[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADYZAT4BPTCS2Z7GV3QHKW":3,"skill-same:01M6ADYZAT4BPTCS2Z7GV3QHKW":146},{"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":31,"publishedAt":61,"linkOnly":62,"markdownContent":63,"markdownBody":64,"frontMatter":65,"refName":70,"commitSha":71,"skillDirectory":72,"forksCount":73,"repositoryHtmlUrl":74,"repositoryHomepageUrl":75,"ownerHtmlUrl":76,"ownerBlogUrl":77,"ownerDescription":78,"updatedAt":79,"install":80,"resources":93},"01M6ADYZAT4BPTCS2Z7GV3QHKW","poka-yoke",null,"Mistake-proof code so misuse cannot be expressed, rather than warning against it. Use when designing an interface, schema, or state machine and the user wants it hard to get wrong (\"make invalid states unrepresentable\", \"so callers cannot screw it up\", \"type-safe API\", \"pit of success\"); when auditing existing code for footguns (\"what could bite us here\", \"what is easy to misuse\", \"poka-yoke this repo\", \"review this diff for ways to get it wrong\"); or when a bug has recurred and the fix must close the class rather than the case (\"make sure this never happens again\", \"this is the third time\"). Especially for money, auth, permissions, deletion, migrations, and pipelines where failure is silent. Classifies every finding by what happens when the mistake occurs and how the device notices, which is what keeps it from collapsing into generic code review.","github\u002Fawesome-copilot","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3PBDYPK7NVFJNJ66Y8RS",41133,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fpoka-yoke\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,9,56,57,58,59,60],"poka yoke","examples","when","which","sure","interface","states","invalid","get","time","scanner","up","never","fix","api","code review","https","state","permissions","code","packages","sql","auth","rust","python","go","typescript","safe","review","2026-11-10 10:12:30",false,"---\nname: poka-yoke\ndescription: 'Mistake-proof code so misuse cannot be expressed, rather than warning against it. Use when designing an interface, schema, or state machine and the user wants it hard to get wrong (\"make invalid states unrepresentable\", \"so callers cannot screw it up\", \"type-safe API\", \"pit of success\"); when auditing existing code for footguns (\"what could bite us here\", \"what is easy to misuse\", \"poka-yoke this repo\", \"review this diff for ways to get it wrong\"); or when a bug has recurred and the fix must close the class rather than the case (\"make sure this never happens again\", \"this is the third time\"). Especially for money, auth, permissions, deletion, migrations, and pipelines where failure is silent. Classifies every finding by what happens when the mistake occurs and how the device notices, which is what keeps it from collapsing into generic code review.'\nlicense: MIT\ncompatibility: 'Cross-platform. The bundled scanner needs Python 3.9+ and no third-party packages. Everything else is language-agnostic guidance; worked examples are TypeScript, Python, Go, Rust and SQL.'\nmetadata:\n  version: '1.0'\n  source: https:\u002F\u002Fgithub.com\u002Frainmanjam\u002Fpoka-yoke\n---\n\n# Poka-Yoke: Make the Mistake Unsayable\n\n**People will always make mistakes. That is not the problem worth solving. The problem is\nletting a mistake become a defect.**\n\nShigeo Shingo, a Japanese industrial engineer, worked this out on a switch assembly line in\n1961. Workers kept forgetting a spring. The fix was not a reminder: the job was split so the\nworker first laid both springs in a dish, then fitted them from the dish. A spring left over\nwas the error announcing itself, before the unit could move on.\n\nThe dish is a device. \"Please remember the spring\" is not.\n\n## The line that does most of the work\n\n> A comment, a docstring, a wiki page, a review checklist, or a line in an instructions file\n> saying \"don't do X\" is **not** a poka-yoke. It is training, and training degrades. A device\n> does not. If your fix relies on someone remembering something, keep going.\n\nThis applies to your own instructions too. A rule written into a config file competes for\nattention with every other rule there and loses a little more as the file grows. A check that\nfails the build does not.\n\n## What this changes about the output\n\nGiven a design, models will readily list what to fix. They rarely state what the fix makes\n*impossible*, and that is the difference between advice you agree with and a constraint you\ncan rely on. That habit is most of what this skill is for.\n\nThe other half is refusing to accept a non-device as a fix. \"Add validation\", \"be careful with\nthis function\", \"document the invariant\" are all rung zero. Each has a real device behind it,\nand naming that device is the work.\n\n## Axis 1: what happens when the mistake occurs\n\nRank every finding on this ladder, and say which rung the current code sits on and which rung\nyour fix reaches.\n\n| Rung | Name | Meaning |\n|---|---|---|\n| 1 | **Control** | The wrong action cannot be performed. Type error, database constraint, missing permission. |\n| 2 | **Warning** | It is possible, but announces itself as it happens. A linter, a runtime assertion, a confirmation you cannot skip. |\n| 3 | **Detection** | It happens, and you find out afterwards. Tests, logging, monitoring, code review. |\n| 0 | **rung zero** | Telling people to be careful. Docs, comments, \"please remember to\". |\n\nDetection is not failure; sometimes it is all that is available. But a plan that stops at\nDetection should say so, rather than presenting it as prevention.\n\n## Axis 2: how the device notices\n\nShingo's three inspection lenses. They are a checklist for *finding* hazards, not decoration:\n\n- **Contact** — can the wrong thing physically fit? Two adjacent parameters of the same type can be swapped silently. A `string` that should be one of four values. Money as a float.\n- **Fixed-value** — is the set complete? A switch with no exhaustiveness check. A config where a missing key silently means \"off\". An enum handled in three of five places.\n- **Motion-step** — is the order right, and did every step happen? A two-phase write with no transaction. A retry with no idempotency key. A resource acquired on one path and released on another.\n\n## Inspect at the source\n\nThe cheapest place to catch a mistake is where it is made, not where it surfaces. A validation\nthat runs three layers below the input has already let the bad value travel, and the stack\ntrace will point at the wrong module. Push the check to the boundary the value crosses.\n\n## Designing something new\n\nMistake-proofing is cheapest before the code has callers. Once it has them, every device is a\nmigration; before it has them, a device is free.\n\nWork from the call site. A signature that reads fine in isolation often reads terribly where\nit is used:\n\n```python\n# the mistake is expressible: nothing stops refunding an order that was never paid\ndef refund(order: dict) -> Refund:\n    return payments.refund(order[\"payment_id\"])\n\n# the mistake is no longer expressible\ndef refund(order: PaidOrder) -> Refund: ...\n```\n\nThe moves, roughly in order of how often they apply:\n\n**Make invalid states unrepresentable.** A bag of optional fields where only certain\ncombinations are legal becomes a discriminated union where the illegal ones cannot be\nconstructed.\n\n**Parse, don't validate.** Convert unstructured input into a type that carries proof at the\nboundary, once, rather than re-checking the same string in nine places.\n\n**Distinguish concepts that share a primitive.** `transfer(from: str, to: str)` accepts its\narguments transposed. Distinct types for the two concepts, or keyword-only parameters, make the\ntransposition a compile error.\n\n**Encode the order.** When calls must happen in sequence, let each step return the type the\nnext step requires, so the wrong order does not typecheck.\n\n**Make the destructive path narrower than the safe one.** A required, non-defaulting argument\nfor the scope of a delete. A default that means \"nothing\" rather than \"everything\".\n\nClose by naming what the design now makes impossible, and, just as importantly, **what you\ndeliberately left possible and why**. A design whose limits are unstated will be trusted past\nthem.\n\n## Auditing code that already exists\n\nYou are not looking for bugs. A bug is a mistake that already happened. You are looking for\n**mistakes that are available**: places where doing the wrong thing is easy, silent, and looks\ncorrect.\n\nRun the bundled scanner first for the textually detectable shapes, then read for the ones no\nscanner can see:\n\n```bash\npython3 scripts\u002Fdetect_hazards.py --paths .          # whole tree\npython3 scripts\u002Fdetect_hazards.py --staged           # pre-commit\npython3 scripts\u002Fdetect_hazards.py --diff --json      # CI, exits non-zero on findings\npython3 scripts\u002Fdetect_hazards.py --severity high\n```\n\nNo dependencies, so it runs in CI and in a pre-commit hook without an install step. It reports\nwhat it scanned: a scan of zero files exits non-zero rather than reporting a clean bill of\nhealth, because an all-clear you got by typo is worse than no check.\n\nRank findings by **blast radius times ease of the mistake**. An unchecked value reaching a\nwrite, a delete, a payment or an auth decision outranks one that can only produce a clean\ncrash. For each finding, state: where it is, what the mistake is, what the consequence is, what\ndevice exists today, what device would close it, and which rung that reaches.\n\n`references\u002Fhazard-catalog.md` is the taxonomy of shapes with their IDs and devices.\nLanguage-specific patterns are in `references\u002Flang-python.md`, `references\u002Flang-typescript.md`\nand `references\u002Flang-rust-go.md`.\n\n## After an incident\n\nSeparate three things that get conflated, because the fix belongs to the third:\n\n- **Defect** — what the user experienced.\n- **Mistake** — the specific wrong action someone took.\n- **Hazard** — the property of the system that made that mistake available.\n\nFixing the mistake fixes one case. Fixing the hazard fixes the class. Then **sweep**: the same\nshape almost certainly exists elsewhere, and finding the second and third instance is the\ndifference between a patch and a lesson.\n\nAttribute cause to the system rather than to a person. Not primarily for kindness: \"they made a\nmistake\" is a complete-sounding explanation that predicts nothing and prevents nothing, and it\nends the investigation early.\n\n## What good output looks like\n\n- **Anchored to lines.** `orders.py:142, apply_discount` is reviewable; \"the discount logic\" is not.\n- **Ranked, with the ranking visible**, so a reader who stops halfway has still covered the ones that matter.\n- **A named device per finding**, not \"add validation\".\n- **The rung stated**, before and after.\n- **The limits stated.** What the fix does not cover is the part readers most need and most often do not get.\n- **Sized honestly.** Three findings that matter beat eleven padded to a round number.\n\n## What to avoid\n\n**Accepting rung zero as a fix.** If the proposal is a comment, a doc, or a convention, the\nwork is not finished.\n\n**Devices nobody can bypass being confused with devices nobody does bypass.** A pre-commit hook\nis skippable with `--no-verify`; it needs CI behind it to be a real gate. Say which one you are\nproposing.\n\n**Over-fitting to one incident.** Machinery that prevents one specific failure must itself be\nunderstood and maintained. Ask whether the shape is common enough to justify it.\n\n**Treating monitoring as prevention.** Detection lowers the cost of a failure; it does not lower\nthe likelihood. Both are worth having, and conflating them means the likelihood never gets\naddressed.\n\n## Evidence, and its limits\n\nThis method was benchmarked at 591 blind-graded runs across six model families, scored against\nassertions written before the runs by a grader that never saw which configuration produced a\nresponse. The behaviour it most reliably changes is stating what a design forecloses: **45% of\nresponses did that unprompted, 80% with the method applied**, across 132 graded verdicts.\n\nThat average conceals where the effect lives. Asked squarely to design an interface, models\nalready do it 77% of the time; the skills add eleven points. The large gains are in tasks\nwhere nobody asked for a design review — writing an endpoint goes 14% to 79%, shipping an\nagent feature 33% to 83%, building a form 29% to 64%.\n\nStated honestly, because the limits matter: every run was the first turn of a fresh session, so\nthis measures the ceiling rather than what survives a long working session. The comparison was\nagainst no methodology at all, not against a different one, so it does not establish that\n*this* method is what produced the gain. And the method costs something measurable: responses\nbecame somewhat worse at spotting the specific defect already on the page while becoming better\nat changing the shape that allowed it. If you want the bug in front of you found, use a\nreviewer. If you want that class of bug to stop being expressible, use this.\n\nRaw runs, the harness and the assertion checklists are at\n\u003Chttps:\u002F\u002Fgithub.com\u002Frainmanjam\u002Fpoka-yoke>.\n","# Poka-Yoke: Make the Mistake Unsayable\n\n**People will always make mistakes. That is not the problem worth solving. The problem is\nletting a mistake become a defect.**\n\nShigeo Shingo, a Japanese industrial engineer, worked this out on a switch assembly line in\n1961. Workers kept forgetting a spring. The fix was not a reminder: the job was split so the\nworker first laid both springs in a dish, then fitted them from the dish. A spring left over\nwas the error announcing itself, before the unit could move on.\n\nThe dish is a device. \"Please remember the spring\" is not.\n\n## The line that does most of the work\n\n> A comment, a docstring, a wiki page, a review checklist, or a line in an instructions file\n> saying \"don't do X\" is **not** a poka-yoke. It is training, and training degrades. A device\n> does not. If your fix relies on someone remembering something, keep going.\n\nThis applies to your own instructions too. A rule written into a config file competes for\nattention with every other rule there and loses a little more as the file grows. A check that\nfails the build does not.\n\n## What this changes about the output\n\nGiven a design, models will readily list what to fix. They rarely state what the fix makes\n*impossible*, and that is the difference between advice you agree with and a constraint you\ncan rely on. That habit is most of what this skill is for.\n\nThe other half is refusing to accept a non-device as a fix. \"Add validation\", \"be careful with\nthis function\", \"document the invariant\" are all rung zero. Each has a real device behind it,\nand naming that device is the work.\n\n## Axis 1: what happens when the mistake occurs\n\nRank every finding on this ladder, and say which rung the current code sits on and which rung\nyour fix reaches.\n\n| Rung | Name | Meaning |\n|---|---|---|\n| 1 | **Control** | The wrong action cannot be performed. Type error, database constraint, missing permission. |\n| 2 | **Warning** | It is possible, but announces itself as it happens. A linter, a runtime assertion, a confirmation you cannot skip. |\n| 3 | **Detection** | It happens, and you find out afterwards. Tests, logging, monitoring, code review. |\n| 0 | **rung zero** | Telling people to be careful. Docs, comments, \"please remember to\". |\n\nDetection is not failure; sometimes it is all that is available. But a plan that stops at\nDetection should say so, rather than presenting it as prevention.\n\n## Axis 2: how the device notices\n\nShingo's three inspection lenses. They are a checklist for *finding* hazards, not decoration:\n\n- **Contact** — can the wrong thing physically fit? Two adjacent parameters of the same type can be swapped silently. A `string` that should be one of four values. Money as a float.\n- **Fixed-value** — is the set complete? A switch with no exhaustiveness check. A config where a missing key silently means \"off\". An enum handled in three of five places.\n- **Motion-step** — is the order right, and did every step happen? A two-phase write with no transaction. A retry with no idempotency key. A resource acquired on one path and released on another.\n\n## Inspect at the source\n\nThe cheapest place to catch a mistake is where it is made, not where it surfaces. A validation\nthat runs three layers below the input has already let the bad value travel, and the stack\ntrace will point at the wrong module. Push the check to the boundary the value crosses.\n\n## Designing something new\n\nMistake-proofing is cheapest before the code has callers. Once it has them, every device is a\nmigration; before it has them, a device is free.\n\nWork from the call site. A signature that reads fine in isolation often reads terribly where\nit is used:\n\n```python\n# the mistake is expressible: nothing stops refunding an order that was never paid\ndef refund(order: dict) -> Refund:\n    return payments.refund(order[\"payment_id\"])\n\n# the mistake is no longer expressible\ndef refund(order: PaidOrder) -> Refund: ...\n```\n\nThe moves, roughly in order of how often they apply:\n\n**Make invalid states unrepresentable.** A bag of optional fields where only certain\ncombinations are legal becomes a discriminated union where the illegal ones cannot be\nconstructed.\n\n**Parse, don't validate.** Convert unstructured input into a type that carries proof at the\nboundary, once, rather than re-checking the same string in nine places.\n\n**Distinguish concepts that share a primitive.** `transfer(from: str, to: str)` accepts its\narguments transposed. Distinct types for the two concepts, or keyword-only parameters, make the\ntransposition a compile error.\n\n**Encode the order.** When calls must happen in sequence, let each step return the type the\nnext step requires, so the wrong order does not typecheck.\n\n**Make the destructive path narrower than the safe one.** A required, non-defaulting argument\nfor the scope of a delete. A default that means \"nothing\" rather than \"everything\".\n\nClose by naming what the design now makes impossible, and, just as importantly, **what you\ndeliberately left possible and why**. A design whose limits are unstated will be trusted past\nthem.\n\n## Auditing code that already exists\n\nYou are not looking for bugs. A bug is a mistake that already happened. You are looking for\n**mistakes that are available**: places where doing the wrong thing is easy, silent, and looks\ncorrect.\n\nRun the bundled scanner first for the textually detectable shapes, then read for the ones no\nscanner can see:\n\n```bash\npython3 scripts\u002Fdetect_hazards.py --paths .          # whole tree\npython3 scripts\u002Fdetect_hazards.py --staged           # pre-commit\npython3 scripts\u002Fdetect_hazards.py --diff --json      # CI, exits non-zero on findings\npython3 scripts\u002Fdetect_hazards.py --severity high\n```\n\nNo dependencies, so it runs in CI and in a pre-commit hook without an install step. It reports\nwhat it scanned: a scan of zero files exits non-zero rather than reporting a clean bill of\nhealth, because an all-clear you got by typo is worse than no check.\n\nRank findings by **blast radius times ease of the mistake**. An unchecked value reaching a\nwrite, a delete, a payment or an auth decision outranks one that can only produce a clean\ncrash. For each finding, state: where it is, what the mistake is, what the consequence is, what\ndevice exists today, what device would close it, and which rung that reaches.\n\n`references\u002Fhazard-catalog.md` is the taxonomy of shapes with their IDs and devices.\nLanguage-specific patterns are in `references\u002Flang-python.md`, `references\u002Flang-typescript.md`\nand `references\u002Flang-rust-go.md`.\n\n## After an incident\n\nSeparate three things that get conflated, because the fix belongs to the third:\n\n- **Defect** — what the user experienced.\n- **Mistake** — the specific wrong action someone took.\n- **Hazard** — the property of the system that made that mistake available.\n\nFixing the mistake fixes one case. Fixing the hazard fixes the class. Then **sweep**: the same\nshape almost certainly exists elsewhere, and finding the second and third instance is the\ndifference between a patch and a lesson.\n\nAttribute cause to the system rather than to a person. Not primarily for kindness: \"they made a\nmistake\" is a complete-sounding explanation that predicts nothing and prevents nothing, and it\nends the investigation early.\n\n## What good output looks like\n\n- **Anchored to lines.** `orders.py:142, apply_discount` is reviewable; \"the discount logic\" is not.\n- **Ranked, with the ranking visible**, so a reader who stops halfway has still covered the ones that matter.\n- **A named device per finding**, not \"add validation\".\n- **The rung stated**, before and after.\n- **The limits stated.** What the fix does not cover is the part readers most need and most often do not get.\n- **Sized honestly.** Three findings that matter beat eleven padded to a round number.\n\n## What to avoid\n\n**Accepting rung zero as a fix.** If the proposal is a comment, a doc, or a convention, the\nwork is not finished.\n\n**Devices nobody can bypass being confused with devices nobody does bypass.** A pre-commit hook\nis skippable with `--no-verify`; it needs CI behind it to be a real gate. Say which one you are\nproposing.\n\n**Over-fitting to one incident.** Machinery that prevents one specific failure must itself be\nunderstood and maintained. Ask whether the shape is common enough to justify it.\n\n**Treating monitoring as prevention.** Detection lowers the cost of a failure; it does not lower\nthe likelihood. Both are worth having, and conflating them means the likelihood never gets\naddressed.\n\n## Evidence, and its limits\n\nThis method was benchmarked at 591 blind-graded runs across six model families, scored against\nassertions written before the runs by a grader that never saw which configuration produced a\nresponse. The behaviour it most reliably changes is stating what a design forecloses: **45% of\nresponses did that unprompted, 80% with the method applied**, across 132 graded verdicts.\n\nThat average conceals where the effect lives. Asked squarely to design an interface, models\nalready do it 77% of the time; the skills add eleven points. The large gains are in tasks\nwhere nobody asked for a design review — writing an endpoint goes 14% to 79%, shipping an\nagent feature 33% to 83%, building a form 29% to 64%.\n\nStated honestly, because the limits matter: every run was the first turn of a fresh session, so\nthis measures the ceiling rather than what survives a long working session. The comparison was\nagainst no methodology at all, not against a different one, so it does not establish that\n*this* method is what produced the gain. And the method costs something measurable: responses\nbecame somewhat worse at spotting the specific defect already on the page while becoming better\nat changing the shape that allowed it. If you want the bug in front of you found, use a\nreviewer. If you want that class of bug to stop being expressible, use this.\n\nRaw runs, the harness and the assertion checklists are at\n\u003Chttps:\u002F\u002Fgithub.com\u002Frainmanjam\u002Fpoka-yoke>.\n",{"name":5,"license":15,"metadata":66,"description":7,"compatibility":69},{"source":67,"version":68},"https:\u002F\u002Fgithub.com\u002Frainmanjam\u002Fpoka-yoke","1.0","Cross-platform. The bundled scanner needs Python 3.9+ and no third-party packages. Everything else is language-agnostic guidance; worked examples are TypeScript, Python, Go, Rust and SQL.","main","5269f7ea2d6c3a9bfda5ed878b6726cf509121fd","skills\u002Fpoka-yoke",5354,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","https:\u002F\u002Fawesome-copilot.github.com\u002F","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-14 05:37:52",{"source":8,"skillName":5,"commands":81,"prompt":91,"zipAvailable":92},[82,85,88],{"tool":83,"command":84},"npx","npx skills add github\u002Fawesome-copilot --skill poka-yoke",{"tool":86,"command":87},"bunx","bunx skills add github\u002Fawesome-copilot --skill poka-yoke",{"tool":89,"command":90},"pnpm","pnpm dlx skills add github\u002Fawesome-copilot --skill poka-yoke","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fpoka-yoke\u002FSKILL.md",true,[94,100,104,108,112,116,120,124,128,132,136,140],{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"examples\u002Fadd-block.md","REFERENCE","参考文档",1232,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fhyperframes-hyperframes-registry\u002Fexamples\u002Fadd-block.md",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"examples\u002Fadd-component.md",1473,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fhyperframes-hyperframes-registry\u002Fexamples\u002Fadd-component.md",{"path":105,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fdemo-html-pattern.md",1884,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fhyperframes-hyperframes-registry\u002Freferences\u002Fdemo-html-pattern.md",{"path":109,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fdiscovery.md",2704,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fhyperframes-hyperframes-registry\u002Freferences\u002Fdiscovery.md",{"path":113,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fhazard-catalog.md",20837,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fpoka-yoke\u002Freferences\u002Fhazard-catalog.md",{"path":117,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Finstall-locations.md",1519,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fhyperframes-hyperframes-registry\u002Freferences\u002Finstall-locations.md",{"path":121,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Flang-python.md",6872,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fpoka-yoke\u002Freferences\u002Flang-python.md",{"path":125,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Flang-rust-go.md",7773,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fpoka-yoke\u002Freferences\u002Flang-rust-go.md",{"path":129,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Flang-typescript.md",6045,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fpoka-yoke\u002Freferences\u002Flang-typescript.md",{"path":133,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fwiring-blocks.md",3127,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fhyperframes-hyperframes-registry\u002Freferences\u002Fwiring-blocks.md",{"path":137,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Fwiring-components.md",2402,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fhyperframes-hyperframes-registry\u002Freferences\u002Fwiring-components.md",{"path":141,"resourceType":142,"resourceTypeDesc":143,"sizeBytes":144,"sourceHtmlUrl":145},"scripts\u002Fdetect_hazards.py","SCRIPT","脚本",26794,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fpoka-yoke\u002Fscripts\u002Fdetect_hazards.py",[147,178,206,231,262,278],{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":159,"publishedAt":61},"01M70KXZNX9ES38N2A8M58ZZMZ","supabase-rls-policies","Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsupabase-rls-policies\u002FSKILL.md",[153,156],{"categoryNo":154,"categoryName":155,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[160,161,162,163,164,34,60,165,166,167,168,169,170,171,172,173,174,175,176,177],"supabase","rls","supabase rls","supabase rls policies","project","change","read","write","security","isolation","tables","as","tests","prove","use","users","functions","with",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":185,"publishedAt":61},"01M70KWA5YWXDV6V8DZ19E3T2Y","skill-distribution-audit","Audit a skill collection before release or investigate installer omissions, archived\u002Ftemplate leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fskill-distribution-audit\u002FSKILL.md",[184],{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},[186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205],"distribution","skill distribution audit","audit","SET","deterministic","installer","for","discovery","comparison","helper","manifest","version","collection","drift","output","investigate","duplicate","template","release","reconcile",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":210,"sourceHtmlUrl":211,"categories":212,"keywords":214,"publishedAt":61},"01M70KCJPFVW7PPQ49CC5R8JGK","logicapps-custom-code-net10-migration","Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project\u002Fpackage configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FSKILL.md",[213],{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[215,51,216,217,218,219,192,164,220,221,222,223,224,225,226,174,227,228,229,230],"custom","logicapps custom code net10 migration","migration","projects","standalone","deployment","applications","local","azure","worker","upgrades","package","apps","Legacy","debugging","workflows",{"skillNo":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":235,"sourceHtmlUrl":236,"categories":237,"keywords":240,"publishedAt":61},"01M6AEBN37RQMXJ3298PEY7PG1","winmd-api-search","Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI\u002FML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FSKILL.md",[238,239],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},[241,242,46,243,244,245,246,247,248,249,250,251,252,253,254,34,255,256,257,258,259,192,260,261],"winmd api search","search","windows","desktop","file access","enumeration","ui","ml","file","networking","capabilities","notifications","explore","access","features","full","camera","events","platform","methods","controls",{"skillNo":263,"name":264,"nameZh":6,"description":265,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":266,"licenseFileUrl":267,"sourceHtmlUrl":268,"categories":269,"keywords":275,"publishedAt":61},"01M6AE571R3SC1ZGE202B3NB5S","resemble-detect","Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FSKILL.md",[270,271,274],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":272,"categoryName":273,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},[276,189,249,48,277],"resemble detect","identity",{"skillNo":279,"name":280,"nameZh":6,"description":281,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":266,"licenseFileUrl":282,"sourceHtmlUrl":283,"categories":284,"keywords":287,"publishedAt":61},"01M6AE30BSK2HCY4TQQ22Z8JRD","quality-playbook","Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FSKILL.md",[285,286],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":157,"categoryName":158,"taxonomyType":21,"taxonomyTypeDesc":22},[288,289,290,47,51,60,9,188,291,292,48,293,294,295,296,297,298,299,300,301,302,303,172,304,305,306,307],"playbook","quality playbook","quality","tdd","run","report","spec","bug report","council","engineering","functional","spec audit","bug","verified","multi-model","three","coverage","model","regression","structural"]