[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CDWEDTRKXN8JSP0FKBX9AW":3,"skill-same:01M7CDWEDTRKXN8JSP0FKBX9AW":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":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},"01M7CDWEDTRKXN8JSP0FKBX9AW","align",null,"Grilling session that challenges current plan against the existing domain model, sharpens terminology, and updates documentation as decisions crystallise. Use to stress-test a plan against their project's language and documented decisions.","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\u002Falign\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: align\ndescription: Grilling session that challenges current plan against the existing domain model, sharpens terminology, and updates documentation as decisions crystallise. Use to stress-test a plan against their project's language and documented decisions.\n---\n\n\u003Cstraw-dog question=\"q-vui7jm\">Mechanism: not yet\u003C\u002Fstraw-dog>\n\n\u003Cwhat-to-do>\n\nBegin every alignment with a **necessity gate**: name the present customer, the observable problem, and why existing behaviour cannot satisfy it. An accepted requirement or ADR passes by citation. Weak evidence means narrow, postpone, or eliminate — settle that before exploring design. The gate fires late too: a mechanism whose name will not settle is evidence it should not exist. [\u002Fimpact](..\u002Fimpact\u002FSKILL.md) traces consequences once the need holds.\n\nProblem before machinery: open with the concrete failures and my own earlier words, read back from the records, before any design question. A new term is a decision, not a convenience; when I do not follow, go more concrete.\n\nInterview me relentlessly about every aspect of current work until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer. If there are alternatives, show pros\u002Fcons\u002Ftradeoffs between them.\n\nAsk the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering. Do not use platform (Cursor\u002FClaude Code) question format, output plain md.\n\nIf a *fact* can be found by exploring the doc corpus or codebase, look it up rather than asking me. The *decisions*, though, are mine - put each one to me and wait for my answer.\n\n\u003Cstraw-dog question=\"q-mro2st\">\nDecomposing the work during an align is [\u002Fticket](..\u002Fticket\u002FSKILL.md)'s, and it calls\n[\u002Fimpact](..\u002Fimpact\u002FSKILL.md) on the draft split. Run that chain and present what it returns as a\nsuggestion; do not mint. A breakdown reached by unaided grouping is not that chain's output,\nhowever ticket-shaped it looks.\n\u003C\u002Fstraw-dog>\n\nDo not enact the plan before I confirm we have reached a shared understanding: the question's `Where it stands` holds the whole, and I have accepted it.\n\n\n\u003C\u002Fwhat-to-do>\n\n\u003Csupporting-info>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n## Good architecture\n\nGoal of architecture is to reduce work on creation and maintenance of the system.\n\nIdentify the load-bearing assumption behind the proposed shape; ask yourself - what is the cheapest real example that could prove this design assumption wrong? \n\nCheck it when practical, preferably against external reality rather than our own documents and tests.\n\nIf falsified, realign.\nIf unverified and load-bearing, preserve the uncertainty explicitly.\n\n## Domain awareness\n\nDuring codebase exploration, also look for existing documentation:\n\n### File structure\n\nMost repos have a single context:\n\n```\n\u002F\n├── docs\u002F\n│   ├── adr\u002F\n│   │   ├── 0001-event-sourced-orders.md\n│   │   └── 0002-postgres-for-write-model.md\n│   ├── architecture.md\n│   └── glossary.md\n└── src\u002F\n```\n\nCreate files lazily — only when you have something to write. If no `docs\u002Fglossary.md` exists, create one when the first term is resolved. If no `docs\u002Fadr\u002F` exists, create it when the first ADR is needed.\n\u003C\u002Fstraw-dog>\n\n## During the session\n\n\u003Cstraw-dog question=\"q-pdmw3a\">\n### Challenge against the glossary\n\nWhen the user uses a term that conflicts with the existing language in `docs\u002Fglossary.md`, call it out immediately. \"Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?\"\n\nThis cuts both ways: before *you* propose a name, check the glossary yourself — including its _Avoid_ lists, which are reservations, not suggestions. If every synonym for a concept is avoided, that is a designed constraint telling you which word the project has chosen; work within it rather than proposing around it.\n\u003C\u002Fstraw-dog>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n### Check whether it was already decided\n\nBefore treating a question as open, search the ADRs and architecture docs for it. A surprising amount of \"open\" questions are accepted decisions the code drifted from — the answer then is \"implement the ADR\", not a fresh trade-off analysis. Cite the deciding document when you find one.\n\u003C\u002Fstraw-dog>\n\n### Challenge against the Edge records\n\n\u003Cinstalled by=\"edge\">\n**E3** When the plan touches an edge — where the system meets those who consume it or extend it — check\nthat edge's record under `docs\u002Fedge\u002F`. A contradiction with its Contract or Invariants is either a\nplan bug or a deliberate contract change, and a contract change is named **breaking or\ncompatible** out loud before proceeding. As decisions land, write them into the record in the\nshape of `.agents\u002Fskills\u002Fedge\u002FEDGE-FORMAT.md`: a contract change in `Contract` and `Invariants`,\nmarked `⚠ pending — \u003Cticket>` until its ticket lands and the record set `Normative (tentative)`\nwhile any is pending, a promise without a validator marked **⚠ unguarded**; newly surfaced\nedge-scoped concerns as pointers in `Concerns`; staging shifts in `Roadmap`.\n\u003C\u002Finstalled>\n\n### Lead with the decisive fact\n\nWhen recommending between alternatives, find the fact that settles it — a reader count, an import direction, an existing invariant, what a test actually asserts — and lead with it. A pros\u002Fcons menu with no decisive fact means you haven't explored enough yet; go look before asking.\n\n### Name the shared assumption\n\nWhen posing an A-or-B fork, state the assumption both branches share. The user's best answer may dissolve the fork rather than pick a branch — treat \"the premise is wrong\" as a first-class outcome, not a detour. If a fork keeps resisting resolution, that is usually the sign.\n\n### Sharpen fuzzy language\n\nWhen the user uses vague or overloaded terms, propose a precise canonical term. \"You're saying 'account' — do you mean the Customer or the User? Those are different things.\"\n\n### Discuss concrete scenarios\n\nWhen domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.\n\n### Cross-reference with code\n\nWhen the user states how something works, check whether the code agrees. If you find a contradiction, surface it: \"Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?\"\n\n\u003Cstraw-dog question=\"q-pdmw3a\">\n### Update glossary.md inline\n\nWhen a term is resolved, update `docs\u002Fglossary.md` right there. Don't batch these up — capture them as they happen. Use the format in [GLOSSARY-FORMAT.md](.\u002FGLOSSARY-FORMAT.md).\n\n`docs\u002Fglossary.md` should be totally devoid of implementation details. Do not treat it as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.\n\u003C\u002Fstraw-dog>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n### Update architecture.md inline\n\nWhen high-level architecture of this project changes, update `architecture.md`. Use format in [ARCH-FORMAT.md](.\u002FARCH-FORMAT.md).\n\n`architecture.md` document captures the **high-level architecture**. Lower-level concerns are intentionally **deferred** and listed at the end.\n> Scope note: everything here is at the architecture\u002Fcontract level. Where a concrete shape would prematurely lock a deferred decision, we define only the *seam*.\n> You should guide the user toward deep modules with simple boundaries.\n\u003C\u002Fstraw-dog>\n\n\n### Land resolutions as they are made\n\nLand each resolution the moment it is made, as the blocks below say.\n\n\u003Cinstalled by=\"mechanism-shape\">\n**R5** Before writing a rule into AGENTS.md, find the mechanism whose work it governs. Land a\nmechanism's rule in AGENTS.md only as an installed block from its rules file. While the\nmechanism is undeclared, write the rule by hand and wrap it as a straw dog bound to the question\nof what the mechanism owns, as you write it.\n\u003C\u002Finstalled>\n\n\u003Cinstalled by=\"ticket\">\n**P7** Rewrite the ticket in place to what the align's landed decisions make true.\n\n**P10** Open an align by saying what its work is: what it builds and the problem it answers, each of its\nterms explained, before the necessity gate or any question.\n\n**P11** Sweep the question's body, and the ticket where there is one, for internal consistency at the end:\nan early line may still assert what a later resolution changed.\n\u003C\u002Finstalled>\n\n\u003Cinstalled by=\"questions\">\n**Q6** Land a decision as it is made, with its provenance: final in its durable home where no open\nquestion's answer can change its form or home, otherwise as a straw dog bound to the nearest open\nancestor whose answer can. One with nowhere to land yet — its home is work not done — is a line in\nthe `## Decisions` list of the lowest question holding everyone who needs it, and takes\n`→ \u003Clink>` when it lands. Close the question it answers against where it landed, and when a line\nlands, repoint every entry closed against its list there. A decision not to do what nothing\ninstructs lands in its question alone.\n\u003C\u002Finstalled>\n\n\u003Cinstalled by=\"product\">\n**U2** When a question under *What is this project for?* is decided with something to build, do three\nthings in one step:\n\n1. With `\u002Fproduct`, write the answer into the document: a row that waits on this question has\n   its *waits on* cell emptied; otherwise a new row takes the next number.\n2. Close the question against that row.\n3. Open the question of how to build it in the *How is this project built?* branch, under the\n   question it belongs to, and give it its trace link with `questions.py realize`, naming the\n   row's number and name.\n\nA decision that changes, replaces or retires an answer is written by `\u002Fproduct` the same way.\n\u003C\u002Finstalled>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n### Offer ADRs sparingly\n\nOnly offer to create an ADR when all three are true:\n\n1. **Hard to reverse** — the cost of changing your mind later is meaningful\n2. **Surprising without context** — a future reader will wonder \"why did they do it this way?\"\n3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons\n\nIf any of the three is missing, skip the ADR. Use the format in [ADR-FORMAT.md](.\u002FADR-FORMAT.md).\n\u003C\u002Fstraw-dog>\n\n\u003C\u002Fsupporting-info>\n","\u003Cstraw-dog question=\"q-vui7jm\">Mechanism: not yet\u003C\u002Fstraw-dog>\n\n\u003Cwhat-to-do>\n\nBegin every alignment with a **necessity gate**: name the present customer, the observable problem, and why existing behaviour cannot satisfy it. An accepted requirement or ADR passes by citation. Weak evidence means narrow, postpone, or eliminate — settle that before exploring design. The gate fires late too: a mechanism whose name will not settle is evidence it should not exist. [\u002Fimpact](..\u002Fimpact\u002FSKILL.md) traces consequences once the need holds.\n\nProblem before machinery: open with the concrete failures and my own earlier words, read back from the records, before any design question. A new term is a decision, not a convenience; when I do not follow, go more concrete.\n\nInterview me relentlessly about every aspect of current work until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer. If there are alternatives, show pros\u002Fcons\u002Ftradeoffs between them.\n\nAsk the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering. Do not use platform (Cursor\u002FClaude Code) question format, output plain md.\n\nIf a *fact* can be found by exploring the doc corpus or codebase, look it up rather than asking me. The *decisions*, though, are mine - put each one to me and wait for my answer.\n\n\u003Cstraw-dog question=\"q-mro2st\">\nDecomposing the work during an align is [\u002Fticket](..\u002Fticket\u002FSKILL.md)'s, and it calls\n[\u002Fimpact](..\u002Fimpact\u002FSKILL.md) on the draft split. Run that chain and present what it returns as a\nsuggestion; do not mint. A breakdown reached by unaided grouping is not that chain's output,\nhowever ticket-shaped it looks.\n\u003C\u002Fstraw-dog>\n\nDo not enact the plan before I confirm we have reached a shared understanding: the question's `Where it stands` holds the whole, and I have accepted it.\n\n\n\u003C\u002Fwhat-to-do>\n\n\u003Csupporting-info>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n## Good architecture\n\nGoal of architecture is to reduce work on creation and maintenance of the system.\n\nIdentify the load-bearing assumption behind the proposed shape; ask yourself - what is the cheapest real example that could prove this design assumption wrong? \n\nCheck it when practical, preferably against external reality rather than our own documents and tests.\n\nIf falsified, realign.\nIf unverified and load-bearing, preserve the uncertainty explicitly.\n\n## Domain awareness\n\nDuring codebase exploration, also look for existing documentation:\n\n### File structure\n\nMost repos have a single context:\n\n```\n\u002F\n├── docs\u002F\n│   ├── adr\u002F\n│   │   ├── 0001-event-sourced-orders.md\n│   │   └── 0002-postgres-for-write-model.md\n│   ├── architecture.md\n│   └── glossary.md\n└── src\u002F\n```\n\nCreate files lazily — only when you have something to write. If no `docs\u002Fglossary.md` exists, create one when the first term is resolved. If no `docs\u002Fadr\u002F` exists, create it when the first ADR is needed.\n\u003C\u002Fstraw-dog>\n\n## During the session\n\n\u003Cstraw-dog question=\"q-pdmw3a\">\n### Challenge against the glossary\n\nWhen the user uses a term that conflicts with the existing language in `docs\u002Fglossary.md`, call it out immediately. \"Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?\"\n\nThis cuts both ways: before *you* propose a name, check the glossary yourself — including its _Avoid_ lists, which are reservations, not suggestions. If every synonym for a concept is avoided, that is a designed constraint telling you which word the project has chosen; work within it rather than proposing around it.\n\u003C\u002Fstraw-dog>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n### Check whether it was already decided\n\nBefore treating a question as open, search the ADRs and architecture docs for it. A surprising amount of \"open\" questions are accepted decisions the code drifted from — the answer then is \"implement the ADR\", not a fresh trade-off analysis. Cite the deciding document when you find one.\n\u003C\u002Fstraw-dog>\n\n### Challenge against the Edge records\n\n\u003Cinstalled by=\"edge\">\n**E3** When the plan touches an edge — where the system meets those who consume it or extend it — check\nthat edge's record under `docs\u002Fedge\u002F`. A contradiction with its Contract or Invariants is either a\nplan bug or a deliberate contract change, and a contract change is named **breaking or\ncompatible** out loud before proceeding. As decisions land, write them into the record in the\nshape of `.agents\u002Fskills\u002Fedge\u002FEDGE-FORMAT.md`: a contract change in `Contract` and `Invariants`,\nmarked `⚠ pending — \u003Cticket>` until its ticket lands and the record set `Normative (tentative)`\nwhile any is pending, a promise without a validator marked **⚠ unguarded**; newly surfaced\nedge-scoped concerns as pointers in `Concerns`; staging shifts in `Roadmap`.\n\u003C\u002Finstalled>\n\n### Lead with the decisive fact\n\nWhen recommending between alternatives, find the fact that settles it — a reader count, an import direction, an existing invariant, what a test actually asserts — and lead with it. A pros\u002Fcons menu with no decisive fact means you haven't explored enough yet; go look before asking.\n\n### Name the shared assumption\n\nWhen posing an A-or-B fork, state the assumption both branches share. The user's best answer may dissolve the fork rather than pick a branch — treat \"the premise is wrong\" as a first-class outcome, not a detour. If a fork keeps resisting resolution, that is usually the sign.\n\n### Sharpen fuzzy language\n\nWhen the user uses vague or overloaded terms, propose a precise canonical term. \"You're saying 'account' — do you mean the Customer or the User? Those are different things.\"\n\n### Discuss concrete scenarios\n\nWhen domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.\n\n### Cross-reference with code\n\nWhen the user states how something works, check whether the code agrees. If you find a contradiction, surface it: \"Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?\"\n\n\u003Cstraw-dog question=\"q-pdmw3a\">\n### Update glossary.md inline\n\nWhen a term is resolved, update `docs\u002Fglossary.md` right there. Don't batch these up — capture them as they happen. Use the format in [GLOSSARY-FORMAT.md](.\u002FGLOSSARY-FORMAT.md).\n\n`docs\u002Fglossary.md` should be totally devoid of implementation details. Do not treat it as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.\n\u003C\u002Fstraw-dog>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n### Update architecture.md inline\n\nWhen high-level architecture of this project changes, update `architecture.md`. Use format in [ARCH-FORMAT.md](.\u002FARCH-FORMAT.md).\n\n`architecture.md` document captures the **high-level architecture**. Lower-level concerns are intentionally **deferred** and listed at the end.\n> Scope note: everything here is at the architecture\u002Fcontract level. Where a concrete shape would prematurely lock a deferred decision, we define only the *seam*.\n> You should guide the user toward deep modules with simple boundaries.\n\u003C\u002Fstraw-dog>\n\n\n### Land resolutions as they are made\n\nLand each resolution the moment it is made, as the blocks below say.\n\n\u003Cinstalled by=\"mechanism-shape\">\n**R5** Before writing a rule into AGENTS.md, find the mechanism whose work it governs. Land a\nmechanism's rule in AGENTS.md only as an installed block from its rules file. While the\nmechanism is undeclared, write the rule by hand and wrap it as a straw dog bound to the question\nof what the mechanism owns, as you write it.\n\u003C\u002Finstalled>\n\n\u003Cinstalled by=\"ticket\">\n**P7** Rewrite the ticket in place to what the align's landed decisions make true.\n\n**P10** Open an align by saying what its work is: what it builds and the problem it answers, each of its\nterms explained, before the necessity gate or any question.\n\n**P11** Sweep the question's body, and the ticket where there is one, for internal consistency at the end:\nan early line may still assert what a later resolution changed.\n\u003C\u002Finstalled>\n\n\u003Cinstalled by=\"questions\">\n**Q6** Land a decision as it is made, with its provenance: final in its durable home where no open\nquestion's answer can change its form or home, otherwise as a straw dog bound to the nearest open\nancestor whose answer can. One with nowhere to land yet — its home is work not done — is a line in\nthe `## Decisions` list of the lowest question holding everyone who needs it, and takes\n`→ \u003Clink>` when it lands. Close the question it answers against where it landed, and when a line\nlands, repoint every entry closed against its list there. A decision not to do what nothing\ninstructs lands in its question alone.\n\u003C\u002Finstalled>\n\n\u003Cinstalled by=\"product\">\n**U2** When a question under *What is this project for?* is decided with something to build, do three\nthings in one step:\n\n1. With `\u002Fproduct`, write the answer into the document: a row that waits on this question has\n   its *waits on* cell emptied; otherwise a new row takes the next number.\n2. Close the question against that row.\n3. Open the question of how to build it in the *How is this project built?* branch, under the\n   question it belongs to, and give it its trace link with `questions.py realize`, naming the\n   row's number and name.\n\nA decision that changes, replaces or retires an answer is written by `\u002Fproduct` the same way.\n\u003C\u002Finstalled>\n\n\u003Cstraw-dog question=\"q-ggpx2r\">\n### Offer ADRs sparingly\n\nOnly offer to create an ADR when all three are true:\n\n1. **Hard to reverse** — the cost of changing your mind later is meaningful\n2. **Surprising without context** — a future reader will wonder \"why did they do it this way?\"\n3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons\n\nIf any of the three is missing, skip the ADR. Use the format in [ADR-FORMAT.md](.\u002FADR-FORMAT.md).\n\u003C\u002Fstraw-dog>\n\n\u003C\u002Fsupporting-info>\n",{"name":5,"description":7},"main","a43633f7ef0eeeb220f42872be487150daec8575",".agents\u002Fskills\u002Falign","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 align",{"tool":37,"command":38},"bunx","bunx skills add dveyarangi\u002Fgoodwolf-harness --skill align",{"tool":40,"command":41},"pnpm","pnpm dlx skills add dveyarangi\u002Fgoodwolf-harness --skill align","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"ADR-FORMAT.md","REFERENCE","参考文档",3194,"https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign\u002FADR-FORMAT.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"ARCH-FORMAT.md",2646,"https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign\u002FARCH-FORMAT.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"GLOSSARY-FORMAT.md",2335,"https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fgoodwolf-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign\u002FGLOSSARY-FORMAT.md",[60,67,74,81,88,95],{"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":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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",[],[]]