[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CYWZPFW21ZVCH0VDCDW7FM":3,"skill-same:01M7CYWZPFW21ZVCH0VDCDW7FM":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M7CYWZPFW21ZVCH0VDCDW7FM","frontend",null,"Detect a repo's current frontend state and bring it to a professional, cohesive look with minimal design decisions from the user — install or wire an appropriate component system, write a project DESIGN.md, and verify the result with a screenshot-critique loop. Manually invoked via \u002Ffrontend against any repo, regardless of how much frontend work already exists there.","jpol34\u002Fpolyak-dev-kit","jpol34","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14319666?v=4","01M7CYWYBNQWVRNN6SNRX8V8B8","01M7CYWYCQZX9312AEP87MYQ42",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: frontend\ndescription: Detect a repo's current frontend state and bring it to a professional, cohesive\n  look with minimal design decisions from the user — install or wire an appropriate component\n  system, write a project DESIGN.md, and verify the result with a screenshot-critique loop.\n  Manually invoked via \u002Ffrontend against any repo, regardless of how much frontend work already\n  exists there.\n---\n\n# Frontend polish\n\nTurn whatever frontend state a repo is in — nothing, something inconsistent, or an already\nmature design system — into a cohesive, professional result, while making as few design\ndecisions on the user's behalf as possible without asking for their taste directly. Follow\nthese steps in order.\n\n## 1. Precondition: aesthetic guardrails\n\nThis skill orchestrates *what* gets changed; it deliberately does not carry its own aesthetic\nguidance, because the official `frontend-design` skill already covers that (avoiding generic\nAI-slop palettes and typography, a plan-review-build-critique process). Check whether that\nskill is available in this session.\n\nIf it is not available: tell the user it's required for good results and offer to install it\n(`\u002Fplugin install frontend-design@claude-plugins-official`). Only continue without it if the\nuser explicitly says to proceed anyway — and if so, note in the final report that aesthetic\nguardrails were skipped for this run.\n\n## 2. Precondition: git safety\n\nRun `git status --porcelain` in the target repo. If it's not a git repository, or the working\ntree isn't clean, stop and ask the user whether to proceed anyway, commit\u002Fstash first, or create\na throwaway branch. Do not write any files until the tree is clean or the user has explicitly\naccepted the risk.\n\n## 3. Detect\n\nRun `python \"\u003Cskill-dir>\u002Fscripts\u002Fdetect.py\" \u003Crepo-root>` (substitute the actual path to this\nskill's directory and the repo being worked on). This is a deterministic scan — trust its\n`evidence` field over any impression from skimming the repo yourself, and show that evidence to\nthe user later rather than restating a bare verdict.\n\nIt returns:\n- `framework`: `next`, `react`, or `other`\n- `maturity`: `bootstrap` (no real UI system yet) or `existing` (some system is present)\n- `signal`: `found` or `none` — `none` means detection was inconclusive, not that the repo is\n  empty\n- `evidence`: the concrete facts behind the classification\n\n## 4. Classify and pick a path\n\n- `framework` is `next` or `react`, `maturity` is `bootstrap` → `references\u002Fbootstrap-react.md`\n- `framework` is `next` or `react`, `maturity` is `existing` → read the `evidence`, then form a\n  recommendation between two paths (do not treat this as fact — it's your read of the evidence,\n  and the user can override it at the confirm gate):\n  - `references\u002Fretrofit-react.md` if the evidence points to inconsistent or ad hoc styling\n    (many small CSS files, mixed\u002Fno component library, no coherent token system)\n  - `references\u002Fexisting-system-react.md` if the evidence points to one coherent system already\n    in place (a real component library, a design-token setup, few one-off styles)\n- `framework` is `other`, or `signal` is `none` → `references\u002Fnon-react.md`, regardless of\n  `maturity`. If `signal` is `none`, tell the user at the confirm gate that detection was\n  inconclusive so they can correct the path before anything is touched.\n\n## 5. Confirm gate\n\nBefore writing anything, present:\n- the detected classification and its evidence\n- the chosen path (and the recommended alternative, for react+existing repos, so the user can\n  switch)\n- the theme or token direction you'd apply, already picked — don't ask the user to choose a\n  theme, just show what you picked and why\n- a draft `DESIGN.md` for the target repo\n- the file allowlist this run will stay inside — the specific files\u002Fdirectories relevant to the\n  chosen path (see each reference file for its scope), plus `DESIGN.md` and, if a component\n  library is being installed, `package.json`\n\nTreat this as a negotiation, not a yes\u002Fno gate. If the user pushes back on any part — wrong\npath, disagrees with the theme, wants a file excluded — revise that part and present again\nrather than starting over or proceeding regardless. Only move to execution once the user gives\nan explicit go-ahead.\n\n## 6. Execute\n\nFollow the chosen reference file. Stay inside the allowlist confirmed in step 5. Write\n`DESIGN.md` into the target repo — this is the one artifact from this whole skill that's\nproject-specific, since it describes that project's actual design system, not this skill's\nprocess.\n\n## 7. Enforce the allowlist\n\nBefore reporting anything as done, run `git diff --name-only` and `git status --porcelain` in\nthe target repo and check every changed or new path against the allowlist confirmed at the gate.\nIf anything falls outside it, stop and tell the user exactly what was touched beyond scope — let\nthem decide whether to keep it, rather than shipping it silently.\n\n## 8. Verify\n\nFollow `references\u002Fvisual-loop.md` for a bounded screenshot-critique-fix pass against the\nrunning app.\n\n## 9. Report\n\nSummarize: which path was taken, which files changed (cross-checked against the allowlist in\nstep 7), what the visual loop found and fixed, screenshots if available, and anything left\nunresolved within its iteration budget.\n","# Frontend polish\n\nTurn whatever frontend state a repo is in — nothing, something inconsistent, or an already\nmature design system — into a cohesive, professional result, while making as few design\ndecisions on the user's behalf as possible without asking for their taste directly. Follow\nthese steps in order.\n\n## 1. Precondition: aesthetic guardrails\n\nThis skill orchestrates *what* gets changed; it deliberately does not carry its own aesthetic\nguidance, because the official `frontend-design` skill already covers that (avoiding generic\nAI-slop palettes and typography, a plan-review-build-critique process). Check whether that\nskill is available in this session.\n\nIf it is not available: tell the user it's required for good results and offer to install it\n(`\u002Fplugin install frontend-design@claude-plugins-official`). Only continue without it if the\nuser explicitly says to proceed anyway — and if so, note in the final report that aesthetic\nguardrails were skipped for this run.\n\n## 2. Precondition: git safety\n\nRun `git status --porcelain` in the target repo. If it's not a git repository, or the working\ntree isn't clean, stop and ask the user whether to proceed anyway, commit\u002Fstash first, or create\na throwaway branch. Do not write any files until the tree is clean or the user has explicitly\naccepted the risk.\n\n## 3. Detect\n\nRun `python \"\u003Cskill-dir>\u002Fscripts\u002Fdetect.py\" \u003Crepo-root>` (substitute the actual path to this\nskill's directory and the repo being worked on). This is a deterministic scan — trust its\n`evidence` field over any impression from skimming the repo yourself, and show that evidence to\nthe user later rather than restating a bare verdict.\n\nIt returns:\n- `framework`: `next`, `react`, or `other`\n- `maturity`: `bootstrap` (no real UI system yet) or `existing` (some system is present)\n- `signal`: `found` or `none` — `none` means detection was inconclusive, not that the repo is\n  empty\n- `evidence`: the concrete facts behind the classification\n\n## 4. Classify and pick a path\n\n- `framework` is `next` or `react`, `maturity` is `bootstrap` → `references\u002Fbootstrap-react.md`\n- `framework` is `next` or `react`, `maturity` is `existing` → read the `evidence`, then form a\n  recommendation between two paths (do not treat this as fact — it's your read of the evidence,\n  and the user can override it at the confirm gate):\n  - `references\u002Fretrofit-react.md` if the evidence points to inconsistent or ad hoc styling\n    (many small CSS files, mixed\u002Fno component library, no coherent token system)\n  - `references\u002Fexisting-system-react.md` if the evidence points to one coherent system already\n    in place (a real component library, a design-token setup, few one-off styles)\n- `framework` is `other`, or `signal` is `none` → `references\u002Fnon-react.md`, regardless of\n  `maturity`. If `signal` is `none`, tell the user at the confirm gate that detection was\n  inconclusive so they can correct the path before anything is touched.\n\n## 5. Confirm gate\n\nBefore writing anything, present:\n- the detected classification and its evidence\n- the chosen path (and the recommended alternative, for react+existing repos, so the user can\n  switch)\n- the theme or token direction you'd apply, already picked — don't ask the user to choose a\n  theme, just show what you picked and why\n- a draft `DESIGN.md` for the target repo\n- the file allowlist this run will stay inside — the specific files\u002Fdirectories relevant to the\n  chosen path (see each reference file for its scope), plus `DESIGN.md` and, if a component\n  library is being installed, `package.json`\n\nTreat this as a negotiation, not a yes\u002Fno gate. If the user pushes back on any part — wrong\npath, disagrees with the theme, wants a file excluded — revise that part and present again\nrather than starting over or proceeding regardless. Only move to execution once the user gives\nan explicit go-ahead.\n\n## 6. Execute\n\nFollow the chosen reference file. Stay inside the allowlist confirmed in step 5. Write\n`DESIGN.md` into the target repo — this is the one artifact from this whole skill that's\nproject-specific, since it describes that project's actual design system, not this skill's\nprocess.\n\n## 7. Enforce the allowlist\n\nBefore reporting anything as done, run `git diff --name-only` and `git status --porcelain` in\nthe target repo and check every changed or new path against the allowlist confirmed at the gate.\nIf anything falls outside it, stop and tell the user exactly what was touched beyond scope — let\nthem decide whether to keep it, rather than shipping it silently.\n\n## 8. Verify\n\nFollow `references\u002Fvisual-loop.md` for a bounded screenshot-critique-fix pass against the\nrunning app.\n\n## 9. Report\n\nSummarize: which path was taken, which files changed (cross-checked against the allowlist in\nstep 7), what the visual loop found and fixed, screenshots if available, and anything left\nunresolved within its iteration budget.\n",{"name":5,"description":7},"master","df6f0f83d05e7ba7bee5e76189c60dd5834a8173","skills\u002Ffrontend","https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit","https:\u002F\u002Fgithub.com\u002Fjpol34","2026-09-18 03:22:58",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add jpol34\u002Fpolyak-dev-kit --skill frontend",{"tool":35,"command":36},"bunx","bunx skills add jpol34\u002Fpolyak-dev-kit --skill frontend",{"tool":38,"command":39},"pnpm","pnpm dlx skills add jpol34\u002Fpolyak-dev-kit --skill frontend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002FSKILL.md",true,[43,49,53,57,61,65],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"references\u002Fbootstrap-react.md","REFERENCE","参考文档",4170,"https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002Freferences\u002Fbootstrap-react.md",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fexisting-system-react.md",1471,"https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002Freferences\u002Fexisting-system-react.md",{"path":54,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fnon-react.md",1504,"https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002Freferences\u002Fnon-react.md",{"path":58,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fretrofit-react.md",1755,"https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002Freferences\u002Fretrofit-react.md",{"path":62,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fvisual-loop.md",2005,"https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002Freferences\u002Fvisual-loop.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fdetect.py","SCRIPT","脚本",5919,"https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Ffrontend\u002Fscripts\u002Fdetect.py",[72,79,86,93],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M7CYXCKJP92GP4TG2WTWETQ6","to-tickets","Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).","https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7CYX7V3CEGDMK16ER3PSW1J","research","Research a topic exhaustively before planning or building — discuss the goal, draft a comprehensive question set, dispatch parallel research agents against it, and synthesize a findings report. Stops there; does NOT chain into \u002Fgrill-me or plan mode. Use when the user wants to research, investigate, or survey a topic\u002Ftechnology\u002Fapproach before deciding what to do about it.","https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fresearch\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7CYX5Q5Z4PHE4QYZJKH7PWC","grilling","Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.","https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M7CYX49PT6SPAQCVK58WBF94","grill","A relentless interview to sharpen a plan or design.","https:\u002F\u002Fgithub.com\u002Fjpol34\u002Fpolyak-dev-kit\u002Fblob\u002Fmaster\u002Fskills\u002Fgrill\u002FSKILL.md",[],[]]