[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C4H40QQ47PRG7F334YYPFZ":3,"skill-same:01M7C4H40QQ47PRG7F334YYPFZ":69},{"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":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7C4H40QQ47PRG7F334YYPFZ","recording-demo-videos",null,"Create or refresh demo videos of a repository's executable applications. Use when asked to record application demos, product walkthroughs, or a video for each app. Discover the applications, run them locally, and deliver verified WebM recordings with edge-tts voice narration, captions, posters, chapters, and rerun commands. Covers web, CLI, API, worker, and native applications; not promotional animation or video editing unrelated to running software.","QuinntyneBrown\u002Fquinntyne-brown-studio","QuinntyneBrown","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1749159?v=4","01M7C4DEMVW0A87TDN8PMZTNFG","Quinntyne Brown","01M7C4DENDYX1QYZDN3F0A5ZX0",1,"MIT","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecording-demo-videos\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: recording-demo-videos\ndescription: >-\n  Create or refresh demo videos of a repository's executable applications.\n  Use when asked to record application demos, product walkthroughs, or a video\n  for each app. Discover the applications, run them locally, and deliver verified\n  WebM recordings with edge-tts voice narration, captions, posters, chapters,\n  and rerun commands.\n  Covers web, CLI, API, worker, and native applications; not promotional animation\n  or video editing unrelated to running software.\n---\n\n# Recording demo videos\n\nCreate a watchable demonstration of each executable application: real execution,\nspoken narration, readable captions, and verified outcomes. The default is one\ncontinuous successful take at 1280 × 720, roughly two to five minutes per\napplication, with a synthesized voice track. Narration is mandatory: a video\nwithout an audible narration track is not a finished demo. Adjust length to\nuseful workflow coverage rather than padding or rushing it. Honor a user's\nrequested applications, format, and presentation overrides.\n\nResolve supporting references relative to this installed skill folder; resolve\napplication files and `docs\u002Fdemo\u002F` relative to the consuming repository.\n\n## 1. Understand the repository and identify applications\n\nRead applicable agent instructions, README files, workspace\u002Fproject manifests,\nentrypoints, startup scripts, tests, and existing demo tooling. Read useful content\nunder `docs\u002Fspecs\u002F` and `docs\u002Fdetailed-designs\u002F` when present. Neither directory is\nrequired: infer behavior from source, tests, and runtime inspection when absent.\nIf documents disagree with the implementation, demonstrate what actually works\nand record the discrepancy; do not claim unimplemented requirements.\n\nInventory every executable application before selecting scenes. Record its\npurpose, audience, entrypoint, run command, local endpoint or interaction surface,\ndependencies, authentication, and candidate workflows. Count independently\nrunnable first-party APIs and workers even when a web app also depends on them.\nSeparate user-facing apps served by one host still deserve separate videos.\nExclude libraries, migrations, test runners, repository maintenance scripts, and third-party\ninfrastructure unless the user explicitly wants to demonstrate those tools.\n\nAssign stable lowercase hyphenated slugs, preserving established demo names.\nDisambiguate duplicate names with their subsystem. Account for every application\nas recorded, blocked with a reason, or excluded by the user's scope. A repository\nwith no executable applications needs an explanation, not an invented demo.\n\n## 2. Choose workflows and the recording method\n\nBuild a short storyboard per application: purpose, starting state, actions,\nobservable assertions, narration, and a useful final state. Write the narration\nas short spoken paragraphs, one per opening card, chapter, or step, in second\nperson and plain language; the same text becomes the on-screen captions. Prefer\ncomplete user journeys over touring every route or endpoint. Include meaningful\nvalidation or permission behavior when it explains the product. Avoid exposing credentials,\nprivate records, tokens, or sensitive shell history in footage and diagnostics.\n\nReuse existing acceptance helpers and demo conventions when suitable. Select the\ncapture method from available tools and the application's real interaction surface:\n\n- Browser UI: read [browser recording](references\u002Fbrowser-recording.md).\n- CLI, API, worker, or native UI: read\n  [terminal and native recording](references\u002Fterminal-native-recording.md).\n\nIf apps share data, order their stories by dependency and reuse deterministic\nsynthetic fixtures. Explain which earlier recording establishes later state.\nProvide a command that reproduces the whole sequence from a clean environment;\nan individual rerun must prepare its prerequisites or name the required sequence.\n\n## 3. Prepare a reproducible local run\n\nVerify the required runtimes, locked dependencies, capture tools, database,\nconfiguration, and local credentials, plus the narration tools: Python with the\n`edge-tts` package, internet access for synthesis, and ffmpeg with ffprobe,\nlibopus, and libvpx. Prefer repository setup\u002Fbuild scripts.\nUse normal authorized local setup to resolve missing dependencies; if credentials,\nplatform support, or external access remain unavailable, report exactly what is\nneeded and continue independent applications.\n\nUse disposable demo storage and synthetic identities. Before any reset or cleanup,\nverify the resolved database, directory, or container belongs to this run. Never\ninherit a reset-on-start setting against an existing development database. Do not\nreuse a listening server unless its identity, configuration, and data isolation\nare established; otherwise choose unused ports. Bind demo-only services locally.\n\nUse real application services and persistence where the application requires them.\nExisting local adapters for mail, payments, AI, or other external integrations are\nacceptable when disclosed. Do not substitute mocked product responses or remove\nauthentication to make the demo pass. Avoid actual external sends or purchases\nwithout authorization already covering them.\n\nCreate application-specific recording scripts in the repository's existing test\nor script structure. Keep recordings separate from the ordinary acceptance run\nand its commit gates. Give startup, individual actions, the whole take, and\nteardown finite timeouts. Check readiness before recording; do not fill the video\nwith build logs or server startup waits.\n\nTrack owned processes and resources from their creation. Enclose startup as well\nas recording in cleanup handling so partial setup failures also clean up. On\nWindows, launch background helpers hidden. Stop only owned processes, restore\nchanged environment settings, and report any cleanup failures and resources left.\nKeep temporary video, trace, credentials, and logs in an ignored run directory.\n\n## 4. Synthesize the narration\n\nSynthesize the voice track with the free `edge-tts` Python package (Microsoft\nEdge online read-aloud; no API key, Azure subscription, or paid Speech service).\nInstall it with `python -m pip install edge-tts` using the interpreter named by\n`PYTHON`, and check connectivity with `python -m edge_tts --list-voices`. Use\nthe same voices as the creating-narrated-videos skill: `en-US-AndrewMultilingualNeural`\nfor the narrator and `en-US-AvaMultilingualNeural` for a second speaker such as\na labelled customer or administrator; `EDGE_VOICE` and `EDGE_VOICE_2` override\nthem. Use one voice set across every application in the same demo index.\n\nKeep the narration text in a per-application `\u003Capp-slug>-narration.md` whose\nparagraphs appear in capture order, each tagged with the chapter or step it\nbelongs to. Edge does not support custom SSML, so keep acronyms and code\nidentifiers in a `pronunciations.json` lexicon of plain-text spoken replacements,\napply it before synthesis, and spot-check difficult entries. Captions keep the\nwritten form; the voice track uses the spoken form.\n\nSynthesize before recording, one clip per paragraph, into the ignored run\ndirectory. Normalize the clips to a common format, measure each with ffprobe,\nand make every presentation hold at least as long as its clip plus a short\nmargin so the narrator finishes before the next action. During capture, log the\ntimestamp at which each paragraph's caption appears. After the video finalizes,\nplace each clip at its logged time, corrected by the same offset used for the\nchapter times, pad the gaps with silence, loudness-normalize the result, and mux\nit into the WebM as an Opus track with ffmpeg without re-encoding the video.\nThe video stream, its duration, and the chapter times must not change.\n\nIf Python, `edge-tts`, internet access, or ffmpeg is unavailable, that is an\nactionable blocker for narration: keep the recording and its narration text in\nstaging, state exactly which commands remain, and do not promote or describe a\nsilent video as a completed demo. Never substitute silence, a text transcript,\nor synthetic placeholder audio for the narration.\n\n## 5. Record and verify\n\nUse readable pacing, a brief opening, chapter transitions, and captions explaining\nthe user's outcome. Keep captions clear of the controls or output being shown.\nPresentation delays are for listening and reading; readiness must use observable\nconditions. Assert actual results before narrating that they succeeded:\npersisted state, calculated values, loaded media, returned responses, or\ncompleted jobs.\n\nRecord one continuous successful take per application. For browser capture, keep\nthe main story in one recorded page. Multiple actors may switch authenticated\nsessions within that story without exposing secrets. Do not splice failed scenes\ninto a successful recording. Disable automatic retries; diagnose a failed take\nand re-record it in full after a justified harness or setup correction.\n\nFix local setup and recording-harness problems within the request. Product bugs\nare outside this skill's default repair scope: capture the failing step and\nexpected versus actual behavior, mark the affected demo blocked, and finish\nindependent apps. Do not repeatedly retry unchanged failures or weaken assertions.\nUser authorization for product repairs can expand that scope explicitly.\n\nAfter capture has finalized and the narration is muxed, open and inspect the\nencoded WebM itself. Check playback, measured duration and dimensions, beginning\nand ending, each chapter, caption readability, and important visual outcomes.\nConfirm with ffprobe that the file has one video stream and one Opus audio\nstream of the same duration, then play the start of each chapter and verify the\nspoken paragraph matches its caption and begins within about a second of the\naction it describes. Sample frames are useful but do not replace playback\nreview for pacing. Verify media really loaded; an image's URL or alt text alone\nis not evidence. Derive chapter times from the recording\ntimeline, verify them against playback, and choose a representative poster from\nthe successful footage. A nonempty file is not sufficient validation.\n\n## 6. Deliver artifacts and rerun instructions\n\nStage each application's video, poster, narration text, and chapter metadata\noutside final paths.\nPromote the verified set only after its assertions and video review pass. Back up\nexisting files and restore them if promotion fails; do not mix an old video with\nnew chapter times or a new poster. Preserve unrelated demos and manual README\ncontent. If a rerun fails, distinguish any retained prior video from this run.\n\nDefault deliverables in the consuming repository:\n\n```text\ndocs\u002Fdemo\u002F\n├── README.md\n├── pronunciations.json\n├── \u003Capp-slug>.webm\n├── \u003Capp-slug>-poster.png\n└── \u003Capp-slug>-narration.md\n```\n\nRepeat the video, poster, and narration files for every application. Synthesized\nclips and the assembled audio track stay in the ignored run directory; the\nnarration text and lexicon are the reproducible sources. The README must include:\n\n- An application inventory with links, purpose, and recorded\u002Fblocked status.\n- Measured video duration, dimensions, file size, audio codec, narrator voices,\n  and linked poster and narration text per recording.\n- Chapter timestamps and the verified workflows they demonstrate.\n- Exact setup and rerun commands, working directories, tool prerequisites,\n  configuration variable names, data preparation, and cleanup behavior.\n- Recording order, relevant source\u002Ftest links and revision when available,\n  integration substitutions, product limitations, and actionable blockers.\n\nRecord the actual commands, not an assumed universal `npm run demo`. Keep secrets\nout of documentation. Include reproducible recording sources, but keep transient\nlogs and failure artifacts out of the deliverable set. Report completion only\nwhen every in-scope application has a reviewed video; otherwise report partial\ncompletion with explicit blockers and links to the successful artifacts.\n","# Recording demo videos\n\nCreate a watchable demonstration of each executable application: real execution,\nspoken narration, readable captions, and verified outcomes. The default is one\ncontinuous successful take at 1280 × 720, roughly two to five minutes per\napplication, with a synthesized voice track. Narration is mandatory: a video\nwithout an audible narration track is not a finished demo. Adjust length to\nuseful workflow coverage rather than padding or rushing it. Honor a user's\nrequested applications, format, and presentation overrides.\n\nResolve supporting references relative to this installed skill folder; resolve\napplication files and `docs\u002Fdemo\u002F` relative to the consuming repository.\n\n## 1. Understand the repository and identify applications\n\nRead applicable agent instructions, README files, workspace\u002Fproject manifests,\nentrypoints, startup scripts, tests, and existing demo tooling. Read useful content\nunder `docs\u002Fspecs\u002F` and `docs\u002Fdetailed-designs\u002F` when present. Neither directory is\nrequired: infer behavior from source, tests, and runtime inspection when absent.\nIf documents disagree with the implementation, demonstrate what actually works\nand record the discrepancy; do not claim unimplemented requirements.\n\nInventory every executable application before selecting scenes. Record its\npurpose, audience, entrypoint, run command, local endpoint or interaction surface,\ndependencies, authentication, and candidate workflows. Count independently\nrunnable first-party APIs and workers even when a web app also depends on them.\nSeparate user-facing apps served by one host still deserve separate videos.\nExclude libraries, migrations, test runners, repository maintenance scripts, and third-party\ninfrastructure unless the user explicitly wants to demonstrate those tools.\n\nAssign stable lowercase hyphenated slugs, preserving established demo names.\nDisambiguate duplicate names with their subsystem. Account for every application\nas recorded, blocked with a reason, or excluded by the user's scope. A repository\nwith no executable applications needs an explanation, not an invented demo.\n\n## 2. Choose workflows and the recording method\n\nBuild a short storyboard per application: purpose, starting state, actions,\nobservable assertions, narration, and a useful final state. Write the narration\nas short spoken paragraphs, one per opening card, chapter, or step, in second\nperson and plain language; the same text becomes the on-screen captions. Prefer\ncomplete user journeys over touring every route or endpoint. Include meaningful\nvalidation or permission behavior when it explains the product. Avoid exposing credentials,\nprivate records, tokens, or sensitive shell history in footage and diagnostics.\n\nReuse existing acceptance helpers and demo conventions when suitable. Select the\ncapture method from available tools and the application's real interaction surface:\n\n- Browser UI: read [browser recording](references\u002Fbrowser-recording.md).\n- CLI, API, worker, or native UI: read\n  [terminal and native recording](references\u002Fterminal-native-recording.md).\n\nIf apps share data, order their stories by dependency and reuse deterministic\nsynthetic fixtures. Explain which earlier recording establishes later state.\nProvide a command that reproduces the whole sequence from a clean environment;\nan individual rerun must prepare its prerequisites or name the required sequence.\n\n## 3. Prepare a reproducible local run\n\nVerify the required runtimes, locked dependencies, capture tools, database,\nconfiguration, and local credentials, plus the narration tools: Python with the\n`edge-tts` package, internet access for synthesis, and ffmpeg with ffprobe,\nlibopus, and libvpx. Prefer repository setup\u002Fbuild scripts.\nUse normal authorized local setup to resolve missing dependencies; if credentials,\nplatform support, or external access remain unavailable, report exactly what is\nneeded and continue independent applications.\n\nUse disposable demo storage and synthetic identities. Before any reset or cleanup,\nverify the resolved database, directory, or container belongs to this run. Never\ninherit a reset-on-start setting against an existing development database. Do not\nreuse a listening server unless its identity, configuration, and data isolation\nare established; otherwise choose unused ports. Bind demo-only services locally.\n\nUse real application services and persistence where the application requires them.\nExisting local adapters for mail, payments, AI, or other external integrations are\nacceptable when disclosed. Do not substitute mocked product responses or remove\nauthentication to make the demo pass. Avoid actual external sends or purchases\nwithout authorization already covering them.\n\nCreate application-specific recording scripts in the repository's existing test\nor script structure. Keep recordings separate from the ordinary acceptance run\nand its commit gates. Give startup, individual actions, the whole take, and\nteardown finite timeouts. Check readiness before recording; do not fill the video\nwith build logs or server startup waits.\n\nTrack owned processes and resources from their creation. Enclose startup as well\nas recording in cleanup handling so partial setup failures also clean up. On\nWindows, launch background helpers hidden. Stop only owned processes, restore\nchanged environment settings, and report any cleanup failures and resources left.\nKeep temporary video, trace, credentials, and logs in an ignored run directory.\n\n## 4. Synthesize the narration\n\nSynthesize the voice track with the free `edge-tts` Python package (Microsoft\nEdge online read-aloud; no API key, Azure subscription, or paid Speech service).\nInstall it with `python -m pip install edge-tts` using the interpreter named by\n`PYTHON`, and check connectivity with `python -m edge_tts --list-voices`. Use\nthe same voices as the creating-narrated-videos skill: `en-US-AndrewMultilingualNeural`\nfor the narrator and `en-US-AvaMultilingualNeural` for a second speaker such as\na labelled customer or administrator; `EDGE_VOICE` and `EDGE_VOICE_2` override\nthem. Use one voice set across every application in the same demo index.\n\nKeep the narration text in a per-application `\u003Capp-slug>-narration.md` whose\nparagraphs appear in capture order, each tagged with the chapter or step it\nbelongs to. Edge does not support custom SSML, so keep acronyms and code\nidentifiers in a `pronunciations.json` lexicon of plain-text spoken replacements,\napply it before synthesis, and spot-check difficult entries. Captions keep the\nwritten form; the voice track uses the spoken form.\n\nSynthesize before recording, one clip per paragraph, into the ignored run\ndirectory. Normalize the clips to a common format, measure each with ffprobe,\nand make every presentation hold at least as long as its clip plus a short\nmargin so the narrator finishes before the next action. During capture, log the\ntimestamp at which each paragraph's caption appears. After the video finalizes,\nplace each clip at its logged time, corrected by the same offset used for the\nchapter times, pad the gaps with silence, loudness-normalize the result, and mux\nit into the WebM as an Opus track with ffmpeg without re-encoding the video.\nThe video stream, its duration, and the chapter times must not change.\n\nIf Python, `edge-tts`, internet access, or ffmpeg is unavailable, that is an\nactionable blocker for narration: keep the recording and its narration text in\nstaging, state exactly which commands remain, and do not promote or describe a\nsilent video as a completed demo. Never substitute silence, a text transcript,\nor synthetic placeholder audio for the narration.\n\n## 5. Record and verify\n\nUse readable pacing, a brief opening, chapter transitions, and captions explaining\nthe user's outcome. Keep captions clear of the controls or output being shown.\nPresentation delays are for listening and reading; readiness must use observable\nconditions. Assert actual results before narrating that they succeeded:\npersisted state, calculated values, loaded media, returned responses, or\ncompleted jobs.\n\nRecord one continuous successful take per application. For browser capture, keep\nthe main story in one recorded page. Multiple actors may switch authenticated\nsessions within that story without exposing secrets. Do not splice failed scenes\ninto a successful recording. Disable automatic retries; diagnose a failed take\nand re-record it in full after a justified harness or setup correction.\n\nFix local setup and recording-harness problems within the request. Product bugs\nare outside this skill's default repair scope: capture the failing step and\nexpected versus actual behavior, mark the affected demo blocked, and finish\nindependent apps. Do not repeatedly retry unchanged failures or weaken assertions.\nUser authorization for product repairs can expand that scope explicitly.\n\nAfter capture has finalized and the narration is muxed, open and inspect the\nencoded WebM itself. Check playback, measured duration and dimensions, beginning\nand ending, each chapter, caption readability, and important visual outcomes.\nConfirm with ffprobe that the file has one video stream and one Opus audio\nstream of the same duration, then play the start of each chapter and verify the\nspoken paragraph matches its caption and begins within about a second of the\naction it describes. Sample frames are useful but do not replace playback\nreview for pacing. Verify media really loaded; an image's URL or alt text alone\nis not evidence. Derive chapter times from the recording\ntimeline, verify them against playback, and choose a representative poster from\nthe successful footage. A nonempty file is not sufficient validation.\n\n## 6. Deliver artifacts and rerun instructions\n\nStage each application's video, poster, narration text, and chapter metadata\noutside final paths.\nPromote the verified set only after its assertions and video review pass. Back up\nexisting files and restore them if promotion fails; do not mix an old video with\nnew chapter times or a new poster. Preserve unrelated demos and manual README\ncontent. If a rerun fails, distinguish any retained prior video from this run.\n\nDefault deliverables in the consuming repository:\n\n```text\ndocs\u002Fdemo\u002F\n├── README.md\n├── pronunciations.json\n├── \u003Capp-slug>.webm\n├── \u003Capp-slug>-poster.png\n└── \u003Capp-slug>-narration.md\n```\n\nRepeat the video, poster, and narration files for every application. Synthesized\nclips and the assembled audio track stay in the ignored run directory; the\nnarration text and lexicon are the reproducible sources. The README must include:\n\n- An application inventory with links, purpose, and recorded\u002Fblocked status.\n- Measured video duration, dimensions, file size, audio codec, narrator voices,\n  and linked poster and narration text per recording.\n- Chapter timestamps and the verified workflows they demonstrate.\n- Exact setup and rerun commands, working directories, tool prerequisites,\n  configuration variable names, data preparation, and cleanup behavior.\n- Recording order, relevant source\u002Ftest links and revision when available,\n  integration substitutions, product limitations, and actionable blockers.\n\nRecord the actual commands, not an assumed universal `npm run demo`. Keep secrets\nout of documentation. Include reproducible recording sources, but keep transient\nlogs and failure artifacts out of the deliverable set. Report completion only\nwhen every in-scope application has a reviewed video; otherwise report partial\ncompletion with explicit blockers and links to the successful artifacts.\n",{"name":5,"description":7},"main","0dbacec4955ea8b75622a8b16233d9bd2618e7ed",".claude\u002Fskills\u002Frecording-demo-videos",0,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown","https:\u002F\u002Fquinntynebrown.com","Microsoft Certified Solutions Developer specializing in C#, ASP.NET Core, TypeScript, Azure, Angular, Web Components, RxJS, SignalR Core & Entity Framework Core","2026-10-19 10:28:28",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill recording-demo-videos",{"tool":39,"command":40},"bunx","bunx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill recording-demo-videos",{"tool":42,"command":43},"pnpm","pnpm dlx skills add QuinntyneBrown\u002Fquinntyne-brown-studio --skill recording-demo-videos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecording-demo-videos\u002FSKILL.md",true,[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",350,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecording-demo-videos\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"evals\u002Fevals.json",6266,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecording-demo-videos\u002Fevals\u002Fevals.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Fvalidation.md",2990,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecording-demo-videos\u002Fevals\u002Fvalidation.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fbrowser-recording.md",5110,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecording-demo-videos\u002Freferences\u002Fbrowser-recording.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fterminal-native-recording.md",4753,"https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecording-demo-videos\u002Freferences\u002Fterminal-native-recording.md",[70,77,84,91,98,105],{"skillNo":71,"name":72,"nameZh":6,"description":73,"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},"01M7C4JA8SJ18P9JERCKVN799X","writing-screen-composition","Create or update docs\u002Fscreen-composition.md, a document that itemizes every page, dialog, notification and shell part from the HTML mocks and lists, for each, the component-library components it shall be composed of plus the UI that must be built locally. Also ensures AGENTS.md has the \"Components library is mandatory (CRITICAL)\" section. Use when the user mentions screen composition, which components a page uses, mapping mocks to a component library, local vs library UI, or before implementing an application against a component library; and whenever docs\u002Fmocks and a component catalogue exist but docs\u002Fscreen-composition.md does not or is out of date.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-screen-composition\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},"01M7C4J46A36085AMSCEKZX3GG","writing-requirements","Create and manage software requirements documents (L1 high-level and L2 detailed with acceptance criteria) in docs\u002Fspecs\u002F. Use this skill whenever the user mentions requirements, specs, specifications, user stories, features to build, acceptance criteria, ATDD, or wants to define what a system should do before coding. Also use when the user says things like 'what should we build', 'let's plan the feature', 'write up what this needs to do', 'define the behavior', or describes functionality they want implemented -- even if they don't explicitly say 'requirements'. If the user is about to start coding a feature and there are no requirements yet, proactively suggest using this skill first. Requirements come before code. Always.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-requirements\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7C4HWSMCNEE8H922B4W4BT7","writing-html-mocks","Write static HTML mocks in docs\u002Fmocks\u002F for EVERY page, dialog and notification of a product in EVERY state (default, loading, empty, error, invalid, busy, success, no-results, forbidden, stacked...), responsive, light and dark, keyboard-accessible, with real copy and a coverage matrix. Use this skill BEFORE writing any frontend code, component, template, view or page; whenever the user says mock, mockup, wireframe, prototype, UI, UX, screen, layout, dialog, modal, toast, banner, empty\u002Ferror\u002Floading state, \"what should this look like\", \"show me the UI\", or describes a feature with a visible result; and whenever docs\u002Fspecs or docs\u002Fdetailed-designs exist but docs\u002Fmocks does not. Also use it to add missing states to existing mocks. Mocks come before implementation: if asked for frontend code with no mocks, say so and offer this first. Pair with extracting-design-systems to turn finished mocks into docs\u002Fdesign-system\u002F.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-html-mocks\u002FSKILL.md",[],[],{"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":97,"publishedAt":19},"01M7C4HQZ8AM15WF2PHH3G2BGN","writing-feature-prompts","Write a ready-to-run implementation prompt for a feature request or a bug fix in the current repository, save it outside the repository and open it in a text editor (Notepad on Windows). A feature prompt drives mocks, design system, requirements, detailed design, estimate update and incremental acceptance-test-driven implementation end to end without stopping; a bug-fix prompt drives reproduce, root cause, fix and documentation alignment. Use whenever the user asks to \"create a prompt\", \"write a prompt for this feature\" or \"for this bug\", wants a \"prompt to build X\" or \"prompt to fix Y\", or asks to open a prompt in Notepad.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-feature-prompts\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7C4HJHMY4ESK2M82BXXJNT9","writing-design-documents","Create software design documents and architecture write-ups from existing L1\u002FL2 requirements in docs\u002Fspecs\u002F. Use for detailed designs organized by subsystem and feature, with requirement traceability and rendered PlantUML C4, class, and sequence diagrams in docs\u002Fdetailed-designs\u002F.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-design-documents\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7C4HAJZ2JQKS09VASR3XM4T","writing-agent-instructions","Writes the agent instruction files a repository needs so coding agents know how to work in it - AGENTS.md plus the CLAUDE.md, GEMINI.md, and .github\u002Fcopilot-instructions.md pointers - generated from a description of what the project shall be, for a project that does not exist yet. Use this whenever someone mentions AGENTS.md, CLAUDE.md, GEMINI.md, copilot-instructions, \"agent instructions\", \"agent context files\", \"coding agent guidance\", or asks to set up, scaffold, bootstrap, or initialise the conventions for a new project or repository. Use it too when someone describes a project they are about to start and wants an agent to follow its conventions, even if they never name any of these files - if they are standing at an empty directory describing what they intend to build, this is the skill.","https:\u002F\u002Fgithub.com\u002FQuinntyneBrown\u002Fquinntyne-brown-studio\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwriting-agent-instructions\u002FSKILL.md",[],[]]