[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DE3D3J4V8GDHDQESBFSY53":3,"skill-same:01M7DE3D3J4V8GDHDQESBFSY53":93},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7DE3D3J4V8GDHDQESBFSY53","verify-transcript",null,"Use when validating transcript CLI behavior, locating its verification features, or running the paid YouTube end-to-end check.","pascalandy\u002Fskills","pascalandy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6694151?v=4","01M7DDRR1T4AMR6J3FV6RHHV5M","Pascal Andy","01M7DDRR2B04BJ8S7QZYZV1WFK",0,"MIT","https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"verify-transcript\"\ndescription: \"Use when validating transcript CLI behavior, locating its verification features, or running the paid YouTube end-to-end check.\"\nkind: \"dev\"\napi-key: \"deepgram\"\n---\n\n# Verify transcript\n\nDrive `transcript` only through `scripts\u002Ftranscript.py`. The verifier finds that public CLI in either the categorized `authoring\u002F` source layout or the flat applied skill layout.\n\n## Launch\n\nThis is a short-lived CLI. It does not start a server or retain a process.\n\n```bash\nVERIFY_DIR=\"\u003Cverify-transcript-skill-dir>\"\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" --help\n```\n\nResolve `VERIFY_DIR` from this skill's directory. Do not depend on the caller's working directory.\n\n## Doctor\n\nCheck the verifier before a run when the layout or local tools look wrong.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" doctor\n```\n\n`doctor` checks `uv`, all seven Feature Map pages, and the adjacent `transcript` public script. It answers `{\"ok\":true}`, or one error per failed check, and `-v` lists every check. It does not call Deepgram, a summary model, YouTube, or Zoom.\n\n## Drive\n\nRun all free checks with one command.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" verify\n```\n\nThe default run covers help and version output, structured recovery, transcript-only planning, discovery, configuration, diagnostics, YouTube dry-run planning, and Zoom source and summary planning. A valid diagnostic response can pass even when the machine is not ready. Read each diagnostic feature's `readiness_ok` observation.\n\nSearch the Feature Map before a focused check. Copy exact selectable values from `features[].id`. Matching Markdown pages are in `documents[]`.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" features zoom\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" features\n```\n\nRead [features\u002FREADME.md](features\u002FREADME.md) for the index. Each feature page names its public command, expected state, and proof.\n\nThe paid end-to-end check runs the canonical test video with the `sonnet` profile. The transcript README's `Test videos` rule pre-authorizes it, sets its limits, and says where it runs.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" verify \\\n  --feature youtube.real-summary \\\n  --allow-paid\n```\n\nPaid work requires both the paid feature ID and `--allow-paid`. The flag alone does not select paid work. `--all` also selects the paid feature and therefore requires `--allow-paid`.\n\n## Evidence\n\nEvery command answers in one JSON line. A verification answers `file`, the run's `result.json`, which records the `verdict` and `evidence_dir`; a failed feature is also one entry of `errors`, with the command that reruns it. A run stopped by an interrupt or a failed write answers `files` instead, the evidence it saved so far. `-v` prints each feature's verdict as it ends. The default evidence root remains `${XDG_STATE_HOME:-~\u002F.local\u002Fstate}\u002Feval-transcript\u002Fruns`. Runs retained before the skill rename stay in the same history.\n\nEach case retains:\n\n- The exact public command with no secret values\n- Captured `stdout`, `stderr`, exit code, duration, and normalized parsed output\n- The feature verdict and observations\n- An artifact manifest with names, sizes, and SHA-256 hashes for the paid flow\n\nThe final `result.json` records the selected layout, aggregate counts, paid authorization, and cleanup result. A successful paid check records the artifact manifest before cleanup. A failed paid check retains its command and process evidence, then cleanup removes any scratch output.\n\n## Cleanup\n\nThe verifier creates one marked directory under the system temporary directory. A `finally` block removes that directory after success, failure, timeout, or interruption.\n\nCleanup refuses a path outside the system temporary directory, a name without the current run ID, or a directory without the current marker. Cleanup never receives the evidence path. Retained evidence survives every normal teardown.\n\nDo not delete evidence as part of verification. If the user asks to remove old evidence, inspect the exact run directories first and use a recoverable deletion method.\n\n## Helpers\n\nAfter changing Deepgram uploads, run this bounded verification loop:\n\n1. Run the verifier doctor above with `-v` and set `TRANSCRIPT_DIR` to the directory its `transcript_skill` line names, whether source or applied\n2. Run the upload contract tests below, then the verifier helper tests\n3. Run the default free verification and inspect its verdict and evidence\n4. Run the `youtube.real-summary` feature above and require its `audio_upload` evidence\n\n```bash\nuv run --with pytest --with httpx --with rich pytest \\\n  \"$TRANSCRIPT_DIR\u002Fscripts\u002Ftests\u002Ftest_transcript.py\" -k TestDeepgramContract -q\n```\n\nThese deterministic tests check bounded upload chunks, intact audio, rejection of success before the full payload is sent, timeout byte reporting, and the workflow deadline. A successful real run alone does not prove behavior on a slow or interrupted connection.\n\nRun the focused helper tests after changing this verifier.\n\n```bash\nuv run --with pytest pytest \"$VERIFY_DIR\u002Fscripts\u002Ftests\" -q\n```\n\nThe tests cover layout discovery, exact feature discovery, public-surface ownership, output streams, paid selection, command confinement, process capture, cleanup, Feature Map coverage, and artifact validation. They stub external paid boundaries. The paid command above is the real end-to-end proof.\n","# Verify transcript\n\nDrive `transcript` only through `scripts\u002Ftranscript.py`. The verifier finds that public CLI in either the categorized `authoring\u002F` source layout or the flat applied skill layout.\n\n## Launch\n\nThis is a short-lived CLI. It does not start a server or retain a process.\n\n```bash\nVERIFY_DIR=\"\u003Cverify-transcript-skill-dir>\"\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" --help\n```\n\nResolve `VERIFY_DIR` from this skill's directory. Do not depend on the caller's working directory.\n\n## Doctor\n\nCheck the verifier before a run when the layout or local tools look wrong.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" doctor\n```\n\n`doctor` checks `uv`, all seven Feature Map pages, and the adjacent `transcript` public script. It answers `{\"ok\":true}`, or one error per failed check, and `-v` lists every check. It does not call Deepgram, a summary model, YouTube, or Zoom.\n\n## Drive\n\nRun all free checks with one command.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" verify\n```\n\nThe default run covers help and version output, structured recovery, transcript-only planning, discovery, configuration, diagnostics, YouTube dry-run planning, and Zoom source and summary planning. A valid diagnostic response can pass even when the machine is not ready. Read each diagnostic feature's `readiness_ok` observation.\n\nSearch the Feature Map before a focused check. Copy exact selectable values from `features[].id`. Matching Markdown pages are in `documents[]`.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" features zoom\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" features\n```\n\nRead [features\u002FREADME.md](features\u002FREADME.md) for the index. Each feature page names its public command, expected state, and proof.\n\nThe paid end-to-end check runs the canonical test video with the `sonnet` profile. The transcript README's `Test videos` rule pre-authorizes it, sets its limits, and says where it runs.\n\n```bash\nuv run \"$VERIFY_DIR\u002Fscripts\u002Fverify_transcript.py\" verify \\\n  --feature youtube.real-summary \\\n  --allow-paid\n```\n\nPaid work requires both the paid feature ID and `--allow-paid`. The flag alone does not select paid work. `--all` also selects the paid feature and therefore requires `--allow-paid`.\n\n## Evidence\n\nEvery command answers in one JSON line. A verification answers `file`, the run's `result.json`, which records the `verdict` and `evidence_dir`; a failed feature is also one entry of `errors`, with the command that reruns it. A run stopped by an interrupt or a failed write answers `files` instead, the evidence it saved so far. `-v` prints each feature's verdict as it ends. The default evidence root remains `${XDG_STATE_HOME:-~\u002F.local\u002Fstate}\u002Feval-transcript\u002Fruns`. Runs retained before the skill rename stay in the same history.\n\nEach case retains:\n\n- The exact public command with no secret values\n- Captured `stdout`, `stderr`, exit code, duration, and normalized parsed output\n- The feature verdict and observations\n- An artifact manifest with names, sizes, and SHA-256 hashes for the paid flow\n\nThe final `result.json` records the selected layout, aggregate counts, paid authorization, and cleanup result. A successful paid check records the artifact manifest before cleanup. A failed paid check retains its command and process evidence, then cleanup removes any scratch output.\n\n## Cleanup\n\nThe verifier creates one marked directory under the system temporary directory. A `finally` block removes that directory after success, failure, timeout, or interruption.\n\nCleanup refuses a path outside the system temporary directory, a name without the current run ID, or a directory without the current marker. Cleanup never receives the evidence path. Retained evidence survives every normal teardown.\n\nDo not delete evidence as part of verification. If the user asks to remove old evidence, inspect the exact run directories first and use a recoverable deletion method.\n\n## Helpers\n\nAfter changing Deepgram uploads, run this bounded verification loop:\n\n1. Run the verifier doctor above with `-v` and set `TRANSCRIPT_DIR` to the directory its `transcript_skill` line names, whether source or applied\n2. Run the upload contract tests below, then the verifier helper tests\n3. Run the default free verification and inspect its verdict and evidence\n4. Run the `youtube.real-summary` feature above and require its `audio_upload` evidence\n\n```bash\nuv run --with pytest --with httpx --with rich pytest \\\n  \"$TRANSCRIPT_DIR\u002Fscripts\u002Ftests\u002Ftest_transcript.py\" -k TestDeepgramContract -q\n```\n\nThese deterministic tests check bounded upload chunks, intact audio, rejection of success before the full payload is sent, timeout byte reporting, and the workflow deadline. A successful real run alone does not prove behavior on a slow or interrupted connection.\n\nRun the focused helper tests after changing this verifier.\n\n```bash\nuv run --with pytest pytest \"$VERIFY_DIR\u002Fscripts\u002Ftests\" -q\n```\n\nThe tests cover layout discovery, exact feature discovery, public-surface ownership, output streams, paid selection, command confinement, process capture, cleanup, Feature Map coverage, and artifact validation. They stub external paid boundaries. The paid command above is the real end-to-end proof.\n",{"kind":24,"name":5,"api-key":25,"description":7},"dev","deepgram","main","c2b929d1a54305e77aad0296872e90e08d68a637","authoring\u002Fverify-loops\u002Fverify-transcript",1,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills","https:\u002F\u002Fgithub.com\u002Fpascalandy","https:\u002F\u002Fblog.pascalandy.com","The question: how can I build the default one-stop place where entrepreneurs can start their mobile-first websites and blog? Psst psst… play-with-ghost.com","2026-11-15 03:34:59",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add pascalandy\u002Fskills --skill verify-transcript",{"tool":41,"command":42},"bunx","bunx skills add pascalandy\u002Fskills --skill verify-transcript",{"tool":44,"command":45},"pnpm","pnpm dlx skills add pascalandy\u002Fskills --skill verify-transcript","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002FSKILL.md",true,[49,55,59,63,67,71,75,79,83,89],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"features\u002Fconfiguration.md","REFERENCE","参考文档",3019,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002Fconfiguration.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"features\u002Fdiagnostics.md",2050,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002Fdiagnostics.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"features\u002Fdry-runs.md",1904,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002Fdry-runs.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"features\u002Finterface.md",5864,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002Finterface.md",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"features\u002FREADME.md",2904,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002FREADME.md",{"path":72,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":73,"sourceHtmlUrl":74},"features\u002Fsummaries.md",2650,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002Fsummaries.md",{"path":76,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":77,"sourceHtmlUrl":78},"features\u002Fyoutube.md",3291,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002Fyoutube.md",{"path":80,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":81,"sourceHtmlUrl":82},"features\u002Fzoom.md",1975,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Ffeatures\u002Fzoom.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Ftests\u002Ftest_verify_transcript.py","SCRIPT","脚本",28514,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Fscripts\u002Ftests\u002Ftest_verify_transcript.py",{"path":90,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fverify_transcript.py",80170,"https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fauthoring\u002Fverify-loops\u002Fverify-transcript\u002Fscripts\u002Fverify_transcript.py",[94,101,108,115,122,127],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7DEA67FREYEGQJYTWD9D0GB","writing-great-skills","Use when creating, modifying, evaluating a skill.","https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-great-skills\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7DEA3ZN566HSV6YJ8KPE824","writing-for-agents","Use when creating, editing, or reviewing a skill, AGENTS.md, CLAUDE.md, or another document agents read.","https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7DEA0FRE0FEYV9XS0YTTBPJ","why","Use for questions about design rationale, the history of regressions or incidents, or the evidence behind thresholds and tradeoffs. Use `how` for runtime behavior. Do not use for plain commit or date lookups.","https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7DE9XVZASJS9PC1A5BVMVHG","verify-video-archive","Use when validating the macOS or Linux archive workflow reached by `just convert-video`, including real media, prerequisites, terminal progress, source safety, locking, and recovery.","https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify-video-archive\u002FSKILL.md",[],[],{"skillNo":123,"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":124,"categories":125,"keywords":126,"publishedAt":19},"01M7DE9VTG6ZEQH1M10J66T8MR","https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify-transcript\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":19},"01M7DE9RWQ6WNVG455HQFHVNFR","verify-skills","Use when verifying `just compile-skills`, `just remote-skills`, `just install-skills`, or `just skills-discover` in the skills repository, such as after changing their scripts or adding, renaming, or moving a skill.","https:\u002F\u002Fgithub.com\u002Fpascalandy\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify-skills\u002FSKILL.md",[],[]]