[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KX1675M9PYRKRV5DHXBQ0P":3,"skill-same:01M6KX1675M9PYRKRV5DHXBQ0P":77},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6KX1675M9PYRKRV5DHXBQ0P","harness-builder",null,"Analyze a codebase and recommend an agent harness (agents, skills, hooks).","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\u002Fmeta\u002Fharness-builder\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"harness builder","harness","builder","edit","codebase","recommend","ls","add","git log","log","hooks","status","write","read","grep","agent harness","analyze","Bash","git","2026-11-10 10:12:30",false,"---\nname: harness-builder\ndescription: Analyze a codebase and recommend an agent harness (agents, skills, hooks).\nallowed-tools: Read, Grep, Glob, Write, Edit, Bash(git log*), Bash(git status*), Bash(git add*), Bash(ls*)\n---\n\n# Harness Builder\n\nGet a harness recommendation tailored to this codebase (agents, skills, hooks,\nand a `CLAUDE.md` skeleton) instead of starting from scratch. The\n`harness-builder` agent reads the stack, workflows, and domain; you review,\ntrim, and then generate the files. Use it early in a project's setup. Its\nrecommendations are starting points that you are expected to customize.\n\nIt needs a git repository (the agent reads history) and a verification\ncommand such as a test suite, linter, or build. The agent sorts what it\nrecommends into facts, project-local content, and the generic set of\nharness-kit skills and agents. This skill writes only the project-local\nClaude Code files. `\u002Fharness bootstrap` (or `$harness bootstrap` on Codex)\nruns the same agent as its first step, then writes the facts and vendors the\ngeneric set for both hosts; use it for a full setup, and this skill when you\nwant the recommendation and a Claude-side starting point.\n\nWhat the agent tends to recommend, and how to read it, is in\n[recommendations.md](recommendations.md).\n\n## 1. Run the agent\n\nDispatch the `harness-builder` agent on the current codebase. Pass it the\nabsolute paths of the harness skill's catalogs so it recommends from them\nrather than from memory: `external-plugins.md`, `architecture-patterns.md`,\n`hooks-reference.md`, and `release-please-reference.md`. The harness skill sits\nbeside this one, in `\u003Cskill-dir>\u002F..\u002Fharness\u002F`, in the plugin and in a\nvendored snapshot alike. Also pass the generic names it can choose from: the\nskill folders beside this one and the plugin's agents.\n\nDone when the agent has returned its report and the report does not say the\ncatalogs were missing; if it does, dispatch it again with the paths. When the\nreport misreads the stack, use the questions under \"Stack detection\" in\nrecommendations.md and fold the answers in.\n\n## 2. Review the recommendations\n\nThe report covers:\n\n- **Stack**: language, frameworks, and the verification command.\n- **Facts**: the verification command as `[facts] verification_command`,\n  then the prose for `AGENTS.md`'s `## Project facts` section.\n- **Agents**: the analytical work to hand off, split into generic\n  (code-reviewer, verifier) and project-local (test-writer, domain-advisor).\n  Judge roles and model tiers against \"Agents\" in recommendations.md.\n- **Skills**: the workflows to provide, split into the generic set (always\n  `\u002Fcommit`, plus GitHub and frontend tools when detected) and project-local\n  skills. \"Skills\" in recommendations.md covers when a need is a fact and\n  when it is a local skill.\n- **Hooks**: formatters, validators, and guidance for auto-fixing. \"Hooks\" in\n  recommendations.md has a working example; the reasoning behind the stages\n  is in `\u003Cskill-dir>\u002F..\u002Fharness\u002Fhooks-patterns.md`.\n- **Domain knowledge**: entity types, ownership, the auth and session system,\n  and the side effects of mutating core entities.\n\nPrefer the generic skills (`\u002Fcommit`, `\u002Freview-pr`) the agent points to,\nwith the project's facts stated for them, over generating new ones. Done\nwhen every recommendation is either accepted or explained away to the user.\n\n## 3. Customize\n\nRemove the agents and skills the project doesn't need, add project-specific\nagents or constraints, and put the project's actual domain rules into\n`CLAUDE.md` in place of boilerplate. Done when the user approves the trimmed\nlist.\n\n## 4. Generate the files\n\nAfter approval, generate the project-local content only:\n\n- `.claude\u002Fagents\u002F*.md`, one per project-local agent, with its tool\n  permissions and domain context.\n- `.claude\u002Fskills\u002F*\u002FSKILL.md`, one per project-local skill, with\n  `allowed-tools` and a description that says what it does and when.\n- `CLAUDE.md`, the harness documentation, with the facts.\n- `.gitignore` updates.\n\nThe generic set is never copied by hand; `\u002Fharness bootstrap` vendors it.\n\nThen run the project's verification command to confirm the setup works. On a\nNix flake, `git add` the new files first, because flakes only see tracked\nfiles. Done when every approved file exists and the verification command\npasses.\n\n## Related\n\n- `\u002Fharness`: audits harness quality, and bootstraps both hosts.\n- `\u002Fskill-writer`: well-structured skills.\n","# Harness Builder\n\nGet a harness recommendation tailored to this codebase (agents, skills, hooks,\nand a `CLAUDE.md` skeleton) instead of starting from scratch. The\n`harness-builder` agent reads the stack, workflows, and domain; you review,\ntrim, and then generate the files. Use it early in a project's setup. Its\nrecommendations are starting points that you are expected to customize.\n\nIt needs a git repository (the agent reads history) and a verification\ncommand such as a test suite, linter, or build. The agent sorts what it\nrecommends into facts, project-local content, and the generic set of\nharness-kit skills and agents. This skill writes only the project-local\nClaude Code files. `\u002Fharness bootstrap` (or `$harness bootstrap` on Codex)\nruns the same agent as its first step, then writes the facts and vendors the\ngeneric set for both hosts; use it for a full setup, and this skill when you\nwant the recommendation and a Claude-side starting point.\n\nWhat the agent tends to recommend, and how to read it, is in\n[recommendations.md](recommendations.md).\n\n## 1. Run the agent\n\nDispatch the `harness-builder` agent on the current codebase. Pass it the\nabsolute paths of the harness skill's catalogs so it recommends from them\nrather than from memory: `external-plugins.md`, `architecture-patterns.md`,\n`hooks-reference.md`, and `release-please-reference.md`. The harness skill sits\nbeside this one, in `\u003Cskill-dir>\u002F..\u002Fharness\u002F`, in the plugin and in a\nvendored snapshot alike. Also pass the generic names it can choose from: the\nskill folders beside this one and the plugin's agents.\n\nDone when the agent has returned its report and the report does not say the\ncatalogs were missing; if it does, dispatch it again with the paths. When the\nreport misreads the stack, use the questions under \"Stack detection\" in\nrecommendations.md and fold the answers in.\n\n## 2. Review the recommendations\n\nThe report covers:\n\n- **Stack**: language, frameworks, and the verification command.\n- **Facts**: the verification command as `[facts] verification_command`,\n  then the prose for `AGENTS.md`'s `## Project facts` section.\n- **Agents**: the analytical work to hand off, split into generic\n  (code-reviewer, verifier) and project-local (test-writer, domain-advisor).\n  Judge roles and model tiers against \"Agents\" in recommendations.md.\n- **Skills**: the workflows to provide, split into the generic set (always\n  `\u002Fcommit`, plus GitHub and frontend tools when detected) and project-local\n  skills. \"Skills\" in recommendations.md covers when a need is a fact and\n  when it is a local skill.\n- **Hooks**: formatters, validators, and guidance for auto-fixing. \"Hooks\" in\n  recommendations.md has a working example; the reasoning behind the stages\n  is in `\u003Cskill-dir>\u002F..\u002Fharness\u002Fhooks-patterns.md`.\n- **Domain knowledge**: entity types, ownership, the auth and session system,\n  and the side effects of mutating core entities.\n\nPrefer the generic skills (`\u002Fcommit`, `\u002Freview-pr`) the agent points to,\nwith the project's facts stated for them, over generating new ones. Done\nwhen every recommendation is either accepted or explained away to the user.\n\n## 3. Customize\n\nRemove the agents and skills the project doesn't need, add project-specific\nagents or constraints, and put the project's actual domain rules into\n`CLAUDE.md` in place of boilerplate. Done when the user approves the trimmed\nlist.\n\n## 4. Generate the files\n\nAfter approval, generate the project-local content only:\n\n- `.claude\u002Fagents\u002F*.md`, one per project-local agent, with its tool\n  permissions and domain context.\n- `.claude\u002Fskills\u002F*\u002FSKILL.md`, one per project-local skill, with\n  `allowed-tools` and a description that says what it does and when.\n- `CLAUDE.md`, the harness documentation, with the facts.\n- `.gitignore` updates.\n\nThe generic set is never copied by hand; `\u002Fharness bootstrap` vendors it.\n\nThen run the project's verification command to confirm the setup works. On a\nNix flake, `git add` the new files first, because flakes only see tracked\nfiles. Done when every approved file exists and the verification command\npasses.\n\n## Related\n\n- `\u002Fharness`: audits harness quality, and bootstraps both hosts.\n- `\u002Fskill-writer`: well-structured skills.\n",{"name":5,"description":7,"allowed-tools":43},"Read, Grep, Glob, Write, Edit, Bash(git log*), Bash(git status*), Bash(git add*), Bash(ls*)","main","023b01bfb4a86fbf1e38a749f1044cce3e5da67d","skills\u002Fmeta\u002Fharness-builder",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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add dougborg\u002Fharness-kit --skill harness-builder",{"tool":59,"command":60},"bunx","bunx skills add dougborg\u002Fharness-kit --skill harness-builder",{"tool":62,"command":63},"pnpm","pnpm dlx skills add dougborg\u002Fharness-kit --skill harness-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fmeta\u002Fharness-builder\u002FSKILL.md",true,[67,73],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"agents\u002Fopenai.yaml","REFERENCE","参考文档",162,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fmeta\u002Fharness-builder\u002Fagents\u002Fopenai.yaml",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"recommendations.md",6236,"https:\u002F\u002Fgithub.com\u002Fdougborg\u002Fharness-kit\u002Fblob\u002Fmain\u002Fskills\u002Fmeta\u002Fharness-builder\u002Frecommendations.md",[78,97,116,149,172,189],{"skillNo":79,"name":80,"nameZh":6,"description":81,"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":89,"publishedAt":38},"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",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[80,90,91,92,93,94,95,96],"lessons","you","with","learned","record","references","sessions",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":108,"publishedAt":38},"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",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[109,110,111,112,113,114,92,31,32,115],"logo","designer","svg logo designer","SVG","color","concepts","generate",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":128,"publishedAt":38},"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",[122,125],{"categoryNo":123,"categoryName":124,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":126,"categoryName":127,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000036","内容创作者",[129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148],"writer","documentation writer","documentation","entries","changelog","architecture","document","files","use","question","README","notes","code","examples","pages","for","information","guides","type","writing",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":38},"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",[],[156,157,158,159,144,160,161,92,162,163,164,165,166,167,168,169,170,171,20,141],"adhd","mode","adhd mode","next","action","kit","output","style","progress","time","back","stop","session","reader","first","REST",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":38},"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",[],[179,180,181,92,182,183,184,185,186,187,188],"wait","wait what","re","it","missing","message","context","explain","land","last",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":38},"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",[],[196,197,144,198,199,200,201,91,202,182,203,204],"to questionnaire","questionnaire","person","can","answer","meeting","make","async","decision"]