[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A5JQTSWM2YPS360XQ34SF":3,"skill-same:01M79A5JQTSWM2YPS360XQ34SF":47},{"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":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79A5JQTSWM2YPS360XQ34SF","cupertino-council",null,"Use at UI\u002Ffrontend build-time, before writing any code, whenever a user-facing interface or screen is being designed. Trigger on 'design this screen', 'build this UI', 'make this feel premium', 'this feels generic', or any request to design or implement a user-facing surface. Applies to any stack (HTML, React, Vue, native, etc.). Always run before code, never after — retrofitting the council onto finished code defeats the purpose. Not for a not-yet-scoped new feature where customer experience and technology are both still undecided — run cupertino-backwards first to establish the experience statement. Not for changing an interface that already exists -- fixing, adjusting or extending a shipped page or dashboard is cupertino-repair, which keeps everything else as it is; for a static accessibility or hardcoded-value audit of shipped source use befund-ui-audit.","Anselmoo\u002Fwerkstoff","Anselmoo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F13209783?v=4","01M799YTB3D7RZ4P3B8CSR2X85","Anselm Hahn","01M799YTBRAM6719D9V0NRGB4R",1,"MIT","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fcupertino\u002Fskills\u002Fcupertino-council\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cupertino-council\ndescription: \"Use at UI\u002Ffrontend build-time, before writing any code, whenever a user-facing interface or screen is being designed. Trigger on 'design this screen', 'build this UI', 'make this feel premium', 'this feels generic', or any request to design or implement a user-facing surface. Applies to any stack (HTML, React, Vue, native, etc.). Always run before code, never after — retrofitting the council onto finished code defeats the purpose. Not for a not-yet-scoped new feature where customer experience and technology are both still undecided — run cupertino-backwards first to establish the experience statement. Not for changing an interface that already exists -- fixing, adjusting or extending a shipped page or dashboard is cupertino-repair, which keeps everything else as it is; for a static accessibility or hardcoded-value audit of shipped source use befund-ui-audit.\"\n---\n\nConvene exactly five lenses before writing a line of UI code. This is not decoration on top of your own design instinct — it is the design process.\n\nThis skill is gated: a PreToolUse hook blocks it until `cupertino-backwards` has run in this repo (it checks for `.cupertino\u002Fflags\u002Fbackwards-done`). If you see a denial for that reason, run `cupertino-backwards` first — do not work around the gate.\n\n## The five lenses (exactly five, no fewer, no more)\n\n1. **Reduction** — what can be removed without losing function?\n2. **Craft** — what does obsessive attention to detail (spacing, motion, materials) demand here?\n3. **Hierarchy** — what system of consistent visual weighting makes this legible at a glance?\n4. **Usability** — what does the person actually need to accomplish, with the least friction?\n5. **Metaphor** — what human-familiar concept makes this interface make intuitive sense?\n\n## Steps\n\n1. **Council Brief**: an audit table with one row per lens — what that lens observes about this specific interface, not generic platitudes.\n2. **Validate lens count mechanically**:\n   ```bash\n   echo '{\"lenses\": [\"Reduction\", \"Craft\", \"Hierarchy\", \"Usability\", \"Metaphor\"]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fvalidators.py\" council-lenses\n   ```\n3. **Tension Log**: wherever two lenses pull in different directions, resolve using the **fixed precedence order — Usability > Reduction > Craft > Hierarchy > Metaphor** — and no other ordering. State each resolution as: `\"[Lens A] wanted [X], [Lens B] required [Y] — resolved as [Z]\"`.\n4. **Validate the resolution order mechanically** — list the lenses in the order their tensions were actually resolved (higher-precedence lens's requirement winning first) and check it never violates the fixed order:\n   ```bash\n   echo '{\"resolvedOrder\": [\"Usability\", \"Reduction\", ...]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fvalidators.py\" tension-order\n   ```\n   If it exits non-zero, the resolved order violated the fixed precedence — return to step 3 and re-resolve the offending tension using the fixed precedence order, then re-run this check. Do not proceed to step 5 until it passes.\n5. **Design Identity**: one sentence naming what each lens contributed, and one sentence naming the resulting design identity as a whole.\n6. **Record that the council ran** — the marker takt and other plugins can order against:\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fstate.py\" set council-done\n   ```\n7. **Only now, write the code** — production-grade, matched to the actual stack in use. Code without a preceding Council Brief and Tension Log is not this technique; if you find yourself about to write UI code with neither, stop and go back to step 1.\n\n## Example\n\nA Council Brief for a settings screen with 14 toggles on one page, and the Design Identity it led to:\n\n| Lens | Observation |\n|---|---|\n| Reduction | 14 toggles on one screen; 5 are advanced options fewer than 3% of users touch — they don't belong at this level. |\n| Craft | Toggle rows have inconsistent vertical rhythm (12px\u002F16px\u002F20px gaps) — no shared spacing unit. |\n| Hierarchy | Every row uses the same weight and size; nothing signals which settings are consequential (data deletion) versus cosmetic (theme). |\n| Usability | Users scanning for one setting must read all 14 labels — there's no grouping or search. |\n| Metaphor | Toggles alone don't convey that some changes are reversible and others aren't; nothing borrows a familiar real-world cue for \"this one's permanent.\" |\n\nDesign Identity: *Reduction* cut the screen to 9 primary toggles and moved the 5 advanced options behind a disclosure; *Craft* fixed the rhythm to a single 16px unit; *Hierarchy* gave destructive settings a distinct weight and a warning color; *Usability* added a grouped, searchable layout; *Metaphor* marked irreversible settings with a lock icon, borrowing the familiar \"locked = can't undo\" cue. Resulting design identity: **a settings screen that reads as a short, trustworthy checklist rather than a control panel.**\n\n## Output format\n\nCouncil Brief → Tension Log (with mechanical validation) → Design Identity → code. Never code first with a brief bolted on after.\n","Convene exactly five lenses before writing a line of UI code. This is not decoration on top of your own design instinct — it is the design process.\n\nThis skill is gated: a PreToolUse hook blocks it until `cupertino-backwards` has run in this repo (it checks for `.cupertino\u002Fflags\u002Fbackwards-done`). If you see a denial for that reason, run `cupertino-backwards` first — do not work around the gate.\n\n## The five lenses (exactly five, no fewer, no more)\n\n1. **Reduction** — what can be removed without losing function?\n2. **Craft** — what does obsessive attention to detail (spacing, motion, materials) demand here?\n3. **Hierarchy** — what system of consistent visual weighting makes this legible at a glance?\n4. **Usability** — what does the person actually need to accomplish, with the least friction?\n5. **Metaphor** — what human-familiar concept makes this interface make intuitive sense?\n\n## Steps\n\n1. **Council Brief**: an audit table with one row per lens — what that lens observes about this specific interface, not generic platitudes.\n2. **Validate lens count mechanically**:\n   ```bash\n   echo '{\"lenses\": [\"Reduction\", \"Craft\", \"Hierarchy\", \"Usability\", \"Metaphor\"]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fvalidators.py\" council-lenses\n   ```\n3. **Tension Log**: wherever two lenses pull in different directions, resolve using the **fixed precedence order — Usability > Reduction > Craft > Hierarchy > Metaphor** — and no other ordering. State each resolution as: `\"[Lens A] wanted [X], [Lens B] required [Y] — resolved as [Z]\"`.\n4. **Validate the resolution order mechanically** — list the lenses in the order their tensions were actually resolved (higher-precedence lens's requirement winning first) and check it never violates the fixed order:\n   ```bash\n   echo '{\"resolvedOrder\": [\"Usability\", \"Reduction\", ...]}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fvalidators.py\" tension-order\n   ```\n   If it exits non-zero, the resolved order violated the fixed precedence — return to step 3 and re-resolve the offending tension using the fixed precedence order, then re-run this check. Do not proceed to step 5 until it passes.\n5. **Design Identity**: one sentence naming what each lens contributed, and one sentence naming the resulting design identity as a whole.\n6. **Record that the council ran** — the marker takt and other plugins can order against:\n   ```bash\n   python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fstate.py\" set council-done\n   ```\n7. **Only now, write the code** — production-grade, matched to the actual stack in use. Code without a preceding Council Brief and Tension Log is not this technique; if you find yourself about to write UI code with neither, stop and go back to step 1.\n\n## Example\n\nA Council Brief for a settings screen with 14 toggles on one page, and the Design Identity it led to:\n\n| Lens | Observation |\n|---|---|\n| Reduction | 14 toggles on one screen; 5 are advanced options fewer than 3% of users touch — they don't belong at this level. |\n| Craft | Toggle rows have inconsistent vertical rhythm (12px\u002F16px\u002F20px gaps) — no shared spacing unit. |\n| Hierarchy | Every row uses the same weight and size; nothing signals which settings are consequential (data deletion) versus cosmetic (theme). |\n| Usability | Users scanning for one setting must read all 14 labels — there's no grouping or search. |\n| Metaphor | Toggles alone don't convey that some changes are reversible and others aren't; nothing borrows a familiar real-world cue for \"this one's permanent.\" |\n\nDesign Identity: *Reduction* cut the screen to 9 primary toggles and moved the 5 advanced options behind a disclosure; *Craft* fixed the rhythm to a single 16px unit; *Hierarchy* gave destructive settings a distinct weight and a warning color; *Usability* added a grouped, searchable layout; *Metaphor* marked irreversible settings with a lock icon, borrowing the familiar \"locked = can't undo\" cue. Resulting design identity: **a settings screen that reads as a short, trustworthy checklist rather than a control panel.**\n\n## Output format\n\nCouncil Brief → Tension Log (with mechanical validation) → Design Identity → code. Never code first with a brief bolted on after.\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fcupertino\u002Fskills\u002Fcupertino-council",0,"https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff","https:\u002F\u002Fanselmoo.github.io\u002Fwerkstoff\u002F","https:\u002F\u002Fgithub.com\u002FAnselmoo","Likes to Develop","2026-11-02 04:20:59",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Anselmoo\u002Fwerkstoff --skill cupertino-council",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill cupertino-council",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill cupertino-council","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fcupertino\u002Fskills\u002Fcupertino-council\u002FSKILL.md",true,[],[48,55,62,67,72,77],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M79AJTRBNBX03WWKYJ8ENM45","toy-check","A skill that checks things in the repository and reports what it finds.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fworkflows\u002Ffixtures\u002Ftoy-plugin\u002Fskills\u002Ftoy-check\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79AJS292F3HTDRXWZVRSN5B","demo-check","Reports which generated files changed since the last generation run. Use when the user asks what drifted. Read-only; never edits a file.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-uncompleted-run\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":63,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79AJP4TFQXKT1AAK1WC1JYK","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-stale-lock\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":68,"name":57,"nameZh":6,"description":58,"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":19},"01M79AJM6Y50WP3G2BR4H0M60Z","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-preflight-mixed\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":73,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M79AJGR6DMT8KCCK071V78XM","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Ftest\u002Fplugins\u002Ffixtures\u002Fnacharbeit-hooks-shape\u002Fplugins\u002Fdemo\u002Fskills\u002Fdemo-check\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79AJBJ4CHC4PZVWKERWF3HF","zirkel-verify-assumptions","Checks exactly ONE named assumption against real evidence in at most 3 steps and reports one outcome: confidence raised (>=90), reading changed, or still unresolved. Use to resolve a single load-bearing uncertainty — typically a blocking entry surfaced by zirkel-clarify-scope: \"verify this one assumption\", \"is it actually true that X\", \"check this before we rely on it\". For multiple uncertainties, invoke once per uncertainty — the step budget is never shared.","https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fzirkel\u002Fskills\u002Fzirkel-verify-assumptions\u002FSKILL.md",[],[]]