[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PZ1XVQHPF8MFPDHZZXEXFE":3,"skill-same:01M6PZ1XVQHPF8MFPDHZZXEXFE":79},{"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":25,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":31,"commitSha":60,"skillDirectory":61,"forksCount":13,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M6PZ1XVQHPF8MFPDHZZXEXFE","slideops",null,"Turn a repository into a cited HTML slide deck and detect the day it drifts from the code. Citations record file, lines, and hash; a stdlib check reports CURRENT, MOVED, or CHANGED.","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\u002Fslideops\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",[5,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"deck","docs-as-code","critical","as","drift","main","community","reports","opencode","cli","html","slides","drift-detection","Citations","repository","code","presentations","documentation","copilot","2026-11-10 10:12:30",false,"---\nname: slideops\ndescription: \"Turn a repository into a cited HTML slide deck and detect the day it drifts from the code. Citations record file, lines, and hash; a stdlib check reports CURRENT, MOVED, or CHANGED.\"\ncategory: content\nrisk: critical\nsource: community\nsource_repo: glukicov\u002Fslideops\nsource_type: community\ndate_added: \"2026-08-31\"\nauthor: glukicov\ntags: [slides, presentations, documentation, docs-as-code, drift-detection, citations, html]\ntools: [claude-code, codex-cli, copilot, opencode]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fglukicov\u002Fslideops\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# SlideOps: slides from a repo, that tell you when they go stale\n\n> **Catalog copy, frozen at v1.0.0.** The canonical source is\n> [glukicov\u002Fslideops](https:\u002F\u002Fgithub.com\u002Fglukicov\u002Fslideops), which also carries the deck\n> template, the two citation scripts, the reference docs, and the companion\n> `slides-to-pdf` skill. Install from there; this page summarizes the workflow.\n\n## Overview\n\nSlideOps has two jobs, and the second one is the point. **Build**: turn a repository into\na single self-contained HTML slide deck whose every claim came from the code, not from a\nmodel's impression of the code. **Keep in sync**: make that deck able to prove, months\nlater, whether it still matches the repository.\n\nThe mechanism joining them is a citation. Every quoted snippet records the file, the line\nrange, and a hash of those source lines at build time, and the deck records the commit it\nwas built from. \"Are these slides still accurate?\" becomes a command instead of a\nre-read: a standard-library Python script diffs each citation against the current code\nand reports `CURRENT`, `MOVED`, `CHANGED`, or `MISSING`. No model, no network, no tokens,\nmilliseconds to run.\n\n## When to Use This Skill\n\n- Use when the user asks for slides, a slide deck, or a presentation about a code\n  repository, one of its subsystems, a feature, or its recent changes: \"make slides\",\n  \"overview deck\", \"team update slides\", \"HTML slides for this repo\".\n- Use when the user asks whether an existing deck still matches the code, or wants one\n  rechecked, refreshed, or kept in sync: \"is this deck still accurate\", \"check the\n  slides against the code\", \"these docs are stale\".\n- Use when the user wants deck freshness wired into CI, a pull request check, or an\n  agent hook: \"fail the build when the deck stops matching the code\".\n- Do **not** use for slide decks about anything other than a codebase (a sales deck, a\n  lecture); the citation mechanism assumes a git repository as the source of truth.\n\n## How It Works\n\n### Step 1: Install from the canonical repo\n\nIn Claude Code, as a plugin (both skills, background updates):\n\n```text\n\u002Fplugin marketplace add glukicov\u002Fslideops\n\u002Fplugin install slideops@slideops\n```\n\nOr for Codex CLI, Copilot CLI, and OpenCode, one installer covers all of them:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fglukicov\u002Fslideops && cd slideops\ngit checkout ba43e89bc7936649be36a1796a62203f704f8c60   # the v1.0.0 release commit\n.\u002Finstall.sh\n```\n\nThe checkout pins the exact commit this catalog copy froze at, which is what a reader\ncan verify independently. (The canonical repo also blocks retargeting of `v*` tags with\nan active tag ruleset, but a SHA does not ask you to trust that.) `install.sh` symlinks\nthe two skills into `~\u002F.claude\u002Fskills` (read by Claude Code and OpenCode) and\n`~\u002F.agents\u002Fskills` (read by Codex CLI and Copilot CLI).\n\n### Step 2: Build a deck\n\nThe skill walks a fixed pipeline: a two-minute repo scan, one compact intake (topic,\naudience, length, theme, scope, extras), an outline checkpoint before any HTML is\nwritten, then slide-by-slide construction from a verified template. Every snippet is\ncited as it is written. Run the citation script from inside the repository being\npresented, via its installed path (an agent resolves `scripts\u002F` against the skill's own\ndirectory automatically; the paths below are for running it yourself after\n`install.sh`):\n\n```bash\npython3 ~\u002F.agents\u002Fskills\u002Fslideops\u002Fscripts\u002Fcite.py app\u002Fmain.py:40-58 --repo . --snippet   # prints data-src + data-sha256\npython3 ~\u002F.agents\u002Fskills\u002Fslideops\u002Fscripts\u002Fcite.py --stamp deck.html --repo .             # stamps the build commit\n```\n\n`--repo` always points at the repository the deck is about, never at the SlideOps\ncheckout.\n\nEvery slide is then rendered with headless Chrome and visually verified before the deck\nis considered done.\n\n### Step 3: Check it later, for free\n\nFrom inside the repository being presented, same path convention as Step 2:\n\n```bash\npython3 ~\u002F.agents\u002Fskills\u002Fslideops\u002Fscripts\u002Fcheck.py docs\u002Fslides\u002F --repo .\n```\n\nReal output, from the demo deck that ships with the skill:\n\n```text\nDeck: skill-demo.html\nBuilt: commit=179bbdb date=2026-08-28 repo=slideops\n\n  slide   9  THEMING        skills\u002Fslideops\u002Fassets\u002Ftemplate.html:22-45    CURRENT\n  slide  14  MERMAID        skills\u002Fslideops\u002Freferences\u002Fdiagrams.md:55-59  CURRENT\n\n2 current, 0 stale, 2 cited in total.\n```\n\n`MOVED` means only line numbers shifted (update two attributes, leave the prose).\n`CHANGED` means the quoted code was edited (read the diff, decide whether the slide's\nclaim survived). `MISSING` means the file is gone (the slide is probably obsolete). The\n`--json` flag emits a complete repair brief per stale citation, so an agent can fix\ndrift without re-reading the repository.\n\n## Examples\n\n### Example 1: New deck\n\n```text\nUser: make slides about this repo\nAgent: [scans repo, proposes 3-4 concrete topics with a \"why now\" each,\n        asks one compact intake, shows an outline, then builds and\n        visually verifies a cited HTML deck at docs\u002Fslides\u002F]\n```\n\n### Example 2: Freshness check in CI\n\n```bash\npython3 tools\u002Fslideops-check.py docs\u002Fslides\u002F --repo . --exit-zero   # report-only PR annotation\n```\n\nThe canonical repo's `references\u002Fautomation.md` has the PR-check workflow, advisory hook\nvariants, and a delegated-refresh recipe. `check.py` is one dependency-free file, meant\nto be vendored into the deck's own repo.\n\n## Best Practices\n\n- ✅ Cite with `cite.py`, never by hand: a hand-computed hash silently reports `CHANGED`\n  months later and nobody can tell whether the code moved or the build was sloppy.\n- ✅ Repair a drifted deck; do not rebuild it. Fix only the slides whose citations went\n  stale, then re-stamp.\n- ✅ Automate the check for evergreen decks (onboarding, architecture); leave snapshots\n  (sprint updates, conference talks) frozen deliberately.\n- ❌ Do not run `check.py` against a PDF export: citations live in the HTML, so the PDF\n  reports \"No citations found in this deck\".\n- ❌ Do not block every commit on the check. Report-only on pull requests first; a docs\n  gate on the fast path trains people to pass `--no-verify`.\n\n## Limitations\n\n- Needs a headless Chrome or Chromium binary (Playwright cache or system install) for\n  the visual verification pass, and Python 3 for the citation scripts.\n- Works offline except two opt-ins: Mermaid diagrams (a one-time `npx` download) and\n  brand-color extraction from a live style guide.\n- The check verifies quoted snippets against the code; it cannot verify prose claims\n  that cite nothing.\n- Drift detection assumes the deck and the code share a git repository.\n\n## Security & Safety Notes\n\n- Ask before cloning the upstream repository, running `install.sh`, creating skill\n  symlinks in the user's home directory, downloading an optional `npx` package, or\n  writing deck output. Show the exact pinned commit and destination paths first, and\n  preserve any existing skill entries instead of overwriting them silently.\n- The citation scripts are standard-library-only Python: no dependencies, no network,\n  no tokens.\n- The skill declares no `allowed-tools`, deliberately: the host agent's own permission\n  model stays in charge, and headless Chrome keeps its sandbox.\n- The skill carries an explicit confidentiality rule for deck content: never read or\n  quote secrets, keys, `.env` files, production logs, or customer data; redact internal\n  hostnames and identifiers; and finish with a redaction scan of the rendered slides,\n  because decks are documents that leave the repository.\n- File writes are limited to the deck output folder (default `docs\u002Fslides\u002F`) plus its\n  companion README.\n\n## Common Pitfalls\n\n- **Problem:** `check.py` on an exported PDF reports no citations.\n  **Solution:** Run it against the HTML deck; the PDF is a derived artifact from the\n  companion `slides-to-pdf` skill.\n- **Problem:** A freshly built deck already reports `CHANGED`.\n  **Solution:** That is a build defect, not a future problem: a snippet was quoted and\n  then edited, or a hash was hand-computed. Re-cite with `cite.py` before shipping.\n- **Problem:** Chrome is not found on the verification step.\n  **Solution:** The canonical repo's `references\u002Fverification.md` has the cross-platform\n  discovery recipe (Playwright cache first, then system installs).\n\n## Related Skills\n\n- `slides-to-pdf` (same canonical repo): screenshots every slide at 2x, prints a\n  page-per-slide PDF, and verifies the result by rendering the PDF back to images.\n- `@2slides-ppt-generator`: API-driven deck generation from text or documents; use it\n  when the source material is not a code repository.\n","# SlideOps: slides from a repo, that tell you when they go stale\n\n> **Catalog copy, frozen at v1.0.0.** The canonical source is\n> [glukicov\u002Fslideops](https:\u002F\u002Fgithub.com\u002Fglukicov\u002Fslideops), which also carries the deck\n> template, the two citation scripts, the reference docs, and the companion\n> `slides-to-pdf` skill. Install from there; this page summarizes the workflow.\n\n## Overview\n\nSlideOps has two jobs, and the second one is the point. **Build**: turn a repository into\na single self-contained HTML slide deck whose every claim came from the code, not from a\nmodel's impression of the code. **Keep in sync**: make that deck able to prove, months\nlater, whether it still matches the repository.\n\nThe mechanism joining them is a citation. Every quoted snippet records the file, the line\nrange, and a hash of those source lines at build time, and the deck records the commit it\nwas built from. \"Are these slides still accurate?\" becomes a command instead of a\nre-read: a standard-library Python script diffs each citation against the current code\nand reports `CURRENT`, `MOVED`, `CHANGED`, or `MISSING`. No model, no network, no tokens,\nmilliseconds to run.\n\n## When to Use This Skill\n\n- Use when the user asks for slides, a slide deck, or a presentation about a code\n  repository, one of its subsystems, a feature, or its recent changes: \"make slides\",\n  \"overview deck\", \"team update slides\", \"HTML slides for this repo\".\n- Use when the user asks whether an existing deck still matches the code, or wants one\n  rechecked, refreshed, or kept in sync: \"is this deck still accurate\", \"check the\n  slides against the code\", \"these docs are stale\".\n- Use when the user wants deck freshness wired into CI, a pull request check, or an\n  agent hook: \"fail the build when the deck stops matching the code\".\n- Do **not** use for slide decks about anything other than a codebase (a sales deck, a\n  lecture); the citation mechanism assumes a git repository as the source of truth.\n\n## How It Works\n\n### Step 1: Install from the canonical repo\n\nIn Claude Code, as a plugin (both skills, background updates):\n\n```text\n\u002Fplugin marketplace add glukicov\u002Fslideops\n\u002Fplugin install slideops@slideops\n```\n\nOr for Codex CLI, Copilot CLI, and OpenCode, one installer covers all of them:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fglukicov\u002Fslideops && cd slideops\ngit checkout ba43e89bc7936649be36a1796a62203f704f8c60   # the v1.0.0 release commit\n.\u002Finstall.sh\n```\n\nThe checkout pins the exact commit this catalog copy froze at, which is what a reader\ncan verify independently. (The canonical repo also blocks retargeting of `v*` tags with\nan active tag ruleset, but a SHA does not ask you to trust that.) `install.sh` symlinks\nthe two skills into `~\u002F.claude\u002Fskills` (read by Claude Code and OpenCode) and\n`~\u002F.agents\u002Fskills` (read by Codex CLI and Copilot CLI).\n\n### Step 2: Build a deck\n\nThe skill walks a fixed pipeline: a two-minute repo scan, one compact intake (topic,\naudience, length, theme, scope, extras), an outline checkpoint before any HTML is\nwritten, then slide-by-slide construction from a verified template. Every snippet is\ncited as it is written. Run the citation script from inside the repository being\npresented, via its installed path (an agent resolves `scripts\u002F` against the skill's own\ndirectory automatically; the paths below are for running it yourself after\n`install.sh`):\n\n```bash\npython3 ~\u002F.agents\u002Fskills\u002Fslideops\u002Fscripts\u002Fcite.py app\u002Fmain.py:40-58 --repo . --snippet   # prints data-src + data-sha256\npython3 ~\u002F.agents\u002Fskills\u002Fslideops\u002Fscripts\u002Fcite.py --stamp deck.html --repo .             # stamps the build commit\n```\n\n`--repo` always points at the repository the deck is about, never at the SlideOps\ncheckout.\n\nEvery slide is then rendered with headless Chrome and visually verified before the deck\nis considered done.\n\n### Step 3: Check it later, for free\n\nFrom inside the repository being presented, same path convention as Step 2:\n\n```bash\npython3 ~\u002F.agents\u002Fskills\u002Fslideops\u002Fscripts\u002Fcheck.py docs\u002Fslides\u002F --repo .\n```\n\nReal output, from the demo deck that ships with the skill:\n\n```text\nDeck: skill-demo.html\nBuilt: commit=179bbdb date=2026-08-28 repo=slideops\n\n  slide   9  THEMING        skills\u002Fslideops\u002Fassets\u002Ftemplate.html:22-45    CURRENT\n  slide  14  MERMAID        skills\u002Fslideops\u002Freferences\u002Fdiagrams.md:55-59  CURRENT\n\n2 current, 0 stale, 2 cited in total.\n```\n\n`MOVED` means only line numbers shifted (update two attributes, leave the prose).\n`CHANGED` means the quoted code was edited (read the diff, decide whether the slide's\nclaim survived). `MISSING` means the file is gone (the slide is probably obsolete). The\n`--json` flag emits a complete repair brief per stale citation, so an agent can fix\ndrift without re-reading the repository.\n\n## Examples\n\n### Example 1: New deck\n\n```text\nUser: make slides about this repo\nAgent: [scans repo, proposes 3-4 concrete topics with a \"why now\" each,\n        asks one compact intake, shows an outline, then builds and\n        visually verifies a cited HTML deck at docs\u002Fslides\u002F]\n```\n\n### Example 2: Freshness check in CI\n\n```bash\npython3 tools\u002Fslideops-check.py docs\u002Fslides\u002F --repo . --exit-zero   # report-only PR annotation\n```\n\nThe canonical repo's `references\u002Fautomation.md` has the PR-check workflow, advisory hook\nvariants, and a delegated-refresh recipe. `check.py` is one dependency-free file, meant\nto be vendored into the deck's own repo.\n\n## Best Practices\n\n- ✅ Cite with `cite.py`, never by hand: a hand-computed hash silently reports `CHANGED`\n  months later and nobody can tell whether the code moved or the build was sloppy.\n- ✅ Repair a drifted deck; do not rebuild it. Fix only the slides whose citations went\n  stale, then re-stamp.\n- ✅ Automate the check for evergreen decks (onboarding, architecture); leave snapshots\n  (sprint updates, conference talks) frozen deliberately.\n- ❌ Do not run `check.py` against a PDF export: citations live in the HTML, so the PDF\n  reports \"No citations found in this deck\".\n- ❌ Do not block every commit on the check. Report-only on pull requests first; a docs\n  gate on the fast path trains people to pass `--no-verify`.\n\n## Limitations\n\n- Needs a headless Chrome or Chromium binary (Playwright cache or system install) for\n  the visual verification pass, and Python 3 for the citation scripts.\n- Works offline except two opt-ins: Mermaid diagrams (a one-time `npx` download) and\n  brand-color extraction from a live style guide.\n- The check verifies quoted snippets against the code; it cannot verify prose claims\n  that cite nothing.\n- Drift detection assumes the deck and the code share a git repository.\n\n## Security & Safety Notes\n\n- Ask before cloning the upstream repository, running `install.sh`, creating skill\n  symlinks in the user's home directory, downloading an optional `npx` package, or\n  writing deck output. Show the exact pinned commit and destination paths first, and\n  preserve any existing skill entries instead of overwriting them silently.\n- The citation scripts are standard-library-only Python: no dependencies, no network,\n  no tokens.\n- The skill declares no `allowed-tools`, deliberately: the host agent's own permission\n  model stays in charge, and headless Chrome keeps its sandbox.\n- The skill carries an explicit confidentiality rule for deck content: never read or\n  quote secrets, keys, `.env` files, production logs, or customer data; redact internal\n  hostnames and identifiers; and finish with a redaction scan of the rendered slides,\n  because decks are documents that leave the repository.\n- File writes are limited to the deck output folder (default `docs\u002Fslides\u002F`) plus its\n  companion README.\n\n## Common Pitfalls\n\n- **Problem:** `check.py` on an exported PDF reports no citations.\n  **Solution:** Run it against the HTML deck; the PDF is a derived artifact from the\n  companion `slides-to-pdf` skill.\n- **Problem:** A freshly built deck already reports `CHANGED`.\n  **Solution:** That is a build defect, not a future problem: a snippet was quoted and\n  then edited, or a hash was hand-computed. Re-cite with `cite.py` before shipping.\n- **Problem:** Chrome is not found on the verification step.\n  **Solution:** The canonical repo's `references\u002Fverification.md` has the cross-platform\n  discovery recipe (Playwright cache first, then system installs).\n\n## Related Skills\n\n- `slides-to-pdf` (same canonical repo): screenshots every slide at 2x, prints a\n  page-per-slide PDF, and verifies the result by rendering the PDF back to images.\n- `@2slides-ppt-generator`: API-driven deck generation from text or documents; use it\n  when the source material is not a code repository.\n",{"name":5,"risk":28,"tags":50,"tools":52,"author":55,"source":32,"license":14,"category":56,"date_added":57,"description":7,"source_repo":58,"source_type":32,"license_source":59},[37,42,43,27,38,51,36],"citations",[53,54,44,34],"claude-code","codex-cli","glukicov","content","2026-08-31","glukicov\u002Fslideops","https:\u002F\u002Fgithub.com\u002Fglukicov\u002Fslideops\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fslideops","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":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill slideops",{"tool":71,"command":72},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill slideops",{"tool":74,"command":75},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill slideops","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\u002Fslideops\u002FSKILL.md",true,[],[80,106,129,154,182,202],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":89,"publishedAt":45},"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",[86],{"categoryNo":87,"categoryName":88,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[90,91,92,93,94,95,82,96,97,98,99,100,32,31,101,28,102,103,104,105],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","active","scope","scripts","relevant","implementing",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":45},"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",[],[113,114,115,116,35,117,118,119,120,121,122,123,124,100,125,32,126,127,28,128],"delegate","zcode","zcode delegate","review","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":45},"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",[],[136,137,138,139,140,141,142,143,144,145,146,147,148,32,31,149,150,151,152,153],"transcript","youtube transcript","youtube","safe","github","codex","research","license","https","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":171,"publishedAt":45},"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",[160,163,166],{"categoryNo":161,"categoryName":162,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":167,"categoryName":168,"taxonomyType":169,"taxonomyTypeDesc":170},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[136,137,138,172,139,173,140,141,143,174,175,176,177,146,178,32,31,179,180,181],"youtube transcript skills","gemini","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":190,"publishedAt":45},"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",[188,189],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},[138,191,192,35,139,193,194,195,41,143,176,196,37,197,198,31,199,149,200,201],"youtube notetaker","notetaker","workflow","official","notes","markdown","annotations","README","study","dair-academy","viewer",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":209,"publishedAt":45},"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",[208],{"categoryNo":161,"categoryName":162,"taxonomyType":20,"taxonomyTypeDesc":21},[210,138,211,212,139,173,174,213,214,175,176,177,146,215,178,32,31,179,216,152],"youtube full","full","google","server","dlp","credits","automatic"]