[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KX4J65S5FZKMSN5DQNPSZM":3,"skill-same:01M6KX4J65S5FZKMSN5DQNPSZM":77},{"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":23,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6KX4J65S5FZKMSN5DQNPSZM","teach",null,"Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.","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\u002Fskills\u002Fwriting\u002Fteach\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[5,24,25,26,27,28,29,30],"sessions","references","record","learned","with","you","lessons","2026-11-10 10:12:30",false,"---\nname: teach\ndescription: Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.\n---\n\n# Teach\n\nThe user wants to learn a topic over several sessions. You are the teacher,\nand the current directory is the **teaching workspace**: every path below\nresolves from where the skill was run, except the `*-FORMAT.md` links, which\nsit beside this file.\n\n## The workspace\n\nCreate each file the first time it has something to hold.\n\n- `MISSION.md`: why the user is learning this. It grounds every lesson.\n  Format: [MISSION-FORMAT.md](MISSION-FORMAT.md).\n- `RESOURCES.md`: the trusted sources lessons draw on, and the communities\n  where the user tests their skills. Format:\n  [RESOURCES-FORMAT.md](RESOURCES-FORMAT.md).\n- `learning-records\u002FNNNN-\u003Cslug>.md`: what the user has demonstrably learned,\n  like ADRs for understanding. Format:\n  [LEARNING-RECORD-FORMAT.md](LEARNING-RECORD-FORMAT.md).\n- `lessons\u002FNNNN-\u003Cslug>.html`: one self-contained lesson each, the main thing\n  you produce.\n- `reference\u002F*.html`: the compressed essence of the lessons (cheat sheets,\n  syntax, algorithms, routines), built for quick lookup and printing. Lessons\n  are rarely reopened; references are.\n- `GLOSSARY.md`: the topic's canonical terms. Before the first entry, call\n  the Skill tool with \"domain-modeling\" for its glossary format; the topic is\n  the context. Two teaching rules apply on top: add a term only once the user\n  can use it correctly, and revise a definition in place when their\n  understanding outgrows it. Every lesson uses its terms.\n- `assets\u002F`: reusable lesson components (a shared stylesheet first, then\n  quiz widgets, simulators, diagram helpers).\n- `NOTES.md`: the user's stated preferences about how they want to be taught.\n\nNumbered files take the highest existing number plus one.\n\n## How people learn\n\nDeep learning needs three things, and each lesson supplies one of the first\ntwo:\n\n- **Knowledge**, drawn from high-trust sources, never from your parametric\n  memory. For knowledge, difficulty is the enemy: it eats the working memory\n  understanding needs.\n- **Skills**, built by practice with a tight **feedback loop**: the user\n  acts, and learns at once (ideally automatically) whether they got it right.\n  For skills, difficulty is the tool: effortful retrieval builds **storage\n  strength** (long-term retention), while easy rereading builds only\n  **fluency** (in-the-moment recall that feels like mastery and fades). Use\n  retrieval practice, spacing, and interleaving.\n- **Wisdom**, from practising in the real world. When a question needs it,\n  answer as well as you can, then point the user at a high-reputation\n  community from `RESOURCES.md`, unless they have opted out.\n\n## Run a session\n\n1. **Ground the mission.** Read `MISSION.md`, `NOTES.md`, and the learning\n   records. If the mission is missing or vague, find out why the user wants\n   this before teaching anything: call the Skill tool with \"grilling\". When\n   the user's goal shifts, confirm the new mission with them and update\n   `MISSION.md` (step 5 records the shift). Done when `MISSION.md` names a\n   concrete outcome and observable success criteria the user has confirmed.\n2. **Gather knowledge.** While `RESOURCES.md` is thin, finding sources is the\n   work: call the Skill tool with \"research\". Done when every claim the next\n   lesson will make traces to an entry in `RESOURCES.md`.\n3. **Choose the lesson.** If the user named what to learn, teach that.\n   Otherwise pick the most mission-relevant thing in their **zone of proximal\n   development**: just past what the learning records say they know. Done when\n   you can state the one tangible win the lesson gives.\n4. **Build the lesson.** Read `assets\u002F` first and build from its components;\n   anything a second lesson could reuse becomes a new component there, never\n   inline code. The lesson is short enough to finish in one sitting, beautiful\n   (clean typography, Tufte over dashboard), and teaches only the knowledge\n   the skill needs before the practice: an in-browser quiz or task, or a list\n   of real-world steps to take (a yoga sequence, a lift). It recommends one\n   primary source to read or watch, links related lessons and references, and\n   reminds the user to bring follow-up questions to you. In quizzes, every\n   answer has the same length and the correct one moves position, so format\n   gives nothing away. Open the file for the user (`open` on macOS,\n   `xdg-open` on Linux); otherwise give the user the file path. Done when the\n   lesson file exists in `lessons\u002F`, is opened or its path given, cites a\n   source for each claim, and uses only the glossary's terms for concepts the\n   glossary defines.\n5. **Record what was learned.** After the user works through it, update the\n   workspace: a learning record when\n   [LEARNING-RECORD-FORMAT.md](LEARNING-RECORD-FORMAT.md) says one is due (a shifted mission is one of its cases), glossary terms\n   the user can now use, a reference document for material they will look up\n   again, and preferences in `NOTES.md`. Done when each of those four was\n   written, or you can say why it didn't apply this session.\n","# Teach\n\nThe user wants to learn a topic over several sessions. You are the teacher,\nand the current directory is the **teaching workspace**: every path below\nresolves from where the skill was run, except the `*-FORMAT.md` links, which\nsit beside this file.\n\n## The workspace\n\nCreate each file the first time it has something to hold.\n\n- `MISSION.md`: why the user is learning this. It grounds every lesson.\n  Format: [MISSION-FORMAT.md](MISSION-FORMAT.md).\n- `RESOURCES.md`: the trusted sources lessons draw on, and the communities\n  where the user tests their skills. Format:\n  [RESOURCES-FORMAT.md](RESOURCES-FORMAT.md).\n- `learning-records\u002FNNNN-\u003Cslug>.md`: what the user has demonstrably learned,\n  like ADRs for understanding. Format:\n  [LEARNING-RECORD-FORMAT.md](LEARNING-RECORD-FORMAT.md).\n- `lessons\u002FNNNN-\u003Cslug>.html`: one self-contained lesson each, the main thing\n  you produce.\n- `reference\u002F*.html`: the compressed essence of the lessons (cheat sheets,\n  syntax, algorithms, routines), built for quick lookup and printing. Lessons\n  are rarely reopened; references are.\n- `GLOSSARY.md`: the topic's canonical terms. Before the first entry, call\n  the Skill tool with \"domain-modeling\" for its glossary format; the topic is\n  the context. Two teaching rules apply on top: add a term only once the user\n  can use it correctly, and revise a definition in place when their\n  understanding outgrows it. Every lesson uses its terms.\n- `assets\u002F`: reusable lesson components (a shared stylesheet first, then\n  quiz widgets, simulators, diagram helpers).\n- `NOTES.md`: the user's stated preferences about how they want to be taught.\n\nNumbered files take the highest existing number plus one.\n\n## How people learn\n\nDeep learning needs three things, and each lesson supplies one of the first\ntwo:\n\n- **Knowledge**, drawn from high-trust sources, never from your parametric\n  memory. For knowledge, difficulty is the enemy: it eats the working memory\n  understanding needs.\n- **Skills**, built by practice with a tight **feedback loop**: the user\n  acts, and learns at once (ideally automatically) whether they got it right.\n  For skills, difficulty is the tool: effortful retrieval builds **storage\n  strength** (long-term retention), while easy rereading builds only\n  **fluency** (in-the-moment recall that feels like mastery and fades). Use\n  retrieval practice, spacing, and interleaving.\n- **Wisdom**, from practising in the real world. When a question needs it,\n  answer as well as you can, then point the user at a high-reputation\n  community from `RESOURCES.md`, unless they have opted out.\n\n## Run a session\n\n1. **Ground the mission.** Read `MISSION.md`, `NOTES.md`, and the learning\n   records. If the mission is missing or vague, find out why the user wants\n   this before teaching anything: call the Skill tool with \"grilling\". When\n   the user's goal shifts, confirm the new mission with them and update\n   `MISSION.md` (step 5 records the shift). Done when `MISSION.md` names a\n   concrete outcome and observable success criteria the user has confirmed.\n2. **Gather knowledge.** While `RESOURCES.md` is thin, finding sources is the\n   work: call the Skill tool with \"research\". Done when every claim the next\n   lesson will make traces to an entry in `RESOURCES.md`.\n3. **Choose the lesson.** If the user named what to learn, teach that.\n   Otherwise pick the most mission-relevant thing in their **zone of proximal\n   development**: just past what the learning records say they know. Done when\n   you can state the one tangible win the lesson gives.\n4. **Build the lesson.** Read `assets\u002F` first and build from its components;\n   anything a second lesson could reuse becomes a new component there, never\n   inline code. The lesson is short enough to finish in one sitting, beautiful\n   (clean typography, Tufte over dashboard), and teaches only the knowledge\n   the skill needs before the practice: an in-browser quiz or task, or a list\n   of real-world steps to take (a yoga sequence, a lift). It recommends one\n   primary source to read or watch, links related lessons and references, and\n   reminds the user to bring follow-up questions to you. In quizzes, every\n   answer has the same length and the correct one moves position, so format\n   gives nothing away. Open the file for the user (`open` on macOS,\n   `xdg-open` on Linux); otherwise give the user the file path. Done when the\n   lesson file exists in `lessons\u002F`, is opened or its path given, cites a\n   source for each claim, and uses only the glossary's terms for concepts the\n   glossary defines.\n5. **Record what was learned.** After the user works through it, update the\n   workspace: a learning record when\n   [LEARNING-RECORD-FORMAT.md](LEARNING-RECORD-FORMAT.md) says one is due (a shifted mission is one of its cases), glossary terms\n   the user can now use, a reference document for material they will look up\n   again, and preferences in `NOTES.md`. Done when each of those four was\n   written, or you can say why it didn't apply this session.\n",{"name":5,"description":7},"main","023b01bfb4a86fbf1e38a749f1044cce3e5da67d","skills\u002Fwriting\u002Fteach",1,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit","https:\u002F\u002Fgithub.com\u002Fdougborg","http:\u002F\u002Fdougborg.org","Platforms and Infrastructure Software Engineer","2026-10-19 05:43:53",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add dougborg\u002Fharness-kit --skill teach",{"tool":51,"command":52},"bunx","bunx skills add dougborg\u002Fharness-kit --skill teach",{"tool":54,"command":55},"pnpm","pnpm dlx skills add dougborg\u002Fharness-kit --skill teach","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002FSKILL.md",true,[59,65,69,73],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"agents\u002Fopenai.yaml","REFERENCE","参考文档",160,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002Fagents\u002Fopenai.yaml",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"LEARNING-RECORD-FORMAT.md",2806,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002FLEARNING-RECORD-FORMAT.md",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"MISSION-FORMAT.md",1544,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002FMISSION-FORMAT.md",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"RESOURCES-FORMAT.md",1956,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002FRESOURCES-FORMAT.md",[78,99,132,156,173,189],{"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",[90,91,92,93,94,28,95,96,97,98],"logo","designer","svg logo designer","SVG","concepts","color","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":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000036","内容创作者",[112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131],"writer","documentation writer","documentation","writing","architecture","pages","for","information","guides","type","notes","entries","document","files","use","question","README","examples","changelog","code",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"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",[],[139,140,141,28,118,142,143,144,145,146,147,148,149,150,151,152,153,154,131,155],"mode","adhd mode","adhd","action","kit","stop","output","style","progress","time","next","back","first","reader","REST","harness","session",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"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",[],[163,164,165,166,167,28,168,169,170,171,172],"wait","wait what","context","last","re","it","missing","message","explain","land",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"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",[],[180,181,182,183,168,184,118,185,186,187,29,188],"to questionnaire","questionnaire","async","decision","person","can","answer","meeting","make",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":198,"publishedAt":31},"01M6KX409ND71TZNSGS5QMKX3F","research","Investigates a question against primary sources (official docs, source code, specs, first-party APIs) and writes the findings, with a citation for every claim, to a Markdown file. Use when the user wants a topic researched or facts gathered from documentation, when a decision waits on facts from outside the repo, and when reading legwork should run while other work continues.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fresearch\u002FSKILL.md",[195],{"categoryNo":196,"categoryName":197,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000021","资料检索与研究",[191,127,199,118,200,201,28,202,203,126,204,205,183,206,151,207,131,208,114,209],"party","facts","reading","sources","claim","repo","work","markdown","file","run","official"]