[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CDWR5RHVXPBTR3DPTB2MTG":3,"skill-same:01M7CDWR5RHVXPBTR3DPTB2MTG":51},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CDWR5RHVXPBTR3DPTB2MTG","discover",null,"Understand a thing better by asking what it is an instance of outside this estate — handed to a separate reasoning process that has none of your context, so it answers in other people's vocabulary rather than yours. Use when about to say what something is, how it compares with its peers, or what sets it apart; when a shape is in front of you and your account of it is the only one you have; when about to generalise from one case; or when asked to look at something properly. Returns material, never a verdict.","dveyarangi\u002Fgoodwolf-harness","dveyarangi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F693404?v=4","01M77KAGWZ8X0CNA092ZDNEF6T","Fima Rotter","01M7CDVSGB58A879MVTYC1SVD0",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiscover\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: discover\ndescription: >-\n  Understand a thing better by asking what it is an instance of outside this\n  estate — handed to a separate reasoning process that has none of your context,\n  so it answers in other people's vocabulary rather than yours. Use when about to\n  say what something is, how it compares with its peers, or what sets it apart;\n  when a shape is in front of you and your account of it is the only one you have;\n  when about to generalise from one case; or when asked to look at something properly.\n  Returns material, never a verdict.\n---\n\n\u003Cstraw-dog question=\"q-uj5v4t\">Mechanism: not yet\u003C\u002Fstraw-dog>\n\n# Discover\n\nYou are the worst-placed party to say what a thing you built is an instance of. Not for want\nof knowledge — you hold a great deal — but because you are reaching for it while holding the\nframe that produced the thing, so you retrieve what confirms the shape you already have.\n\nThis hands the shape to a process with none of that, and files what comes back.\n\n**It returns material and never a verdict.** What it names is a candidate for your case, not\na finding about it. Why any of this: [EVIDENCE.md](.\u002FEVIDENCE.md).\n\n## What it is for, and what it is not\n\n**For:** you hold one account of something and it is the only one you have. You are about to\nsay what a thing *is*. You have one instance and are about to speak about the class.\n\n**Not for:** ordinary recognition. Naming a thing correctly is not an error, and this does not\nfire on plain naming. It fires where the existence you are ascribing has quietly become one\n**exhausted by your way of grasping it** — where your handle on the thing has replaced it.\n\n**Never the reason to change something.** A ladder always has a higher rung, so a pass will\nalways return room for improvement; that is the shape of the question rather than\ninformation. Its output informs a change that already has a reason. A pass that motivates\nwork has inverted, and the honest name for that is worthening.\n\n## Run it\n\n**Ask the question the shape answers, not the shape:** what it is for, the situation it serves,\nwithout how this tree meets it — a shape described, in anyone's words, sends its frame along. No\nlocal file names, no local rule numbers, no local record names, no house terms. If the pass can only answer in your\nwords, it never left — and this is the whole of the method, so it is worth more care than the\nrest of the tasking put together.\n\n**Transmit the frame as little as the subject allows, and say what you transmitted.** The\ncapture that matters is not the vocabulary of your files; it is the framing you cannot help\nsending, and a fresh process does not fix that by itself. A pass told what to look for will\nfind it and the finding will be worth nothing.\n\n**Give it the rules it works under**, written into the tasking — they are the pass's own\ninstructions, not yours. Ask it for several families rather than one, each with where this sits on\nthat family's own ladder, what the family already knows about how this goes wrong, and its\nconfidence per claim.\n\n**Ask it to name what your tasking smuggled in.** A first-class answer, and the one most\nlikely to be the useful part.\n\n## Sort what comes back\n\n**Recency for evidence, longevity for principles.** A claim that something *works* is\nevidence and must come from the same substrate, recent enough to be about it. A claim about\nhow things of this shape behave in general is a principle, and there **longevity** qualifies —\nwhich is continued life, not elapsed time: still cited, still taught, still used to decide\nthings. A dead old idea has age and no longevity. **The same source flips value depending on\nwhich you asked it for**, and nothing about the source changes.\n\n**Several doors, not one.** A family is a full alternative approach to the thing, not a slice\nof it. So a disagreement between families is not a defect to resolve into one account — an\nanswer that harmonises them has probably lost both.\n\n**Structural fit, not topical.** Retrieval is cued by surface features, so an unconstrained\n*what is this like* returns subject-matter neighbours sharing no structure. Refuse a family\nwhose mapping cannot be stated.\n\n**Stop where no further grounds appear.** Depth is a consequence of that, never a parameter.\n\n## How to run it\n\n**Spawn a separate process** — a general-purpose subagent — and tell it not to read this\nrepository. Reading it re-contaminates, which is the one thing the separate process buys.\nUnless the shape is the repository itself: then the repository is the subject, and your\ndescription of it is the frame. The pass reads it cold, from a fresh clone, and gets only the\nquestion.\n\n**Never feed one pass into the next.** A pass given an earlier pass's output retrieves what it\nalready said, and the second isolation buys nothing.\n\n**Put the material into the work as it came back.** A summary written before you use it is your\nreading of the pass, which is the contamination the pass exists to escape. It goes into the body of\nthe question that prompted it, the way `\u002Fimpact`'s does, and to the person in the same turn: each\nfamily in a sentence of their words, what it would mean here, and what the tasking was found to\nsmuggle — before any decision that stands on it is put to them.\n\n## Neighbours\n\nThe two passes are a pair, and the overlap is intentional. [\u002Fimpact](..\u002Fimpact\u002FSKILL.md) is\nthe first pass: what a shape is made of here, and what depends on it — it needs the corpus.\nThis is the second: what the shape is an instance of elsewhere — it must not read the corpus.\nRunning both means two processes with opposite permissions, which is the point of having two.\n\n[\u002Falign](..\u002Falign\u002FSKILL.md) stress-tests a shape with a person in the room; this runs without\none. A third pass, where a shape wants to go, is not built.\n\nOutput only:\n\n## Families\nEach an alternative account of the shape — not a slice of one. For each: where this sits on that\nfamily's own ladder, what the family already knows about how this goes wrong, and confidence per\nclaim.\n\n## What the tasking smuggled in\nThe framing the pass could see in how it was asked.\n\n## Nothing to take\nFamilies refused for want of a statable mapping, and — when it applies — that the pass returned no\nusable material. That is a result, not a failed run.\n","\u003Cstraw-dog question=\"q-uj5v4t\">Mechanism: not yet\u003C\u002Fstraw-dog>\n\n# Discover\n\nYou are the worst-placed party to say what a thing you built is an instance of. Not for want\nof knowledge — you hold a great deal — but because you are reaching for it while holding the\nframe that produced the thing, so you retrieve what confirms the shape you already have.\n\nThis hands the shape to a process with none of that, and files what comes back.\n\n**It returns material and never a verdict.** What it names is a candidate for your case, not\na finding about it. Why any of this: [EVIDENCE.md](.\u002FEVIDENCE.md).\n\n## What it is for, and what it is not\n\n**For:** you hold one account of something and it is the only one you have. You are about to\nsay what a thing *is*. You have one instance and are about to speak about the class.\n\n**Not for:** ordinary recognition. Naming a thing correctly is not an error, and this does not\nfire on plain naming. It fires where the existence you are ascribing has quietly become one\n**exhausted by your way of grasping it** — where your handle on the thing has replaced it.\n\n**Never the reason to change something.** A ladder always has a higher rung, so a pass will\nalways return room for improvement; that is the shape of the question rather than\ninformation. Its output informs a change that already has a reason. A pass that motivates\nwork has inverted, and the honest name for that is worthening.\n\n## Run it\n\n**Ask the question the shape answers, not the shape:** what it is for, the situation it serves,\nwithout how this tree meets it — a shape described, in anyone's words, sends its frame along. No\nlocal file names, no local rule numbers, no local record names, no house terms. If the pass can only answer in your\nwords, it never left — and this is the whole of the method, so it is worth more care than the\nrest of the tasking put together.\n\n**Transmit the frame as little as the subject allows, and say what you transmitted.** The\ncapture that matters is not the vocabulary of your files; it is the framing you cannot help\nsending, and a fresh process does not fix that by itself. A pass told what to look for will\nfind it and the finding will be worth nothing.\n\n**Give it the rules it works under**, written into the tasking — they are the pass's own\ninstructions, not yours. Ask it for several families rather than one, each with where this sits on\nthat family's own ladder, what the family already knows about how this goes wrong, and its\nconfidence per claim.\n\n**Ask it to name what your tasking smuggled in.** A first-class answer, and the one most\nlikely to be the useful part.\n\n## Sort what comes back\n\n**Recency for evidence, longevity for principles.** A claim that something *works* is\nevidence and must come from the same substrate, recent enough to be about it. A claim about\nhow things of this shape behave in general is a principle, and there **longevity** qualifies —\nwhich is continued life, not elapsed time: still cited, still taught, still used to decide\nthings. A dead old idea has age and no longevity. **The same source flips value depending on\nwhich you asked it for**, and nothing about the source changes.\n\n**Several doors, not one.** A family is a full alternative approach to the thing, not a slice\nof it. So a disagreement between families is not a defect to resolve into one account — an\nanswer that harmonises them has probably lost both.\n\n**Structural fit, not topical.** Retrieval is cued by surface features, so an unconstrained\n*what is this like* returns subject-matter neighbours sharing no structure. Refuse a family\nwhose mapping cannot be stated.\n\n**Stop where no further grounds appear.** Depth is a consequence of that, never a parameter.\n\n## How to run it\n\n**Spawn a separate process** — a general-purpose subagent — and tell it not to read this\nrepository. Reading it re-contaminates, which is the one thing the separate process buys.\nUnless the shape is the repository itself: then the repository is the subject, and your\ndescription of it is the frame. The pass reads it cold, from a fresh clone, and gets only the\nquestion.\n\n**Never feed one pass into the next.** A pass given an earlier pass's output retrieves what it\nalready said, and the second isolation buys nothing.\n\n**Put the material into the work as it came back.** A summary written before you use it is your\nreading of the pass, which is the contamination the pass exists to escape. It goes into the body of\nthe question that prompted it, the way `\u002Fimpact`'s does, and to the person in the same turn: each\nfamily in a sentence of their words, what it would mean here, and what the tasking was found to\nsmuggle — before any decision that stands on it is put to them.\n\n## Neighbours\n\nThe two passes are a pair, and the overlap is intentional. [\u002Fimpact](..\u002Fimpact\u002FSKILL.md) is\nthe first pass: what a shape is made of here, and what depends on it — it needs the corpus.\nThis is the second: what the shape is an instance of elsewhere — it must not read the corpus.\nRunning both means two processes with opposite permissions, which is the point of having two.\n\n[\u002Falign](..\u002Falign\u002FSKILL.md) stress-tests a shape with a person in the room; this runs without\none. A third pass, where a shape wants to go, is not built.\n\nOutput only:\n\n## Families\nEach an alternative account of the shape — not a slice of one. For each: where this sits on that\nfamily's own ladder, what the family already knows about how this goes wrong, and confidence per\nclaim.\n\n## What the tasking smuggled in\nThe framing the pass could see in how it was asked.\n\n## Nothing to take\nFamilies refused for want of a statable mapping, and — when it applies — that the pass returned no\nusable material. That is a result, not a failed run.\n",{"name":5,"description":7},"main","a43633f7ef0eeeb220f42872be487150daec8575",".agents\u002Fskills\u002Fdiscover","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness","https:\u002F\u002Fgithub.com\u002Fdveyarangi","http:\u002F\u002Fdveyarangi.blogspot.com\u002F","2026-11-14 12:09:52",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add dveyarangi\u002Fgoodwolf-harness --skill discover",{"tool":37,"command":38},"bunx","bunx skills add dveyarangi\u002Fgoodwolf-harness --skill discover",{"tool":40,"command":41},"pnpm","pnpm dlx skills add dveyarangi\u002Fgoodwolf-harness --skill discover","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiscover\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"EVIDENCE.md","REFERENCE","参考文档",7063,"https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdiscover\u002FEVIDENCE.md",[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7CDYHDFRAZP8T121PGMZ46R","verify","Use after an implementation pass, or to verify a landed slice before close. Whole verification of landed work: ticket, RFC, governing docs, and the project's verification set.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7CDYES9QW4N2JZ8GX1Q9DMV","ticket","Use to decompose a parent work into independently-workable child tickets. Use to mint ticket(s), possibly a single one, when planning implementation without one.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fticket\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7CDYB6CFM7PD0APTBBS17HH","tdd","Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions \"red-green-refactor\", wants integration tests, or asks for test-first development.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftdd\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7CDY7V9VR5DDC0TPXQRB6K1","skill-up","Aid agent skill creation or modification. Use when creating a new skill or changing an existing one. Use whenever writing any agent instructions, whether to a file or directly in a reply.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-up\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7CDY4B01RZP7Y90JGTCHNY5","setup-devops","Set up the project's engineering scaffolding, from toolchain to CICD and observability. Use when initializing a repo or filling a setup gap.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsetup-devops\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7CDY1P8T9VT2W2ZXEH1H4PR","review-architecture","Explore the codebase for module-deepening opportunities — architectural improvements that raise testability and navigability. Use when asked to improve or refactor the architecture.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freview-architecture\u002FSKILL.md",[],[]]