[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P212J6NA6DCFSCYVTWZSZM":3,"skill-same:01M6P212J6NA6DCFSCYVTWZSZM":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":13,"repositoryHtmlUrl":68,"repositoryHomepageUrl":6,"ownerHtmlUrl":69,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":70,"install":71,"resources":84},"01M6P212J6NA6DCFSCYVTWZSZM","dos-verify-done-claims",null,"Before accepting an agent's 'done \u002F shipped \u002F fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's `dos verify` and `dos commit-audit` — never the agent's own narration.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fdos-verify-done-claims\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"claims","dos verify done claims","done","verify","master","quality-gate","critical","claim","community","trust","narration","cli","never","diff","audit","verification","git","commit","gemini","safe","2026-11-10 10:12:30",false,"---\nname: dos-verify-done-claims\ndescription: \"Before accepting an agent's 'done \u002F shipped \u002F fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's `dos verify` and `dos commit-audit` — never the agent's own narration.\"\ncategory: quality\nrisk: critical\nsource: community\nsource_repo: anthony-chaudhary\u002Fdos-kernel\nsource_type: community\ndate_added: \"2026-06-12\"\nauthor: anthony-chaudhary\ntags: [verification, git, ai-agents, trust, quality-gate]\ntools: [claude, cursor, gemini]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Fdos-kernel\u002Fblob\u002Fmaster\u002FLICENSE\"\nplugin:\n  targets:\n    codex: blocked\n    claude: blocked\n  setup:\n    type: manual\n    summary: \"Setup installs and executes an external PyPI CLI; keep out of plugin-safe bundles.\"\n    docs: SKILL.md\n---\n\n# Verify done-claims against ground truth, not the agent's word\n\n## Overview\n\nWhen an AI agent says \"done\", \"shipped\", or \"fixed\", that is a **claim**, not a\nfact — and a claim the agent checks by re-reading its own work is *consistency,\nnot grounding*. This skill replaces that self-report with a verdict from a\nwitness the agent did not author: it shells the **DOS kernel** (`dos verify`,\n`dos commit-audit`) to confirm the claimed effect from git ancestry and the\ncommit's actual diff. DOS is deterministic — no API key, no LLM. The verdict is\ngit-only and offline as used here; the one exception is `dos verify` in a\nworkspace that wires a CI oracle, which `--no-ci` suppresses (see Security &\nSafety Notes).\n\nThis skill adapts the DOS reference \"witness-claim\" pattern\n(`anthony-chaudhary\u002Fdos-kernel`) into a host-agnostic screenplay.\n\n## When to Use This Skill\n\n- Use when an agent reports a task\u002Fphase\u002Ffeature as **complete** and you want\n  that \"done\" confirmed from evidence before building on it.\n- Use right after a commit, to confirm the commit's **message matches its diff**\n  (catch a `fix:` that only touched a README, or a \"tests pass\" that deleted the\n  assertions).\n- Use when folding many sub-agents' results — verify each claimed effect instead\n  of trusting the return string.\n- **Do not** use it to judge whether code is *correct* — that is what the test\n  suite is for. This skill checks did-the-claimed-thing-actually-ship.\n\n## How It Works\n\n### Step 1: Install the kernel (once)\n\n```bash\npython3 -m venv .dos-venv\n. .dos-venv\u002Fbin\u002Factivate\npython -m pip install 'dos-kernel==\u003Creviewed-version>'  # provides the `dos` CLI\n```\n\n### Step 2: Audit the latest commit's claim vs its diff\n\nA commit subject is forgeable (whoever wrote the message authored it); the files\nit touched are not (git did). `dos commit-audit` grades the subject against the\nactual diff:\n\n```bash\ndos commit-audit --workspace . HEAD --json\n```\n\n`commit-audit --json` prints a JSON **array** of audited commits (one element\neven for a single `HEAD`), so read `verdict` from the first element — e.g.\n`dos commit-audit --workspace . HEAD --json | jq -r '.[0].verdict'`. (Without\n`--json` the same verdict prints as a one-line text row: `· OK …`,\n`⚑ UNWITNESSED …`, or `· abstain …`.) The verdicts are: `OK` (the diff backs the\nclaim's *kind*), `CLAIM_UNWITNESSED` (the subject's claim is not evidenced by the\ndiff — treat the \"done\" as unproven), or `ABSTAIN`. This judges the *kind* of\nchange, never correctness — run the tests for that.\n\n### Step 3: Verify a named phase actually shipped\n\nIf the agent claims a specific plan\u002Fphase landed, confirm it from git history\nrather than the transcript:\n\n```bash\ndos verify --workspace . PLAN PHASE --json --no-ci\n```\n\n`--no-ci` keeps the verdict git-only (see the Security note below). With `--json`\nyou get the `shipped` and `source` fields. (The default text form prints\n`SHIPPED PLAN PHASE (via grep)` or `NOT_SHIPPED PLAN PHASE (via none)` — the same\nverdict, and the process exit code is non-zero when not shipped.)\n\nGrade `shipped: true` by the `source`, because git fallback grades itself by\n**forgeability** — and forgeable evidence is exactly what this skill exists to\ndistrust:\n\n- `registry` or `grep-artifact` — **non-forgeable** (a registry row, or an\n  artefact\u002Fdiff rung). This closes the claim.\n- `grep-subject` (or bare `grep`) — **forgeable**: a commit *subject* or body\n  carried the phase token, which an agent can write without doing the work (even\n  on an empty commit). Treat this as *shipped-per-the-subject*, not confirmed —\n  corroborate it (run `dos commit-audit` on that commit, below) before you close.\n- `none` — no positive evidence; accept as \"not shipped\", not as a tool failure.\n\n### Step 4: Fold only confirmed effects\n\nAccept the agent's \"done\" **only** when Step 2\u002F3 corroborate it. If\n`CLAIM_UNWITNESSED` or `shipped: false`, the work is not done regardless of how\nconfidently the agent narrated it — send it back.\n\n## Examples\n\n### Example 1: gate an agent's \"I fixed the bug\" claim\n\n```bash\n# The agent committed and said it's fixed. Check the diff backs the claim.\n# commit-audit --json returns an array, so read the first element's verdict:\ndos commit-audit --workspace . HEAD --json | jq -r '.[0].verdict'\n# OK                -> the change is of the claimed kind; now run the tests\n# CLAIM_UNWITNESSED -> the commit doesn't do what it says; reject\n```\n\n### Example 2: confirm a feature phase shipped before closing a ticket\n\n```bash\ndos verify --workspace . AUTH AUTH2 --json --no-ci\n# shipped: true, source: registry|grep-artifact -> non-forgeable; safe to close\n# shipped: true, source: grep-subject|grep       -> forgeable subject\u002Fbody match;\n#   shipped-per-the-subject only -> corroborate with commit-audit before closing\n# shipped: false, source: none -> no evidence; keep the ticket open\n```\n\n## Best Practices\n\n- ✅ Run `dos commit-audit HEAD` immediately after every agent commit.\n- ✅ Treat `source: none` \u002F `CLAIM_UNWITNESSED` as \"not done\", not as a tool error.\n- ✅ Close a claim on a **non-forgeable** `source` (`registry`, `grep-artifact`).\n  Treat `grep-subject` \u002F bare `grep` as forgeable (an agent can write the subject\n  text) — corroborate before closing.\n- ✅ Keep the test suite as the separate correctness gate — this skill checks shipping, not correctness.\n- ❌ Don't accept a \"done\" because the agent's prose was confident.\n- ❌ Don't use this to replace code review or testing.\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- It checks whether a claimed change *shipped* \u002F matches its diff — not whether the code is *correct*.\n- `dos verify` reads git history; in a repo with no commits there is nothing to witness (it will honestly report `source: none`).\n- Stop and ask for clarification if required inputs (a git repo, the `dos` CLI) are missing.\n\n## Security & Safety Notes\n\n- This skill runs shell commands: installing `dos-kernel` into an isolated\n  virtualenv and the read-only\n  `dos` verbs (`dos commit-audit`, `dos verify`). These verbs never **mutate**\n  the repo or push. `dos commit-audit` only reads git history and the working\n  tree (no network). `dos verify` is also git-only **unless** the workspace has\n  wired a CI oracle (`[verify] non_git_oracle` in its `dos.toml`), in which case\n  it may shell a network check (e.g. `gh api`) for the verdict — pass `--no-ci`\n  (as the examples above do) to force the git-only path and guarantee no network.\n- `pip install dos-kernel` installs from PyPI. The distribution name is\n  `dos-kernel` (the bare `dos` on PyPI is an unrelated package — do not install\n  it). Pin a reviewed version; do not install an unpinned latest release into a\n  global Python environment.\n- Run in the repository you intend to adjudicate; the `--workspace .` argument\n  scopes every verdict to that repo.\n\n## Common Pitfalls\n\n- **Problem:** `dos verify` returns `source: none` and it looks like a failure.\n  **Solution:** That is the honest \"no evidence\" verdict — it means the phase has\n  no ship commit, so the claim is unproven. Re-stamp the real commit or keep the\n  task open.\n- **Problem:** Installing the wrong package.\n  **Solution:** The PyPI name is `dos-kernel`, not `dos`.\n\n## Related Skills\n\n- The upstream DOS reference screenplays (`dos-witness-claim`, `dos-goal-gate`)\n  in `anthony-chaudhary\u002Fdos-kernel` cover the multi-agent fan-out and\n  self-stopping-agent variants of this same witness discipline.\n","# Verify done-claims against ground truth, not the agent's word\n\n## Overview\n\nWhen an AI agent says \"done\", \"shipped\", or \"fixed\", that is a **claim**, not a\nfact — and a claim the agent checks by re-reading its own work is *consistency,\nnot grounding*. This skill replaces that self-report with a verdict from a\nwitness the agent did not author: it shells the **DOS kernel** (`dos verify`,\n`dos commit-audit`) to confirm the claimed effect from git ancestry and the\ncommit's actual diff. DOS is deterministic — no API key, no LLM. The verdict is\ngit-only and offline as used here; the one exception is `dos verify` in a\nworkspace that wires a CI oracle, which `--no-ci` suppresses (see Security &\nSafety Notes).\n\nThis skill adapts the DOS reference \"witness-claim\" pattern\n(`anthony-chaudhary\u002Fdos-kernel`) into a host-agnostic screenplay.\n\n## When to Use This Skill\n\n- Use when an agent reports a task\u002Fphase\u002Ffeature as **complete** and you want\n  that \"done\" confirmed from evidence before building on it.\n- Use right after a commit, to confirm the commit's **message matches its diff**\n  (catch a `fix:` that only touched a README, or a \"tests pass\" that deleted the\n  assertions).\n- Use when folding many sub-agents' results — verify each claimed effect instead\n  of trusting the return string.\n- **Do not** use it to judge whether code is *correct* — that is what the test\n  suite is for. This skill checks did-the-claimed-thing-actually-ship.\n\n## How It Works\n\n### Step 1: Install the kernel (once)\n\n```bash\npython3 -m venv .dos-venv\n. .dos-venv\u002Fbin\u002Factivate\npython -m pip install 'dos-kernel==\u003Creviewed-version>'  # provides the `dos` CLI\n```\n\n### Step 2: Audit the latest commit's claim vs its diff\n\nA commit subject is forgeable (whoever wrote the message authored it); the files\nit touched are not (git did). `dos commit-audit` grades the subject against the\nactual diff:\n\n```bash\ndos commit-audit --workspace . HEAD --json\n```\n\n`commit-audit --json` prints a JSON **array** of audited commits (one element\neven for a single `HEAD`), so read `verdict` from the first element — e.g.\n`dos commit-audit --workspace . HEAD --json | jq -r '.[0].verdict'`. (Without\n`--json` the same verdict prints as a one-line text row: `· OK …`,\n`⚑ UNWITNESSED …`, or `· abstain …`.) The verdicts are: `OK` (the diff backs the\nclaim's *kind*), `CLAIM_UNWITNESSED` (the subject's claim is not evidenced by the\ndiff — treat the \"done\" as unproven), or `ABSTAIN`. This judges the *kind* of\nchange, never correctness — run the tests for that.\n\n### Step 3: Verify a named phase actually shipped\n\nIf the agent claims a specific plan\u002Fphase landed, confirm it from git history\nrather than the transcript:\n\n```bash\ndos verify --workspace . PLAN PHASE --json --no-ci\n```\n\n`--no-ci` keeps the verdict git-only (see the Security note below). With `--json`\nyou get the `shipped` and `source` fields. (The default text form prints\n`SHIPPED PLAN PHASE (via grep)` or `NOT_SHIPPED PLAN PHASE (via none)` — the same\nverdict, and the process exit code is non-zero when not shipped.)\n\nGrade `shipped: true` by the `source`, because git fallback grades itself by\n**forgeability** — and forgeable evidence is exactly what this skill exists to\ndistrust:\n\n- `registry` or `grep-artifact` — **non-forgeable** (a registry row, or an\n  artefact\u002Fdiff rung). This closes the claim.\n- `grep-subject` (or bare `grep`) — **forgeable**: a commit *subject* or body\n  carried the phase token, which an agent can write without doing the work (even\n  on an empty commit). Treat this as *shipped-per-the-subject*, not confirmed —\n  corroborate it (run `dos commit-audit` on that commit, below) before you close.\n- `none` — no positive evidence; accept as \"not shipped\", not as a tool failure.\n\n### Step 4: Fold only confirmed effects\n\nAccept the agent's \"done\" **only** when Step 2\u002F3 corroborate it. If\n`CLAIM_UNWITNESSED` or `shipped: false`, the work is not done regardless of how\nconfidently the agent narrated it — send it back.\n\n## Examples\n\n### Example 1: gate an agent's \"I fixed the bug\" claim\n\n```bash\n# The agent committed and said it's fixed. Check the diff backs the claim.\n# commit-audit --json returns an array, so read the first element's verdict:\ndos commit-audit --workspace . HEAD --json | jq -r '.[0].verdict'\n# OK                -> the change is of the claimed kind; now run the tests\n# CLAIM_UNWITNESSED -> the commit doesn't do what it says; reject\n```\n\n### Example 2: confirm a feature phase shipped before closing a ticket\n\n```bash\ndos verify --workspace . AUTH AUTH2 --json --no-ci\n# shipped: true, source: registry|grep-artifact -> non-forgeable; safe to close\n# shipped: true, source: grep-subject|grep       -> forgeable subject\u002Fbody match;\n#   shipped-per-the-subject only -> corroborate with commit-audit before closing\n# shipped: false, source: none -> no evidence; keep the ticket open\n```\n\n## Best Practices\n\n- ✅ Run `dos commit-audit HEAD` immediately after every agent commit.\n- ✅ Treat `source: none` \u002F `CLAIM_UNWITNESSED` as \"not done\", not as a tool error.\n- ✅ Close a claim on a **non-forgeable** `source` (`registry`, `grep-artifact`).\n  Treat `grep-subject` \u002F bare `grep` as forgeable (an agent can write the subject\n  text) — corroborate before closing.\n- ✅ Keep the test suite as the separate correctness gate — this skill checks shipping, not correctness.\n- ❌ Don't accept a \"done\" because the agent's prose was confident.\n- ❌ Don't use this to replace code review or testing.\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- It checks whether a claimed change *shipped* \u002F matches its diff — not whether the code is *correct*.\n- `dos verify` reads git history; in a repo with no commits there is nothing to witness (it will honestly report `source: none`).\n- Stop and ask for clarification if required inputs (a git repo, the `dos` CLI) are missing.\n\n## Security & Safety Notes\n\n- This skill runs shell commands: installing `dos-kernel` into an isolated\n  virtualenv and the read-only\n  `dos` verbs (`dos commit-audit`, `dos verify`). These verbs never **mutate**\n  the repo or push. `dos commit-audit` only reads git history and the working\n  tree (no network). `dos verify` is also git-only **unless** the workspace has\n  wired a CI oracle (`[verify] non_git_oracle` in its `dos.toml`), in which case\n  it may shell a network check (e.g. `gh api`) for the verdict — pass `--no-ci`\n  (as the examples above do) to force the git-only path and guarantee no network.\n- `pip install dos-kernel` installs from PyPI. The distribution name is\n  `dos-kernel` (the bare `dos` on PyPI is an unrelated package — do not install\n  it). Pin a reviewed version; do not install an unpinned latest release into a\n  global Python environment.\n- Run in the repository you intend to adjudicate; the `--workspace .` argument\n  scopes every verdict to that repo.\n\n## Common Pitfalls\n\n- **Problem:** `dos verify` returns `source: none` and it looks like a failure.\n  **Solution:** That is the honest \"no evidence\" verdict — it means the phase has\n  no ship commit, so the claim is unproven. Re-stamp the real commit or keep the\n  task open.\n- **Problem:** Installing the wrong package.\n  **Solution:** The PyPI name is `dos-kernel`, not `dos`.\n\n## Related Skills\n\n- The upstream DOS reference screenplays (`dos-witness-claim`, `dos-goal-gate`)\n  in `anthony-chaudhary\u002Fdos-kernel` cover the multi-agent fan-out and\n  self-stopping-agent variants of this same witness discipline.\n",{"name":5,"risk":29,"tags":48,"tools":50,"author":53,"plugin":54,"source":31,"license":14,"category":61,"date_added":62,"description":7,"source_repo":63,"source_type":31,"license_source":64},[38,39,49,32,28],"ai-agents",[51,52,41],"claude","cursor","anthony-chaudhary",{"setup":55,"targets":59},{"docs":56,"type":57,"summary":58},"SKILL.md","manual","Setup installs and executes an external PyPI CLI; keep out of plugin-safe bundles.",{"codex":60,"claude":60},"blocked","quality","2026-06-12","anthony-chaudhary\u002Fdos-kernel","https:\u002F\u002Fgithub.com\u002Fanthony-chaudhary\u002Fdos-kernel\u002Fblob\u002Fmaster\u002FLICENSE","main","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fdos-verify-done-claims","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill dos-verify-done-claims",{"tool":77,"command":78},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill dos-verify-done-claims",{"tool":80,"command":81},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill dos-verify-done-claims","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fdos-verify-done-claims\u002FSKILL.md",true,[],[86,110,133,157,184,208],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":95,"publishedAt":43},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[96,32,97,98,99,38,88,100,101,102,103,104,31,65,105,29,106,107,108,109],"ZeRO","zero trust","architecture","assessment","segmentation","devops-security","access","configure","only","active","scope","scripts","relevant","implementing",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":43},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[117,118,119,120,34,121,122,123,124,125,126,127,128,104,129,31,130,131,29,132],"delegate","zcode","zcode delegate","review","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":43},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[140,141,142,42,143,144,145,146,147,148,149,150,151,31,65,152,153,154,155,156],"transcript","youtube transcript","youtube","github","codex","research","license","https","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":174,"publishedAt":43},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[163,166,169],{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":167,"categoryName":168,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":170,"categoryName":171,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[140,141,142,175,42,41,143,144,146,176,177,178,179,149,180,31,65,181,182,183],"youtube transcript skills","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":194,"publishedAt":43},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[190,193],{"categoryNo":191,"categoryName":192,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":167,"categoryName":168,"taxonomyType":20,"taxonomyTypeDesc":21},[142,195,196,34,42,197,198,199,200,146,178,201,202,203,204,65,205,152,206,207],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":215,"publishedAt":43},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[214],{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},[216,142,217,218,42,41,176,219,220,177,178,179,149,221,180,31,65,181,222,155],"youtube full","full","google","server","dlp","credits","automatic"]