[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BV8JY5JRF8DKP3WJXREKFX":3,"skill-same:01M6BV8JY5JRF8DKP3WJXREKFX":58},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":14,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6BV8JY5JRF8DKP3WJXREKFX","verify-this",null,"Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.","bnferguson\u002Fdotfiles","bnferguson","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47749?v=4","01M6BV4H2TJKK8P14W86V1ZCPP","Brandon Ferguson","01M6BV4H7GJWTZJ1BVHQ1TX11Y",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-this\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"verify","verify this","artifacts","baseline","capture","evidence","claim","local","fresh","compare","it","restate","with","verified","2026-11-10 10:12:30",false,"---\nname: verify-this\ndescription: \"Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.\"\n---\n\n# Verify This\n\nVerification is not a recap. It proves or disproves a specific claim with repeatable evidence.\n\n## When To Use\n\n- The user asks \"verify this\", \"prove it works\", \"did this fix it\", or \"show me the evidence\".\n- A bug fix needs a before\u002Fafter repro.\n- A UI, CLI, API, performance, or memory claim needs measurement.\n- A test passes but the user-visible behavior still needs confirmation.\n\nDo not use this for vague claims like \"the code is cleaner\". Ask for a measurable claim first.\n\n## Workflow\n\n1. Restate the claim in falsifiable form: condition, metric, and threshold.\n2. Pick the smallest local surface that can disprove it.\n3. Capture a baseline from the old state: merge base, parent commit, failing branch, or current broken repro.\n4. Capture treatment from the changed state with the same command, data, warmup, and environment.\n5. Compare raw artifacts: numbers, screenshots, terminal transcripts, HTTP responses, profiles, heap snapshots, or test output.\n6. Return exactly one verdict: `VERIFIED`, `NOT VERIFIED`, or `INCONCLUSIVE`.\n\n## Local Surfaces\n\n- Code behavior: focused unit\u002Fintegration tests or a minimal repro script.\n- CLI\u002FTUI behavior: `control-cli`, terminal transcript, or demo recording.\n- UI behavior: `control-ui`, screenshots, accessibility snapshots, or browser traces.\n- API behavior: local HTTP\u002FRPC request and response diff.\n- Performance: same-machine baseline\u002Ftreatment timings or CPU profiles.\n- Memory: heap snapshots before and after the suspected operation.\n\n## Artifact Layout\n\nWhen safe to write artifacts:\n\n```text\n\u002Ftmp\u002Fverify-this\u002F\u003Cclaim-slug>\u002F\n├── claim.md\n├── timeline.md\n├── baseline\u002F\n├── treatment\u002F\n├── diff\u002F\n└── verdict.md\n```\n\nIf artifacts may contain sensitive code, prompts, screenshots, HTTP bodies, or heap data, keep only the minimal inline evidence unless the user agrees to disk storage.\n\n## Verdict Rules\n\n- `VERIFIED`: baseline and treatment differ in the predicted direction, by the claimed threshold, with no obvious confound.\n- `NOT VERIFIED`: the behavior is unchanged, moves the wrong way, or misses the threshold.\n- `INCONCLUSIVE`: no valid baseline, noisy signal, failed measurement, or an environment difference invalidates the comparison.\n\n## Output\n\nUse this shape:\n\n```text\nVERIFIED | NOT VERIFIED | INCONCLUSIVE\nClaim: \u003Cfalsifiable claim>\n\nEvidence:\n\u003Cmetric\u002Fartifact>: baseline=\u003C...>, treatment=\u003C...>, delta=\u003C...>, threshold=\u003C...>\n\nReasoning:\n\u003Cone tight paragraph naming the evidence and any confounds>\n```\n\nDo not soften a negative result. A clear `NOT VERIFIED` is useful.\n","# Verify This\n\nVerification is not a recap. It proves or disproves a specific claim with repeatable evidence.\n\n## When To Use\n\n- The user asks \"verify this\", \"prove it works\", \"did this fix it\", or \"show me the evidence\".\n- A bug fix needs a before\u002Fafter repro.\n- A UI, CLI, API, performance, or memory claim needs measurement.\n- A test passes but the user-visible behavior still needs confirmation.\n\nDo not use this for vague claims like \"the code is cleaner\". Ask for a measurable claim first.\n\n## Workflow\n\n1. Restate the claim in falsifiable form: condition, metric, and threshold.\n2. Pick the smallest local surface that can disprove it.\n3. Capture a baseline from the old state: merge base, parent commit, failing branch, or current broken repro.\n4. Capture treatment from the changed state with the same command, data, warmup, and environment.\n5. Compare raw artifacts: numbers, screenshots, terminal transcripts, HTTP responses, profiles, heap snapshots, or test output.\n6. Return exactly one verdict: `VERIFIED`, `NOT VERIFIED`, or `INCONCLUSIVE`.\n\n## Local Surfaces\n\n- Code behavior: focused unit\u002Fintegration tests or a minimal repro script.\n- CLI\u002FTUI behavior: `control-cli`, terminal transcript, or demo recording.\n- UI behavior: `control-ui`, screenshots, accessibility snapshots, or browser traces.\n- API behavior: local HTTP\u002FRPC request and response diff.\n- Performance: same-machine baseline\u002Ftreatment timings or CPU profiles.\n- Memory: heap snapshots before and after the suspected operation.\n\n## Artifact Layout\n\nWhen safe to write artifacts:\n\n```text\n\u002Ftmp\u002Fverify-this\u002F\u003Cclaim-slug>\u002F\n├── claim.md\n├── timeline.md\n├── baseline\u002F\n├── treatment\u002F\n├── diff\u002F\n└── verdict.md\n```\n\nIf artifacts may contain sensitive code, prompts, screenshots, HTTP bodies, or heap data, keep only the minimal inline evidence unless the user agrees to disk storage.\n\n## Verdict Rules\n\n- `VERIFIED`: baseline and treatment differ in the predicted direction, by the claimed threshold, with no obvious confound.\n- `NOT VERIFIED`: the behavior is unchanged, moves the wrong way, or misses the threshold.\n- `INCONCLUSIVE`: no valid baseline, noisy signal, failed measurement, or an environment difference invalidates the comparison.\n\n## Output\n\nUse this shape:\n\n```text\nVERIFIED | NOT VERIFIED | INCONCLUSIVE\nClaim: \u003Cfalsifiable claim>\n\nEvidence:\n\u003Cmetric\u002Fartifact>: baseline=\u003C...>, treatment=\u003C...>, delta=\u003C...>, threshold=\u003C...>\n\nReasoning:\n\u003Cone tight paragraph naming the evidence and any confounds>\n```\n\nDo not soften a negative result. A clear `NOT VERIFIED` is useful.\n",{"name":5,"description":7},"main","e63965e4644984470d4cc8b3014a8b001f0c2666",".agents\u002Fskills\u002Fverify-this","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles","https:\u002F\u002Fgithub.com\u002Fbnferguson","2026-11-11 03:04:59",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add bnferguson\u002Fdotfiles --skill verify-this",{"tool":50,"command":51},"bunx","bunx skills add bnferguson\u002Fdotfiles --skill verify-this",{"tool":53,"command":54},"pnpm","pnpm dlx skills add bnferguson\u002Fdotfiles --skill verify-this","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-this\u002FSKILL.md",true,[],[59,91,108,138,147,160],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":72,"publishedAt":33},"01M6BVA3RS3M016FANZ6792F9H","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude\u002Fconfig\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002Fclaude\u002Fconfig\u002Fskills\u002Fskill-creator\u002FSKILL.md",[67],{"categoryNo":68,"categoryName":69,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[73,74,75,76,77,78,79,80,81,82,83,84,85,86,31,87,88,89,90],"creator","skill creator","specialized","workflows","create","update","capabilities","knowledge","tool","integrations","guide","new skill","existing skill","users","for","Existing","when","new",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":105,"publishedAt":33},"01M6BV94WN2RPYM8N6PN8TBNT8","writing-shape","Writing, exploit: shape raw material into an article, paragraph by paragraph.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-shape\u002FSKILL.md",[97,100],{"categoryNo":98,"categoryName":99,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[106,107],"writing shape","writing",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":121,"publishedAt":33},"01M6BV8QDFJ6PXBVK5NFBZT5M7","webapp-testing","Test local web applications using Playwright. Use when verifying frontend functionality, debugging UI behavior, capturing browser screenshots, or viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[115,118],{"categoryNo":116,"categoryName":117,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":119,"categoryName":120,"taxonomyType":70,"taxonomyTypeDesc":71},"01JBSEEDCAT000000000000009","前端开发",[122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,26,137,89],"webapp","webapp testing","testing","browser","frontend","screenshots","playwright","test","web","debugging","ui","logs","applications","behavior","use","test local",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":33},"01M6BV8MDXKXNVHKS3QF3YDFTF","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[145,146],"wait what","land",{"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":156,"publishedAt":33},"01M6BV756DJHT5BDA1HVRVHJJ7","prototype","Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fprototype\u002FSKILL.md",[153],{"categoryNo":154,"categoryName":155,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000032","设计师",[149,157,158,132,159],"design","explore","state",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":167,"publishedAt":33},"01M6BV6SBW166685KVBPWM2K4N","improve-codebase-architecture","Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.","https:\u002F\u002Fgithub.com\u002Fbnferguson\u002Fdotfiles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimprove-codebase-architecture\u002FSKILL.md",[166],{"categoryNo":119,"categoryName":120,"taxonomyType":70,"taxonomyTypeDesc":71},[168,169,170,171],"architecture","improve","improve codebase architecture","report"]