[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75NQWA9SS76GEBCDTS4AB7B":3,"skill-same:01M75NQWA9SS76GEBCDTS4AB7B":65},{"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},"01M75NQWA9SS76GEBCDTS4AB7B","improve-codebase-architecture",null,"Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs\u002Fadr\u002F. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.","Kushal9889\u002Fclaude-plugins","Kushal9889","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234108364?v=4","01M75N3MJASY98ADCZ0RNAC66K","Kushal Gaddamwar","01M75N3MK1VKFXDPK7H6DV9Y2Z",2,"MIT","https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fmattpocock-skills\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: improve-codebase-architecture\ndescription: Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs\u002Fadr\u002F. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.\n---\n\n# Improve Codebase Architecture\n\nSurface architectural friction and propose **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.\n\n## Glossary\n\nUse these terms exactly in every suggestion. Consistent language is the point — don't drift into \"component,\" \"service,\" \"API,\" or \"boundary.\" Full definitions in [LANGUAGE.md](LANGUAGE.md).\n\n- **Module** — anything with an interface and an implementation (function, class, package, slice).\n- **Interface** — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.\n- **Implementation** — the code inside.\n- **Depth** — leverage at the interface: a lot of behaviour behind a small interface. **Deep** = high leverage. **Shallow** = interface nearly as complex as the implementation.\n- **Seam** — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not \"boundary.\")\n- **Adapter** — a concrete thing satisfying an interface at a seam.\n- **Leverage** — what callers get from depth.\n- **Locality** — what maintainers get from depth: change, bugs, knowledge concentrated in one place.\n\nKey principles (see [LANGUAGE.md](LANGUAGE.md) for the full list):\n\n- **Deletion test**: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.\n- **The interface is the test surface.**\n- **One adapter = hypothetical seam. Two adapters = real seam.**\n\nThis skill is _informed_ by the project's domain model. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.\n\n## Process\n\n### 1. Explore\n\nRead the project's domain glossary and any ADRs in the area you're touching first.\n\nThen use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:\n\n- Where does understanding one concept require bouncing between many small modules?\n- Where are modules **shallow** — interface nearly as complex as the implementation?\n- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?\n- Where do tightly-coupled modules leak across their seams?\n- Which parts of the codebase are untested, or hard to test through their current interface?\n\nApply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A \"yes, concentrates\" is the signal you want.\n\n### 2. Present candidates as an HTML report\n\nWrite a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from `$TMPDIR`, falling back to `\u002Ftmp` (or `%TEMP%` on Windows), and write to `\u003Ctmpdir>\u002Farchitecture-review-\u003Ctimestamp>.html` so each run gets a fresh file. Open it for the user — `xdg-open \u003Cpath>` on Linux, `open \u003Cpath>` on macOS, `start \u003Cpath>` on Windows — and tell them the absolute path.\n\nThe report uses **Tailwind via CDN** for layout and styling, and **Mermaid via CDN** for diagrams where a graph\u002Fflow\u002Fsequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS\u002FSVG visuals — use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs\u002FSVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a **before\u002Fafter visualisation**. Be visual.\n\nFor each candidate, the same template as before, but rendered as a card:\n\n- **Files** — which files\u002Fmodules are involved\n- **Problem** — why the current architecture is causing friction\n- **Solution** — plain English description of what would change\n- **Benefits** — explained in terms of locality and leverage, and how tests would improve\n- **Before \u002F After diagram** — side-by-side, custom-drawn, illustrating the shallowness and the deepening\n- **Recommendation strength** — one of `Strong`, `Worth exploring`, `Speculative`, rendered as a badge\n\nEnd the report with a **Top recommendation** section: which candidate you'd tackle first and why.\n\n**Use CONTEXT.md vocabulary for the domain, and [LANGUAGE.md](LANGUAGE.md) vocabulary for the architecture.** If `CONTEXT.md` defines \"Order,\" talk about \"the Order intake module\" — not \"the FooBarHandler,\" and not \"the Order service.\"\n\n**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _\"contradicts ADR-0007 — but worth reopening because…\"_). Don't list every theoretical refactor an ADR forbids.\n\nSee [HTML-REPORT.md](HTML-REPORT.md) for the full HTML scaffold, diagram patterns, and styling guidance.\n\nDo NOT propose interfaces yet. After the file is written, ask the user: \"Which of these would you like to explore?\"\n\n### 3. Grilling loop\n\nOnce the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.\n\nSide effects happen inline as decisions crystallize:\n\n- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md` — same discipline as `\u002Fgrill-with-docs` (see [CONTEXT-FORMAT.md](..\u002Fgrill-with-docs\u002FCONTEXT-FORMAT.md)). Create the file lazily if it doesn't exist.\n- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.\n- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _\"Want me to record this as an ADR so future architecture reviews don't re-suggest it?\"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons (\"not worth it right now\") and self-evident ones. See [ADR-FORMAT.md](..\u002Fgrill-with-docs\u002FADR-FORMAT.md).\n- **Want to explore alternative interfaces for the deepened module?** See [INTERFACE-DESIGN.md](INTERFACE-DESIGN.md).\n","# Improve Codebase Architecture\n\nSurface architectural friction and propose **deepening opportunities** — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.\n\n## Glossary\n\nUse these terms exactly in every suggestion. Consistent language is the point — don't drift into \"component,\" \"service,\" \"API,\" or \"boundary.\" Full definitions in [LANGUAGE.md](LANGUAGE.md).\n\n- **Module** — anything with an interface and an implementation (function, class, package, slice).\n- **Interface** — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.\n- **Implementation** — the code inside.\n- **Depth** — leverage at the interface: a lot of behaviour behind a small interface. **Deep** = high leverage. **Shallow** = interface nearly as complex as the implementation.\n- **Seam** — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not \"boundary.\")\n- **Adapter** — a concrete thing satisfying an interface at a seam.\n- **Leverage** — what callers get from depth.\n- **Locality** — what maintainers get from depth: change, bugs, knowledge concentrated in one place.\n\nKey principles (see [LANGUAGE.md](LANGUAGE.md) for the full list):\n\n- **Deletion test**: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.\n- **The interface is the test surface.**\n- **One adapter = hypothetical seam. Two adapters = real seam.**\n\nThis skill is _informed_ by the project's domain model. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.\n\n## Process\n\n### 1. Explore\n\nRead the project's domain glossary and any ADRs in the area you're touching first.\n\nThen use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:\n\n- Where does understanding one concept require bouncing between many small modules?\n- Where are modules **shallow** — interface nearly as complex as the implementation?\n- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no **locality**)?\n- Where do tightly-coupled modules leak across their seams?\n- Which parts of the codebase are untested, or hard to test through their current interface?\n\nApply the **deletion test** to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A \"yes, concentrates\" is the signal you want.\n\n### 2. Present candidates as an HTML report\n\nWrite a self-contained HTML file to the OS temp directory so nothing lands in the repo. Resolve the temp dir from `$TMPDIR`, falling back to `\u002Ftmp` (or `%TEMP%` on Windows), and write to `\u003Ctmpdir>\u002Farchitecture-review-\u003Ctimestamp>.html` so each run gets a fresh file. Open it for the user — `xdg-open \u003Cpath>` on Linux, `open \u003Cpath>` on macOS, `start \u003Cpath>` on Windows — and tell them the absolute path.\n\nThe report uses **Tailwind via CDN** for layout and styling, and **Mermaid via CDN** for diagrams where a graph\u002Fflow\u002Fsequence reliably communicates the structure. Mix Mermaid with hand-crafted CSS\u002FSVG visuals — use Mermaid when relationships are graph-shaped (call graphs, dependencies, sequences), and hand-built divs\u002FSVG when you want something more editorial (mass diagrams, cross-sections, collapse animations). Each candidate gets a **before\u002Fafter visualisation**. Be visual.\n\nFor each candidate, the same template as before, but rendered as a card:\n\n- **Files** — which files\u002Fmodules are involved\n- **Problem** — why the current architecture is causing friction\n- **Solution** — plain English description of what would change\n- **Benefits** — explained in terms of locality and leverage, and how tests would improve\n- **Before \u002F After diagram** — side-by-side, custom-drawn, illustrating the shallowness and the deepening\n- **Recommendation strength** — one of `Strong`, `Worth exploring`, `Speculative`, rendered as a badge\n\nEnd the report with a **Top recommendation** section: which candidate you'd tackle first and why.\n\n**Use CONTEXT.md vocabulary for the domain, and [LANGUAGE.md](LANGUAGE.md) vocabulary for the architecture.** If `CONTEXT.md` defines \"Order,\" talk about \"the Order intake module\" — not \"the FooBarHandler,\" and not \"the Order service.\"\n\n**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _\"contradicts ADR-0007 — but worth reopening because…\"_). Don't list every theoretical refactor an ADR forbids.\n\nSee [HTML-REPORT.md](HTML-REPORT.md) for the full HTML scaffold, diagram patterns, and styling guidance.\n\nDo NOT propose interfaces yet. After the file is written, ask the user: \"Which of these would you like to explore?\"\n\n### 3. Grilling loop\n\nOnce the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.\n\nSide effects happen inline as decisions crystallize:\n\n- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md` — same discipline as `\u002Fgrill-with-docs` (see [CONTEXT-FORMAT.md](..\u002Fgrill-with-docs\u002FCONTEXT-FORMAT.md)). Create the file lazily if it doesn't exist.\n- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.\n- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _\"Want me to record this as an ADR so future architecture reviews don't re-suggest it?\"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing — skip ephemeral reasons (\"not worth it right now\") and self-evident ones. See [ADR-FORMAT.md](..\u002Fgrill-with-docs\u002FADR-FORMAT.md).\n- **Want to explore alternative interfaces for the deepened module?** See [INTERFACE-DESIGN.md](INTERFACE-DESIGN.md).\n",{"name":5,"description":7},"main","e49a897c0789a26d4e8cf16b3e0322b9032f584a","mattpocock-skills\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture",0,"https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins","https:\u002F\u002Fgithub.com\u002FKushal9889","https:\u002F\u002Fkushal-portfolio-223.netlify.app","AI Engineer · MSCS @ BU · Open PRs: vLLM #56846, LlamaIndex #23053 · Reported deepagents #4846 (maintainer fix #4925)","2026-11-13 01:03:25",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Kushal9889\u002Fclaude-plugins --skill improve-codebase-architecture",{"tool":39,"command":40},"bunx","bunx skills add Kushal9889\u002Fclaude-plugins --skill improve-codebase-architecture",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Kushal9889\u002Fclaude-plugins --skill improve-codebase-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fmattpocock-skills\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FSKILL.md",true,[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"DEEPENING.md","REFERENCE","参考文档",2565,"https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fmattpocock-skills\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FDEEPENING.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"HTML-REPORT.md",6671,"https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fmattpocock-skills\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FHTML-REPORT.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"INTERFACE-DESIGN.md",2725,"https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fmattpocock-skills\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FINTERFACE-DESIGN.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"LANGUAGE.md",3804,"https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fmattpocock-skills\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FLANGUAGE.md",[66,73,79,85,92,99],{"skillNo":67,"name":68,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":72},"01M78TAEHR7PW92YHTBFTJRMYP","higgsfield-skills","https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Finstalled\u002Fhiggsfield-skills\u002Fskills\u002Fhiggsfield-skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":74,"name":75,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":72},"01M78TAB9MCR7QH3NZJKH5PJFJ","cutaway","https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Finstalled\u002Fcutaway\u002Fskills\u002Fcutaway\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":6,"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":84,"publishedAt":72},"01M78TA9YK7YE80960SFP5QJ6D","cracked","https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Finstalled\u002Fcracked\u002Fskills\u002Fcracked\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M75NWKDRSD7GPTBD80S8P5KW","spec","Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator\nof the project spec. Triggers when the user asks to write a spec, start\na new spec, distill a spec from existing code, add invariants, amend\nsections (§G, §C, §I, §V, §T, §B), or record a bug via backprop.\nCommon phrasings: \"write the spec for...\", \"new spec\", \"bug: ...\",\n\"amend §V.3\", \"distill spec from code\", \"spec this idea\". Reads and\nfollows FORMAT.md for the caveman encoding rules and pipe-table shape\nof §T and §B.","https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fspec\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M75NWFNN2NFMPZY5X9Q2DTBT","check","Read-only drift detector. Diffs SPEC.md against current code and reports\nviolations grouped by severity. Writes nothing — suggests remedies via\nthe spec or build skills but never invokes them. Triggers when the user\nasks to check drift, audit the spec, verify invariants, or ask whether\ncode still matches the spec. Phrasings: \"check drift\", \"audit the spec\",\n\"does the code still match §V\", \"check invariants\", \"spec vs code\".","https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fcheck\u002FSKILL.md",[],[],{"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":105,"publishedAt":19},"01M75NWCP6RRA3PFBPN8B94FYE","backprop","Bug → spec protocol. When a bug is found or a test fails, trace the cause,\ndecide whether a new §V invariant would catch recurrence, append to §B.\nThis is the one non-obvious thing SDD does that plan-then-execute doesn't.\nTriggers on test failure, bug report, post-mortem, or explicit user ask.","https:\u002F\u002Fgithub.com\u002FKushal9889\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fworkflow\u002Fskills\u002Fbackprop\u002FSKILL.md",[],[]]