[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B1C83V9J94BFCD3EF6NTYP":3,"skill-same:01M7B1C83V9J94BFCD3EF6NTYP":47},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7B1C83V9J94BFCD3EF6NTYP","coach",null,"Decision support and grounded teaching for the human. Invoke when the user signals a message didn't land (\"wait, what?\", \"I don't understand\", \"explain it like I'm five\", \"which is better?\", \"I'm not sure\") about a question or fork they've been asked, or when they hand over a MEMORY.md lesson, an ADR, or a bundle and want to learn the concept behind it.","ReinaMacCredy\u002Fwaymark","ReinaMacCredy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F146199234?v=4","01M7B1C6DEJXGZNVS5MNE2AMFF","Reina MacCredy","01M7B1C6E2R8X4ACEJPPBA6H7N",1,"MIT","https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fcoach\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: coach\ndescription: Decision support and grounded teaching for the human. Invoke when the user signals a message didn't land (\"wait, what?\", \"I don't understand\", \"explain it like I'm five\", \"which is better?\", \"I'm not sure\") about a question or fork they've been asked, or when they hand over a MEMORY.md lesson, an ADR, or a bundle and want to learn the concept behind it.\n---\n\n# coach\n\nHelp the human decide and learn — never decide for them, never drift into\nlecture.\n\n## Fork mode\n\nAny skill has put a question to the user and the user signals confusion.\n\n1. Pause the fork; do not press for an answer. If the user can't answer\n   because someone else owns the decision, route to `questionnaire` instead.\n2. Re-pitch as if to someone with zero background: short sentences, one\n   concrete analogy or image per option, no jargon before step 3 names it.\n   Use the vocabulary of `.waymark\u002FCONTEXT.md` when it exists; explain each\n   option with its concrete consequence in this repository — not textbook\n   generalities.\n3. Name the underlying software-engineering concepts by their real names\n   (coupling, migration cost, blast radius, lock-in...) so the user collects\n   the vocabulary to steer with next time.\n4. Give one recommendation and the reason it fits this repo's constraints.\n5. Re-ask the original fork. The user still decides; a coach that answers\n   its own question has failed.\n\n## Grounded-teach mode\n\nThe user hands over a MEMORY.md line, an ADR, or a bundle.\n\n1. Read the source: the bundle's SPEC\u002FNOTES, the ADR, or the code the lesson\n   points at.\n2. Teach the general concept behind it — the lesson is the example, not the\n   syllabus. (\"sticky positioning belongs to question rows\" → CSS sticky and\n   stacking contexts, demonstrated on this repo's transcript component.)\n3. Work through the actual repository code, never invented examples.\n4. End with one check: ask the user to predict or explain one nearby\n   behavior; correct gently, with evidence.\n\nEither mode: when a plain-prose explanation has failed to land twice,\nescalate the medium, not the volume — build a single-file HTML visual\nexplainer of the concept (big visuals, few words, zero jargon) and walk it\nwith the user. One concept per explainer; it teaches, it never argues for an\noption.\n\nOne concept per session — depth over coverage. Full-topic syllabi are a\ndifferent engagement, not this skill.\n","# coach\n\nHelp the human decide and learn — never decide for them, never drift into\nlecture.\n\n## Fork mode\n\nAny skill has put a question to the user and the user signals confusion.\n\n1. Pause the fork; do not press for an answer. If the user can't answer\n   because someone else owns the decision, route to `questionnaire` instead.\n2. Re-pitch as if to someone with zero background: short sentences, one\n   concrete analogy or image per option, no jargon before step 3 names it.\n   Use the vocabulary of `.waymark\u002FCONTEXT.md` when it exists; explain each\n   option with its concrete consequence in this repository — not textbook\n   generalities.\n3. Name the underlying software-engineering concepts by their real names\n   (coupling, migration cost, blast radius, lock-in...) so the user collects\n   the vocabulary to steer with next time.\n4. Give one recommendation and the reason it fits this repo's constraints.\n5. Re-ask the original fork. The user still decides; a coach that answers\n   its own question has failed.\n\n## Grounded-teach mode\n\nThe user hands over a MEMORY.md line, an ADR, or a bundle.\n\n1. Read the source: the bundle's SPEC\u002FNOTES, the ADR, or the code the lesson\n   points at.\n2. Teach the general concept behind it — the lesson is the example, not the\n   syllabus. (\"sticky positioning belongs to question rows\" → CSS sticky and\n   stacking contexts, demonstrated on this repo's transcript component.)\n3. Work through the actual repository code, never invented examples.\n4. End with one check: ask the user to predict or explain one nearby\n   behavior; correct gently, with evidence.\n\nEither mode: when a plain-prose explanation has failed to land twice,\nescalate the medium, not the volume — build a single-file HTML visual\nexplainer of the concept (big visuals, few words, zero jargon) and walk it\nwith the user. One concept per explainer; it teaches, it never argues for an\noption.\n\nOne concept per session — depth over coverage. Full-topic syllabi are a\ndifferent engagement, not this skill.\n",{"name":5,"description":7},"main","eeef86fa761c8c67f815766959c1424781e398d8","waymark\u002Fskills\u002Fcoach",0,"https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark","https:\u002F\u002Fgithub.com\u002FReinaMacCredy","https:\u002F\u002Fmaccredyreina.me","♪『 Say my name when a tree susurrates Once and again telling a story lost in time The way it starts and the way it ends 』♪","2026-08-23 22:02:41",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add ReinaMacCredy\u002Fwaymark --skill coach",{"tool":39,"command":40},"bunx","bunx skills add ReinaMacCredy\u002Fwaymark --skill coach",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ReinaMacCredy\u002Fwaymark --skill coach","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fcoach\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7B1D0TGN0XGCNPF10Q5FPZB","verify","Execute VERIFY.md scenarios through real consumer paths, review the frozen task-owned diff, deliver the verdict, and close the bundle — distilling durable lessons into the repo's MEMORY.md. Also the route for re-running an open bundle's gates or updating its VERIFY.md\u002FNOTES.md, including after another agent's commits — never by ad-hoc scripts. For an open bundle only; tier-Light changes are verified inline, not through this skill.","https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7B1CYFHWTG0AQ9T3BC5TPQT","spec","Turn the current conversation and codebase understanding into a work bundle with SPEC.md — synthesis of what is already known, interviewing only on material open forks. Use for unresolved ideas, requirements, sources, system maps, or plans.","https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fspec\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7B1CV4PDHZC4E1TJ9M9RK9Z","scout","Settle the pre-spec unknowns that need a decision — interview the user on open forks, prototype feel-right design questions, sharpen the domain model, or chart an effort too big for one session. Use when an idea is still vague, options compete unchosen, the user doesn't know where to start, or asks to be grilled. Evidence questions with no decision attached (external facts, baselines) belong to explore instead.","https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fscout\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7B1CRD9TR10HVT3A50EN57J","questionnaire","Turn a decision the user can't fully answer into a Markdown questionnaire for the one person who can — filled in async, or together over a meeting. Adapted from Matt Pocock's to-questionnaire.","https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fquestionnaire\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7B1CMRM5TB1894EFCNTTDHA","implement","Implement authorized Full-tier work from the bundle's SPEC.md, red-first at pre-agreed seams. Requires an explicit user request to implement or fix production code, and a SPEC whose red-test list covers this exact scope — post-ship review findings and follow-ups go through spec first. Never invoke on your own initiative. Do NOT trigger when the target is a throwaway prototype, research spike, or baseline (explore's scope), or when the fix is a tier-Light quickfix (proceed directly, no skill).","https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fimplement\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7B1CJFC64XMR1KW1PA41THC","handoff","Compact the current conversation so another agent can pick the work up — into the active bundle's NOTES.md when one exists, or a standalone handoff document otherwise. Adapted from Matt Pocock's handoff.","https:\u002F\u002Fgithub.com\u002FReinaMacCredy\u002Fwaymark\u002Fblob\u002Fmain\u002Fwaymark\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[]]