- **Brief**: what a checkpoint shows, a decision-ready summary (what was\n  produced, why, and a link to the thing itself), never the raw output.\n  Review speed is the point.\n\n## The workspace\n\nThe current directory is the workspace.\n\n- `workflows\u002F*.md`: one spec per workflow, the source of truth.\n- `NOTES.md`: the user's world: the tools they use, the channels they\n  process, and their own names for both. Record each fuzzy term as its\n  canonical name as it is sharpened.\n\n## Run a session\n\n1. **Map the user's world.** Read `NOTES.md`. When it is empty or thin,\n   interview the user about their tools and channels before specifying\n   anything. Done when `NOTES.md` names the tools and channels the candidate\n   loops run through.\n2. **Find the loops.** If the user named a workflow, start there. Otherwise\n   use the loop lens to list candidates, including ones the user hasn't\n   noticed, and let them pick. Done when the user has chosen the loop to\n   specify.\n3. **Write the spec.** Grill the chosen loop into `workflows\u002F\u003Cname>.md`,\n   editing or deleting existing specs as answers change them. Done when an\n   agent could build the workflow without asking a single question.\n\nBuilding and scheduling the workflow is a separate job; this skill stops at\nthe spec.\n",{"name":5,"description":7,"disable-model-invocation":36},true,"main","023b01bfb4a86fbf1e38a749f1044cce3e5da67d","claude-skills\u002Floop-me",1,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit","https:\u002F\u002Fgithub.com\u002Fdougborg","http:\u002F\u002Fdougborg.org","Platforms and Infrastructure Software Engineer","2026-11-13 07:43:37",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":36},[48,51,54],{"tool":49,"command":50},"npx","npx skills add dougborg\u002Fharness-kit --skill loop-me",{"tool":52,"command":53},"bunx","bunx skills add dougborg\u002Fharness-kit --skill loop-me",{"tool":55,"command":56},"pnpm","pnpm dlx skills add dougborg\u002Fharness-kit --skill loop-me","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fclaude-skills\u002Floop-me\u002FSKILL.md",[],[60,78,99,131,155,171],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":71,"publishedAt":31},"01M6KX4J65S5FZKMSN5DQNPSZM","teach","Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002FSKILL.md",[66],{"categoryNo":67,"categoryName":68,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[62,72,28,73,74,75,76,77],"lessons","with","learned","record","references","sessions",{"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":89,"publishedAt":31},"01M6KX4FSSG7MHF00JDT5QT0BQ","svg-logo-designer","Generate SVG logos with multiple concepts, layouts, and color variations.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fsvg-logo-designer\u002FSKILL.md",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[90,91,92,93,94,95,73,96,97,98],"logo","designer","svg logo designer","SVG","color","concepts","write","read","generate",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":111,"publishedAt":31},"01M6KX4BD3J9MZPPSH4MENH7FP","documentation-writer","Writes and revises human-facing documentation — READMEs, contributor and setup guides, reference pages, architecture notes, CLAUDE.md, and changelog entries. Covers picking the right document type for the question being asked, structuring for skimming, writing examples that actually run, and keeping docs from going stale. Use when creating or rewriting docs, when a README has drifted from the code, or when deciding where a piece of information belongs. For SKILL.md and agent files, use \u002Fskill-writer instead.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fdocumentation-writer\u002FSKILL.md",[105,108],{"categoryNo":106,"categoryName":107,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":109,"categoryName":110,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000036","内容创作者",[112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,30,127,128,129,130],"writer","documentation writer","documentation","entries","changelog","architecture","document","files","use","question","README","notes","code","examples","pages","information","guides","type","writing",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":31},"01M6KX47ZJ4ZWHDN3MY8SYAWZZ","adhd-mode","Shapes every response for a reader with ADHD: the next action first, numbered steps, progress restated each turn, tangents held back, concrete time estimates, wins made visible. Stays on for the rest of the session until the reader says \"stop adhd mode\". On Claude Code, the harness-kit:adhd output style does the same without invoking this skill.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fadhd-mode\u002FSKILL.md",[],[138,139,140,141,30,142,143,73,144,145,146,147,148,149,150,151,152,153,154,124],"adhd","mode","adhd mode","next","action","kit","output","style","progress","time","back","stop","session","reader","first","REST","harness",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":31},"01M6KX463Z6E18EPDW873GDHKB","wait-what","That last message didn't land: re-explain it with the missing context.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fwait-what\u002FSKILL.md",[],[162,163,164,73,27,165,166,167,168,169,170],"wait","wait what","re","missing","message","context","explain","land","last",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":31},"01M6KX43NE1NB0Y2HECY515730","to-questionnaire","Turn a decision you can't make alone into a questionnaire for the one person who can answer it, filled in async or together in a meeting.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fto-questionnaire\u002FSKILL.md",[],[178,179,30,180,181,182,183,28,184,27,185,186],"to questionnaire","questionnaire","person","can","answer","meeting","make","async","decision"]