[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79A7GA5Q48S2ZCDH808T04R":3,"skill-same:01M79A7GA5Q48S2ZCDH808T04R":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},"01M79A7GA5Q48S2ZCDH808T04R","cupertino-reveal",null,"Use at ship-time, as the last automatic step for a finished feature, module, tool, or API, to deliver exactly one non-obvious, high-leverage addition in a keynote 'and one more thing' structure. Trigger on 'what's missing here', 'is there anything else this needs before shipping', or automatically as the final stage when cupertino-review runs the full pipeline. Never produces a list — exactly one suggestion, and it must be built, not pitched. Not inside a cupertino-repair run (the hook refuses it there), and never as a way to 'fix' an existing artifact: that is cupertino-repair.","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-reveal\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cupertino-reveal\ndescription: \"Use at ship-time, as the last automatic step for a finished feature, module, tool, or API, to deliver exactly one non-obvious, high-leverage addition in a keynote 'and one more thing' structure. Trigger on 'what's missing here', 'is there anything else this needs before shipping', or automatically as the final stage when cupertino-review runs the full pipeline. Never produces a list — exactly one suggestion, and it must be built, not pitched. Not inside a cupertino-repair run (the hook refuses it there), and never as a way to 'fix' an existing artifact: that is cupertino-repair.\"\n---\n\nDeliver exactly one reveal. Never a numbered list, never a set of alternatives to choose from — the discipline of \"and one more thing\" is that there is exactly one thing.\n\n## Steps\n\n1. **State plainly what the shipped artifact does** — the baseline, so the gap is legible against it.\n2. **Name the gap**: the specific capability or delight that's genuinely missing, that a user would eventually ask for or silently miss without knowing to ask.\n3. **\"And one more thing\"** — the pivot. Name the one idea.\n4. **Describe it**: what it is, concretely.\n5. **Explain why it wasn't already there** — a real reason (it required the foundation just built, it wasn't obvious until this artifact existed, it's a genuine insight rather than a known backlog item).\n6. **Implementation sketch**, then **build it** — production-grade, matched to the artifact's actual stack. Write the code directly into the shipped artifact's actual source tree (the real files that ship, not a separate write-up or scratch file); if the artifact has no editable source tree to write into, say so explicitly and name where the built code lives instead. A reveal that stays pitched as a roadmap item is not a reveal; \"real artists ship.\"\n7. **Impact sentence**: one sentence on what this actually changes for the person using the artifact.\n\n## Worked example\n\nA compact instance of the full seven-part shape (a real reveal is longer; this shows the structure, not the length):\n\n````\nBaseline: The CLI now parses a config file and runs the pipeline end to end.\nGap: Every run re-reads and re-validates the same config from disk, even\n  in a tight retry loop — nothing caches the parsed result.\nAnd one more thing: a process-lifetime config cache, invalidated on mtime change.\nDescription: Wrap the loader so a second call in the same process returns the\n  already-parsed object unless the file's mtime has moved.\nWhy it wasn't already there: this only pays off once the pipeline is called\n  repeatedly in one process, which only became possible once retry-on-failure\n  (built this session) existed.\n\n  ```python\n  _cache: dict[str, tuple[float, Config]] = {}\n\n  def load_config(path: str) -> Config:\n      mtime = os.stat(path).st_mtime\n      cached = _cache.get(path)\n      if cached and cached[0] == mtime:\n          return cached[1]\n      config = Config.parse(path)\n      _cache[path] = (mtime, config)\n      return config\n  ```\n\nImpact: retrying a failed run no longer re-parses and re-validates config on\n  every attempt — a 20-retry backoff loop does one parse instead of 20.\n````\n\n## Validate mechanically\n\nDo not eyeball the \"exactly one, and it's built\" requirements:\n\n```bash\necho '{\"text\": \"\u003Cyour full reveal writeup, including the code block>\"}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fvalidators.py\" reveal-shape\n```\n\nThis rejects the reveal if it contains a numbered or bulleted list of suggestions (more than one idea presented), or if it has no fenced code block at all (meaning nothing was actually built). If it fails, cut to one idea and build it before presenting again. If it fails validation twice in a row, stop retrying — report the blocker (what failed and why) to the user instead of attempting a third pass.\n\n## Refuse\n\n- Never suggest something already obviously on the user's mental backlog — the reveal must be genuinely surprising.\n- Never suggest something trivial (\"add type hints\", \"fix a typo\") — it must be non-trivial and high-leverage.\n- Never present it as a future consideration rather than working code.\n","Deliver exactly one reveal. Never a numbered list, never a set of alternatives to choose from — the discipline of \"and one more thing\" is that there is exactly one thing.\n\n## Steps\n\n1. **State plainly what the shipped artifact does** — the baseline, so the gap is legible against it.\n2. **Name the gap**: the specific capability or delight that's genuinely missing, that a user would eventually ask for or silently miss without knowing to ask.\n3. **\"And one more thing\"** — the pivot. Name the one idea.\n4. **Describe it**: what it is, concretely.\n5. **Explain why it wasn't already there** — a real reason (it required the foundation just built, it wasn't obvious until this artifact existed, it's a genuine insight rather than a known backlog item).\n6. **Implementation sketch**, then **build it** — production-grade, matched to the artifact's actual stack. Write the code directly into the shipped artifact's actual source tree (the real files that ship, not a separate write-up or scratch file); if the artifact has no editable source tree to write into, say so explicitly and name where the built code lives instead. A reveal that stays pitched as a roadmap item is not a reveal; \"real artists ship.\"\n7. **Impact sentence**: one sentence on what this actually changes for the person using the artifact.\n\n## Worked example\n\nA compact instance of the full seven-part shape (a real reveal is longer; this shows the structure, not the length):\n\n````\nBaseline: The CLI now parses a config file and runs the pipeline end to end.\nGap: Every run re-reads and re-validates the same config from disk, even\n  in a tight retry loop — nothing caches the parsed result.\nAnd one more thing: a process-lifetime config cache, invalidated on mtime change.\nDescription: Wrap the loader so a second call in the same process returns the\n  already-parsed object unless the file's mtime has moved.\nWhy it wasn't already there: this only pays off once the pipeline is called\n  repeatedly in one process, which only became possible once retry-on-failure\n  (built this session) existed.\n\n  ```python\n  _cache: dict[str, tuple[float, Config]] = {}\n\n  def load_config(path: str) -> Config:\n      mtime = os.stat(path).st_mtime\n      cached = _cache.get(path)\n      if cached and cached[0] == mtime:\n          return cached[1]\n      config = Config.parse(path)\n      _cache[path] = (mtime, config)\n      return config\n  ```\n\nImpact: retrying a failed run no longer re-parses and re-validates config on\n  every attempt — a 20-retry backoff loop does one parse instead of 20.\n````\n\n## Validate mechanically\n\nDo not eyeball the \"exactly one, and it's built\" requirements:\n\n```bash\necho '{\"text\": \"\u003Cyour full reveal writeup, including the code block>\"}' | python3 -B \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fvalidators.py\" reveal-shape\n```\n\nThis rejects the reveal if it contains a numbered or bulleted list of suggestions (more than one idea presented), or if it has no fenced code block at all (meaning nothing was actually built). If it fails, cut to one idea and build it before presenting again. If it fails validation twice in a row, stop retrying — report the blocker (what failed and why) to the user instead of attempting a third pass.\n\n## Refuse\n\n- Never suggest something already obviously on the user's mental backlog — the reveal must be genuinely surprising.\n- Never suggest something trivial (\"add type hints\", \"fix a typo\") — it must be non-trivial and high-leverage.\n- Never present it as a future consideration rather than working code.\n",{"name":5,"description":7},"main","6158c1e4e112c06af2c7ac01b13b2ed7214c0fcf","plugins\u002Fcupertino\u002Fskills\u002Fcupertino-reveal",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-reveal",{"tool":39,"command":40},"bunx","bunx skills add Anselmoo\u002Fwerkstoff --skill cupertino-reveal",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Anselmoo\u002Fwerkstoff --skill cupertino-reveal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAnselmoo\u002Fwerkstoff\u002Fblob\u002Fmain\u002Fplugins\u002Fcupertino\u002Fskills\u002Fcupertino-reveal\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",[],[]]