[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BHVBXJJSZ5RAH7FGWX2808":3,"skill-same:01M7BHVBXJJSZ5RAH7FGWX2808":60},{"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":30,"updatedAt":31,"install":32,"resources":45},"01M7BHVBXJJSZ5RAH7FGWX2808","architect",null,"Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for \u002Farchitect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.","gannonh\u002Fcodex-plugins","gannonh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1012888?v=4","01M725CQ84YM7074SNHKWKZ323","Gannon Hall","01M7BHVA7G558FKQNQ9449DTJE",0,"MIT","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Farchitect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: architect\ndescription: \"Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for \u002Farchitect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.\"\n---\n\n# Architect\n\nDesign before implementing. Sketch types, function signatures, class shapes, and module boundaries with `not implemented` bodies and pseudocode. Synthesize across multiple model perspectives, then fill in code against the chosen sketch. If implementation proves the sketch wrong, throw it out and redesign.\n\n**Dispatch contract.** Architect's Arena uses the centralized provider routing in [`provider-dispatch.md`](..\u002Fpoteto-mode\u002Freferences\u002Fprovider-dispatch.md). Configured entries are descriptors, not native model slugs. Resolve remaining Claude tool names via [`codex-tools.md`](..\u002Fpoteto-mode\u002Freferences\u002Fcodex-tools.md).\n\n## Start\n\nOpen a todolist with one entry per phase before starting. Autonomous mode without checkpoints needs the list to show phase position and keep phases from silently disappearing.\n\n1. Ground\n2. Sketch\n3. Agree\n4. Implement\n5. Scrap\n\n## Phase A: Ground the problem\n\nBuild a real mental model of every system the new code touches. Run the **how** skill over the relevant subsystems. Critique mode if existing structure is the constraint or the design must push back on it.\n\nNaming a file isn't grounding. Produce the traced model `how` prescribes. If the design redefines ownership or layering, also run the **why** skill on the existing shape so the rationale becomes a constraint, not a guess.\n\nSkip Phase A only when the work is genuinely greenfield with no surrounding system to integrate.\n\n## Phase B: Sketch\n\nRun the **arena** skill with the design-sketch task and the Phase A grounding artifacts. Pass `references\u002Frunner-prompt.md` as each runner's prompt. Each candidate produces a design package shaped per `references\u002Frationale-template.md`: the caller's usage written first, then the type sketch, function signatures, module map, and prose rationale derived from it.\n\nUse your configured architect runners (defaults `codex:gpt-5.6-luna@max`, `codex:gpt-5.6-sol@medium`, `codex:gpt-5.6-sol@high`, `codex:gpt-5.6-sol@xhigh`).\n\nDesign it twice. Require at least two structurally distinct candidates before synthesis, even when the first looks sufficient. This is the **exhaust-the-design-space** principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.\n\nScreen every candidate against [`references\u002Fdesign-red-flags.md`](references\u002Fdesign-red-flags.md) before synthesis. Reject or revise shallow modules, information leakage, temporal decomposition, and pass-through methods.\n\nCompare viable candidates on interface depth. Prefer the design that hides more complexity behind a smaller, simpler public surface. A rich interface can keep call chains short by concentrating capability instead of scattering it across layers.\n\nArena returns one synthesized design package. The synthesis decision populates the rationale's \"Synthesis decision\" section.\n\n## Phase C: Agree (opt-in)\n\nDefault: proceed directly to implementation with the synthesized design. No human checkpoint.\n\nOpt in to a checkpoint when the invoker explicitly asks: \"\u002Farchitect with checkpoint,\" \"stop and show me before implementing,\" or similar. Then surface the synthesized design and pause for sign-off.\n\nThe synthesis can ship as its own commit either way. That's the \"scaffold first\" mode of the **foundational-thinking** principle skill; subsequent commits read as filling in bodies against a stable contract. Planned and scoped breakage during fill-in is fine, per the **outcome-oriented-execution** principle skill. For adversarial pressure on the design before implementing, run the **interrogate** skill on the synthesized sketch.\n\nIf the human pushes back on the shape (in a checkpoint or after the fact), treat that as Phase A evidence. Re-ground and re-run Phase B before writing more code.\n\n## Phase D: Implement against the sketch\n\nReplace `not implemented` bodies with code, pseudocode with logic. The synthesized sketch is the contract.\n\nDeviations from the sketch are signal worth surfacing, not friction to absorb silently. If a function needs a parameter the sketch didn't anticipate, ask whether the sketch was wrong, the requirement was missed, or the implementation is overreaching. Surface it; don't bolt it on.\n\n## Phase E: Scrap when the architecture is wrong\n\nIf implementation keeps producing friction the sketch can't absorb, throw the sketch out. Don't bolt fixes onto a wrong design, per the **redesign-from-first-principles** and **fix-root-causes** principle skills.\n\nThe signal is a *pattern*, not single instances. Tells:\n\n- The same shape of workaround appearing repeatedly across unrelated code.\n- Multiple unrelated edge cases that all need special-case branches.\n- Types that need escape hatches (`any`, casts, optional fields always set in practice) to compile.\n- The \"we need a lock\" reflex when the sketch said the state wasn't shared.\n- Callers having to know the abstraction's internal rules to use it.\n- Two or more independent Phase D deviations of the same shape across the implementation. Surfacing deviations is Phase D's job; a repeated pattern of them is Phase E's trigger.\n\nUse judgment. A few edge cases don't condemn an architecture. Some problems are legitimately complex; complexity in the data is not complexity in the design. The rewrite signal is repeated friction of the same shape, not single hard cases.\n\nWhen you scrap:\n\n1. Re-run the **how** skill over what's been built. The implementation lessons enter the new design as inputs, not vibes.\n2. Redesign as if the new constraints had been day-one assumptions, per redesign-from-first-principles.\n3. Subtract before adding, per the **subtract-before-you-add** principle skill. The new sketch should be smaller than the old one before it grows.\n4. Return to Phase B and re-run arena.\n\n## Outputs\n\nThe caller's usage is written first and the type sketch derived from it. One file with new types and signatures for small changes; module map plus type definitions for larger work. The rationale ships alongside, shaped per `references\u002Frationale-template.md`, including the usage sketch and the synthesis decision.\n","# Architect\n\nDesign before implementing. Sketch types, function signatures, class shapes, and module boundaries with `not implemented` bodies and pseudocode. Synthesize across multiple model perspectives, then fill in code against the chosen sketch. If implementation proves the sketch wrong, throw it out and redesign.\n\n**Dispatch contract.** Architect's Arena uses the centralized provider routing in [`provider-dispatch.md`](..\u002Fpoteto-mode\u002Freferences\u002Fprovider-dispatch.md). Configured entries are descriptors, not native model slugs. Resolve remaining Claude tool names via [`codex-tools.md`](..\u002Fpoteto-mode\u002Freferences\u002Fcodex-tools.md).\n\n## Start\n\nOpen a todolist with one entry per phase before starting. Autonomous mode without checkpoints needs the list to show phase position and keep phases from silently disappearing.\n\n1. Ground\n2. Sketch\n3. Agree\n4. Implement\n5. Scrap\n\n## Phase A: Ground the problem\n\nBuild a real mental model of every system the new code touches. Run the **how** skill over the relevant subsystems. Critique mode if existing structure is the constraint or the design must push back on it.\n\nNaming a file isn't grounding. Produce the traced model `how` prescribes. If the design redefines ownership or layering, also run the **why** skill on the existing shape so the rationale becomes a constraint, not a guess.\n\nSkip Phase A only when the work is genuinely greenfield with no surrounding system to integrate.\n\n## Phase B: Sketch\n\nRun the **arena** skill with the design-sketch task and the Phase A grounding artifacts. Pass `references\u002Frunner-prompt.md` as each runner's prompt. Each candidate produces a design package shaped per `references\u002Frationale-template.md`: the caller's usage written first, then the type sketch, function signatures, module map, and prose rationale derived from it.\n\nUse your configured architect runners (defaults `codex:gpt-5.6-luna@max`, `codex:gpt-5.6-sol@medium`, `codex:gpt-5.6-sol@high`, `codex:gpt-5.6-sol@xhigh`).\n\nDesign it twice. Require at least two structurally distinct candidates before synthesis, even when the first looks sufficient. This is the **exhaust-the-design-space** principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.\n\nScreen every candidate against [`references\u002Fdesign-red-flags.md`](references\u002Fdesign-red-flags.md) before synthesis. Reject or revise shallow modules, information leakage, temporal decomposition, and pass-through methods.\n\nCompare viable candidates on interface depth. Prefer the design that hides more complexity behind a smaller, simpler public surface. A rich interface can keep call chains short by concentrating capability instead of scattering it across layers.\n\nArena returns one synthesized design package. The synthesis decision populates the rationale's \"Synthesis decision\" section.\n\n## Phase C: Agree (opt-in)\n\nDefault: proceed directly to implementation with the synthesized design. No human checkpoint.\n\nOpt in to a checkpoint when the invoker explicitly asks: \"\u002Farchitect with checkpoint,\" \"stop and show me before implementing,\" or similar. Then surface the synthesized design and pause for sign-off.\n\nThe synthesis can ship as its own commit either way. That's the \"scaffold first\" mode of the **foundational-thinking** principle skill; subsequent commits read as filling in bodies against a stable contract. Planned and scoped breakage during fill-in is fine, per the **outcome-oriented-execution** principle skill. For adversarial pressure on the design before implementing, run the **interrogate** skill on the synthesized sketch.\n\nIf the human pushes back on the shape (in a checkpoint or after the fact), treat that as Phase A evidence. Re-ground and re-run Phase B before writing more code.\n\n## Phase D: Implement against the sketch\n\nReplace `not implemented` bodies with code, pseudocode with logic. The synthesized sketch is the contract.\n\nDeviations from the sketch are signal worth surfacing, not friction to absorb silently. If a function needs a parameter the sketch didn't anticipate, ask whether the sketch was wrong, the requirement was missed, or the implementation is overreaching. Surface it; don't bolt it on.\n\n## Phase E: Scrap when the architecture is wrong\n\nIf implementation keeps producing friction the sketch can't absorb, throw the sketch out. Don't bolt fixes onto a wrong design, per the **redesign-from-first-principles** and **fix-root-causes** principle skills.\n\nThe signal is a *pattern*, not single instances. Tells:\n\n- The same shape of workaround appearing repeatedly across unrelated code.\n- Multiple unrelated edge cases that all need special-case branches.\n- Types that need escape hatches (`any`, casts, optional fields always set in practice) to compile.\n- The \"we need a lock\" reflex when the sketch said the state wasn't shared.\n- Callers having to know the abstraction's internal rules to use it.\n- Two or more independent Phase D deviations of the same shape across the implementation. Surfacing deviations is Phase D's job; a repeated pattern of them is Phase E's trigger.\n\nUse judgment. A few edge cases don't condemn an architecture. Some problems are legitimately complex; complexity in the data is not complexity in the design. The rewrite signal is repeated friction of the same shape, not single hard cases.\n\nWhen you scrap:\n\n1. Re-run the **how** skill over what's been built. The implementation lessons enter the new design as inputs, not vibes.\n2. Redesign as if the new constraints had been day-one assumptions, per redesign-from-first-principles.\n3. Subtract before adding, per the **subtract-before-you-add** principle skill. The new sketch should be smaller than the old one before it grows.\n4. Return to Phase B and re-run arena.\n\n## Outputs\n\nThe caller's usage is written first and the type sketch derived from it. One file with new types and signatures for small changes; module map plus type definitions for larger work. The rationale ships alongside, shaped per `references\u002Frationale-template.md`, including the usage sketch and the synthesis decision.\n",{"name":5,"description":7},"main","1466ce6355abd331a82e9d9effd66d42bacb5978","pstack-codex\u002Fskills\u002Farchitect","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins","https:\u002F\u002Fgithub.com\u002Fgannonh","gannonhall.com","product \u002F dev; ex-google","2026-08-28 03:55:17",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add gannonh\u002Fcodex-plugins --skill architect",{"tool":38,"command":39},"bunx","bunx skills add gannonh\u002Fcodex-plugins --skill architect",{"tool":41,"command":42},"pnpm","pnpm dlx skills add gannonh\u002Fcodex-plugins --skill architect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Farchitect\u002FSKILL.md",true,[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdesign-red-flags.md","REFERENCE","参考文档",1944,"https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Farchitect\u002Freferences\u002Fdesign-red-flags.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frationale-template.md",3050,"https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Farchitect\u002Freferences\u002Frationale-template.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frunner-prompt.md",3091,"https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Farchitect\u002Freferences\u002Frunner-prompt.md",[61,68,75,82,89,96],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7BHZ35XF855R2QY1XDW7WKV","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7BHZ1JDZTKC9QNVDW8KV8K7","what-did-i-get-done","Summarize authored commits over a user-specified time period into a concise update","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Fwhat-did-i-get-done\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7BHZ00R1YG2BA0XHQ2ZW4EB","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7BHYYKRMCFKQ8C08X1ZPRSZ","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7BHYVM5D5C815M36BF1P13R","thermo-nuclear-code-quality-review","Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Fthermo-nuclear-code-quality-review\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7BHYQTEFR4H9882BM1FA4Y1","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fgannonh\u002Fcodex-plugins\u002Fblob\u002Fmain\u002Fpstack-codex\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[]]