[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KWZNYCMPQWNX15KKW8RNG8":3,"skill-same:01M6KWZNYCMPQWNX15KKW8RNG8":82},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6KWZNYCMPQWNX15KKW8RNG8","improve-codebase-architecture",null,"Scans a codebase for deepening opportunities (shallow modules that would be easier to test and navigate if their interfaces shrank), presents them as a visual HTML report, then grills through whichever one the user picks. Use when the user asks for an architecture review, wants to find refactoring opportunities, or says the codebase is getting hard to change.","dougborg\u002Fharness-kit","dougborg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1261222?v=4","01M6KWS4PB51EYD4ZDJJSGNGB2","Doug Borg","01M6KWS4T8ZZW6SX5QZS9B5BN2",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"improve codebase architecture","codebase","architecture","improve","deepening","review","for","as","visual","modules","html","use","user","find","html report","refactoring","report","architecture review","change","test","2026-11-10 10:12:30",false,"---\nname: improve-codebase-architecture\ndescription: >-\n  Scans a codebase for deepening opportunities (shallow modules that would be\n  easier to test and navigate if their interfaces shrank), presents them as a\n  visual HTML report, then grills through whichever one the user picks. Use\n  when the user asks for an architecture review, wants to find refactoring\n  opportunities, or says the codebase is getting hard to change.\n---\n\n# Improve Codebase Architecture\n\nFind architectural friction and propose **deepening opportunities**:\nrefactors that turn shallow modules into deep ones, for testability and so\nagents can navigate the code.\n\nTwo vocabularies drive every suggestion:\n\n- **Architecture.** Call the Skill tool with \"codebase-design\" for its terms\n  (module, interface, implementation, depth, seam, adapter, leverage,\n  locality) and principles (the deletion test, \"the interface is the test\n  surface\", \"one adapter is a hypothetical seam, two make it real\"). Use\n  those terms exactly; don't drift into \"component\", \"service\", \"API\", or\n  \"boundary\".\n- **Domain.** The project's `GLOSSARY.md` (or the one `GLOSSARY-MAP.md`\n  points to for the area) names the good seams, and ADRs in `docs\u002Fadr\u002F`\n  record decisions this review doesn't re-litigate.\n\n## 1. Explore\n\n**Scope before you scan.** Deepening pays off by making future changes\neasier, so weight the parts of the code that change often:\n\n- If the user named a direction (a module, a subsystem, a pain point), take\n  it and skip the next bullet.\n- Otherwise read a good stretch of `git log --oneline --name-only` for hot\n  spots, the files and areas that keep coming up, and look there first. If\n  changes are scattered with no hot spot, widen the net.\n\nRead the glossary and any ADRs for the area. Then send a subagent to walk the\ncode: on Claude Code the `Explore` agent, which doesn't load `CLAUDE.md`, so\nput the glossary terms and the questions below in its prompt; on Codex a\nspawned agent. Have it explore freely and report where it hits friction:\n\n- Where does one concept mean bouncing between many small modules?\n- Where are modules **shallow**, with an interface nearly as complex as the\n  implementation?\n- Where were pure functions extracted for testability while the bugs hide in\n  how they're called (no **locality**)?\n- Where do tightly coupled modules leak across their seams?\n- What is untested, or hard to test through its current interface?\n\nApply the **deletion test** to every suspect: would deleting it concentrate\ncomplexity, or just move it? \"Concentrates\" is the signal you want.\n\nDone when you have a short list of candidates, each with its files and the\nfriction it causes.\n\n## 2. Present candidates as an HTML report\n\nWrite one self-contained HTML file to the OS temp directory, so nothing lands\nin the repo: `${TMPDIR:-\u002Ftmp}\u002Farchitecture-review-\u003Ctimestamp>.html` (`%TEMP%`\non Windows). Open it (`open` on macOS, `xdg-open` on Linux, `start` on\nWindows) and give the user the absolute path, since opening a browser can\nfail inside a sandbox.\n\nEach candidate gets a card with its files, the problem, the solution in\nplain English, the wins in terms of locality, leverage, and tests, a\nbefore\u002Fafter diagram, and a strength badge: `Strong`, `Worth exploring`, or\n`Speculative`. End with a **Top recommendation**: which candidate to tackle\nfirst and why. [HTML-REPORT.md](HTML-REPORT.md) has the scaffold, the diagram\npatterns, and the tone.\n\nName things with the glossary. If `GLOSSARY.md` defines \"Order\", write \"the\nOrder intake module\", not \"the FooBarHandler\" or \"the Order service\".\n\nIf a candidate contradicts an ADR, include it only when the friction is real\nenough to reopen the decision, and mark it in the card (\"contradicts\nADR-0007, but worth reopening because…\"). Don't list every refactor an ADR\nrules out.\n\nDon't propose interfaces yet. Ask which candidate to explore: through\n`AskUserQuestion` on Claude Code, with the top candidates as options; as a\nplain question on Codex.\n\nDone when the report is open or its path is shared, and the user has picked\na candidate.\n\n## 3. Grill the chosen candidate\n\nCall the Skill tool with \"grilling\" to walk the decision tree with the user:\nconstraints, dependencies, the shape of the deepened module, what sits\nbehind the seam, which tests survive.\n\nCall the Skill tool with \"domain-modeling\" to keep the domain model current\nas decisions land:\n\n- **A deepened module named after a concept not in `GLOSSARY.md`?** Add the\n  term, creating the file if needed.\n- **A fuzzy term sharpened in conversation?** Update `GLOSSARY.md` there and\n  then.\n- **The user rejects the candidate for a load-bearing reason?** Offer an ADR:\n  \"Want me to record this as an ADR so future architecture reviews don't\n  suggest it again?\" Offer only when a future reviewer would need the\n  reason; skip passing reasons (\"not now\") and obvious ones.\n- **Want alternative interfaces for the deepened module?** Use\n  `codebase-design`'s design-it-twice pattern.\n\nDone when the candidate is settled (a chosen interface, or a recorded\nrejection) and the glossary and ADRs reflect what was decided.\n","# Improve Codebase Architecture\n\nFind architectural friction and propose **deepening opportunities**:\nrefactors that turn shallow modules into deep ones, for testability and so\nagents can navigate the code.\n\nTwo vocabularies drive every suggestion:\n\n- **Architecture.** Call the Skill tool with \"codebase-design\" for its terms\n  (module, interface, implementation, depth, seam, adapter, leverage,\n  locality) and principles (the deletion test, \"the interface is the test\n  surface\", \"one adapter is a hypothetical seam, two make it real\"). Use\n  those terms exactly; don't drift into \"component\", \"service\", \"API\", or\n  \"boundary\".\n- **Domain.** The project's `GLOSSARY.md` (or the one `GLOSSARY-MAP.md`\n  points to for the area) names the good seams, and ADRs in `docs\u002Fadr\u002F`\n  record decisions this review doesn't re-litigate.\n\n## 1. Explore\n\n**Scope before you scan.** Deepening pays off by making future changes\neasier, so weight the parts of the code that change often:\n\n- If the user named a direction (a module, a subsystem, a pain point), take\n  it and skip the next bullet.\n- Otherwise read a good stretch of `git log --oneline --name-only` for hot\n  spots, the files and areas that keep coming up, and look there first. If\n  changes are scattered with no hot spot, widen the net.\n\nRead the glossary and any ADRs for the area. Then send a subagent to walk the\ncode: on Claude Code the `Explore` agent, which doesn't load `CLAUDE.md`, so\nput the glossary terms and the questions below in its prompt; on Codex a\nspawned agent. Have it explore freely and report where it hits friction:\n\n- Where does one concept mean bouncing between many small modules?\n- Where are modules **shallow**, with an interface nearly as complex as the\n  implementation?\n- Where were pure functions extracted for testability while the bugs hide in\n  how they're called (no **locality**)?\n- Where do tightly coupled modules leak across their seams?\n- What is untested, or hard to test through its current interface?\n\nApply the **deletion test** to every suspect: would deleting it concentrate\ncomplexity, or just move it? \"Concentrates\" is the signal you want.\n\nDone when you have a short list of candidates, each with its files and the\nfriction it causes.\n\n## 2. Present candidates as an HTML report\n\nWrite one self-contained HTML file to the OS temp directory, so nothing lands\nin the repo: `${TMPDIR:-\u002Ftmp}\u002Farchitecture-review-\u003Ctimestamp>.html` (`%TEMP%`\non Windows). Open it (`open` on macOS, `xdg-open` on Linux, `start` on\nWindows) and give the user the absolute path, since opening a browser can\nfail inside a sandbox.\n\nEach candidate gets a card with its files, the problem, the solution in\nplain English, the wins in terms of locality, leverage, and tests, a\nbefore\u002Fafter diagram, and a strength badge: `Strong`, `Worth exploring`, or\n`Speculative`. End with a **Top recommendation**: which candidate to tackle\nfirst and why. [HTML-REPORT.md](HTML-REPORT.md) has the scaffold, the diagram\npatterns, and the tone.\n\nName things with the glossary. If `GLOSSARY.md` defines \"Order\", write \"the\nOrder intake module\", not \"the FooBarHandler\" or \"the Order service\".\n\nIf a candidate contradicts an ADR, include it only when the friction is real\nenough to reopen the decision, and mark it in the card (\"contradicts\nADR-0007, but worth reopening because…\"). Don't list every refactor an ADR\nrules out.\n\nDon't propose interfaces yet. Ask which candidate to explore: through\n`AskUserQuestion` on Claude Code, with the top candidates as options; as a\nplain question on Codex.\n\nDone when the report is open or its path is shared, and the user has picked\na candidate.\n\n## 3. Grill the chosen candidate\n\nCall the Skill tool with \"grilling\" to walk the decision tree with the user:\nconstraints, dependencies, the shape of the deepened module, what sits\nbehind the seam, which tests survive.\n\nCall the Skill tool with \"domain-modeling\" to keep the domain model current\nas decisions land:\n\n- **A deepened module named after a concept not in `GLOSSARY.md`?** Add the\n  term, creating the file if needed.\n- **A fuzzy term sharpened in conversation?** Update `GLOSSARY.md` there and\n  then.\n- **The user rejects the candidate for a load-bearing reason?** Offer an ADR:\n  \"Want me to record this as an ADR so future architecture reviews don't\n  suggest it again?\" Offer only when a future reviewer would need the\n  reason; skip passing reasons (\"not now\") and obvious ones.\n- **Want alternative interfaces for the deepened module?** Use\n  `codebase-design`'s design-it-twice pattern.\n\nDone when the candidate is settled (a chosen interface, or a recorded\nrejection) and the glossary and ADRs reflect what was decided.\n",{"name":5,"description":7},"main","023b01bfb4a86fbf1e38a749f1044cce3e5da67d","skills\u002Fengineering\u002Fimprove-codebase-architecture",1,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit","https:\u002F\u002Fgithub.com\u002Fdougborg","http:\u002F\u002Fdougborg.org","Platforms and Infrastructure Software Engineer","2026-11-13 07:43:37",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add dougborg\u002Fharness-kit --skill improve-codebase-architecture",{"tool":64,"command":65},"bunx","bunx skills add dougborg\u002Fharness-kit --skill improve-codebase-architecture",{"tool":67,"command":68},"pnpm","pnpm dlx skills add dougborg\u002Fharness-kit --skill improve-codebase-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FSKILL.md",true,[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"agents\u002Fopenai.yaml","REFERENCE","参考文档",192,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002Fagents\u002Fopenai.yaml",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"HTML-REPORT.md",5587,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fengineering\u002Fimprove-codebase-architecture\u002FHTML-REPORT.md",[83,102,121,151,175,192],{"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":94,"publishedAt":44},"01M6KX4J65S5FZKMSN5DQNPSZM","teach","Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fteach\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[85,95,96,97,98,99,100,101],"lessons","you","with","learned","record","references","sessions",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":111,"publishedAt":44},"01M6KX4FSSG7MHF00JDT5QT0BQ","svg-logo-designer","Generate SVG logos with multiple concepts, layouts, and color variations.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fsvg-logo-designer\u002FSKILL.md",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[112,113,114,115,116,117,97,118,119,120],"logo","designer","svg logo designer","SVG","color","concepts","write","read","generate",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":133,"publishedAt":44},"01M6KX4BD3J9MZPPSH4MENH7FP","documentation-writer","Writes and revises human-facing documentation — READMEs, contributor and setup guides, reference pages, architecture notes, CLAUDE.md, and changelog entries. Covers picking the right document type for the question being asked, structuring for skimming, writing examples that actually run, and keeping docs from going stale. Use when creating or rewriting docs, when a README has drifted from the code, or when deciding where a piece of information belongs. For SKILL.md and agent files, use \u002Fskill-writer instead.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fdocumentation-writer\u002FSKILL.md",[127,130],{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":131,"categoryName":132,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000036","内容创作者",[134,135,136,137,138,26,139,140,35,141,142,143,144,145,146,30,147,148,149,150],"writer","documentation writer","documentation","entries","changelog","document","files","question","README","notes","code","examples","pages","information","guides","type","writing",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":44},"01M6KX47ZJ4ZWHDN3MY8SYAWZZ","adhd-mode","Shapes every response for a reader with ADHD: the next action first, numbered steps, progress restated each turn, tangents held back, concrete time estimates, wins made visible. Stays on for the rest of the session until the reader says \"stop adhd mode\". On Claude Code, the harness-kit:adhd output style does the same without invoking this skill.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fadhd-mode\u002FSKILL.md",[],[158,159,160,161,30,162,163,97,164,165,166,167,168,169,170,171,172,173,174,144],"adhd","mode","adhd mode","next","action","kit","output","style","progress","time","back","stop","session","reader","first","REST","harness",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":44},"01M6KX463Z6E18EPDW873GDHKB","wait-what","That last message didn't land: re-explain it with the missing context.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fwait-what\u002FSKILL.md",[],[182,183,184,97,185,186,187,188,189,190,191],"wait","wait what","re","it","missing","message","context","explain","land","last",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":198,"publishedAt":44},"01M6KX43NE1NB0Y2HECY515730","to-questionnaire","Turn a decision you can't make alone into a questionnaire for the one person who can answer it, filled in async or together in a meeting.","https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fthinking\u002Fto-questionnaire\u002FSKILL.md",[],[199,200,30,201,202,203,204,96,205,185,206,207],"to questionnaire","questionnaire","person","can","answer","meeting","make","async","decision"]