[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79J02RSDB93T2EZ9ECSJVT9":3,"skill-same:01M79J02RSDB93T2EZ9ECSJVT9":56},{"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":6,"updatedAt":31,"install":32,"resources":45},"01M79J02RSDB93T2EZ9ECSJVT9","explainer-reading-site-generate-base",null,"Internal build orchestrator invoked by book and paper site consumers. Turns reports into semantic pages, a landing page, assets, and navigation using the consumer's ordering profile and vocabulary.","choplin\u002Fexplainer-studio","choplin","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F342798?v=4","01M79HWTA907677Q3R963A4PVZ","Akihiro Okuno","01M79HWTB0VNAN238405SZ6ESK",1,"MIT","https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fexplainer\u002Fexplainer-reading-site-generate-base\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: explainer-reading-site-generate-base\ndescription: \"Internal build orchestrator invoked by book and paper site consumers. Turns reports into semantic pages, a landing page, assets, and navigation using the consumer's ordering profile and vocabulary.\"\nuser-invocable: false\n---\n\n# explainer-reading-site-generate-base — shared build pipeline\n\nThis skill owns the pipeline shared by [[book-explainer-generate-site]],\n[[paper-explainer-generate-site]], and future consumers that turn a work directory's\n`reports\u002F` into a reading-guide site.\n\nThe consumer owns only:\n\n- its trigger;\n- an ordered `[{ slug, kicker }]` page profile;\n- the absolute path to its canonical source-structure artifact;\n- its locator kind (`pdf-page` or `epub`) and EPUB locator map when applicable;\n- its optional original-media source and destination;\n- three landing-page nouns: guide kicker, cards-section heading, and count-chip unit.\n\nThis base owns scaffold, semantic authoring, the single generator build, landing page,\nnavigation manifest, verification, and deployment handoff. The output is\n`\u003CWORK_DIR>\u002Fsite\u002F`; deployment is a separate\n[[explainer-reading-site-deploy]] action.\n\n## Required reading by phase\n\n- **Before resolving pages or adding a consumer:** read\n  [`references\u002Fprofile-contract.md`](references\u002Fprofile-contract.md) completely.\n  It defines the ordered-list invariants, current PDF\u002FPaper profiles, and landing\n  vocabulary.\n- **At the start of Phase 2:** read\n  [`references\u002Fauthoring-and-verification.md`](references\u002Fauthoring-and-verification.md)\n  completely. It contains per-page delegation inputs, landing source notation,\n  nav-manifest format, gotchas, and the full success checklist.\n\nDo not read the second reference during Phase 1 inventory unless you need to inspect\nthe later output contract.\n\n## Preconditions and ownership\n\nThe input is `\u003CWORK_DIR>` with at least one `reports\u002F*.md` and the consumer's\ncanonical source-structure artifact. `audio\u002F`, PDF `ocr\u002Ffigures\u002F`, and EPUB\n`epub\u002Fmedia\u002F` are optional. If\nreports or the structure artifact are missing, stop and ask the consumer's\nsummarize skill to run first. Audio is produced through\n[[explainer-audio-guide]], which owns the whole audio phase chain.\n\nBoth dependency skills must be installed:\n\n- [[explainer-html-docs]] supplies `base.css`, `base.js`, the deterministic\n  semantic-Markdown generator, and the `reading-nav` component.\n- [[explainer-reading-site-library-base]] supplies the shared content layer\n  `reading-site.css`.\n\nIf either dependency is missing, stop and report it; never guess a path or fork the\nassets.\n\nPages are **authored, not converted**, and are written as semantic Markdown. The\n[[explainer-reading-site-page]] procedure restructures each report for web reading.\nThe generator then owns head markup, theme boot, asset order, classes, table wrapping,\nand figure-path rewriting. A 1:1 Markdown conversion or hand-written HTML is not the\ndeliverable.\n\n## Pipeline\n\nRun these phases in order. Do not build before every semantic source, including the\nlanding, is ready.\n\n### Phase 1 — Scaffold\n\n1. Inventory `reports\u002F*.md`, audio files (`.m4a`, `.mp3`, `.wav`), PDF\n   `ocr\u002Ffigures\u002F*`, and EPUB `epub\u002Fmedia\u002F*` as applicable.\n2. Read `references\u002Fprofile-contract.md` and resolve the consumer profile into one\n   deterministic ordered `[{ slug, kicker }]` list. Fix it now; it is the source of\n   truth for cards and navigation.\n3. Resolve the consumer's canonical source-structure artifact and verify it exists.\n   Keep its absolute path as the source-topology authority for every page worker\n   and the fan-in sweep; never infer source structure from authored pages.\n4. If `site\u002F` already exists, ask before clearing `site\u002F` and `src\u002F`. Recommend a\n   clean rebuild so removed reports\u002Faudio cannot remain as publishable orphans. If\n   the user declines, build over the existing tree and warn about stale files.\n5. Create `src\u002F` and `site\u002Faudio\u002F`; copy all source audio into `site\u002Faudio\u002F`.\n   `src\u002F` and `site\u002F` are reproducible and disposable. Never hand-edit `site\u002F`.\n6. If `ocr\u002Ffigures\u002F` exists, copy the whole directory to `site\u002Ffigures\u002F`. Copy every\n   crop because page authors run independently; the generator rewrites report paths\n   from `..\u002Focr\u002Ffigures\u002F...` to `figures\u002F...`.\n7. If the consumer supplied `epub\u002Fmedia\u002F`, copy it recursively to `site\u002Fmedia\u002F`.\n   The generator rewrites `..\u002Fepub\u002Fmedia\u002F...` to `media\u002F...`; keep original bytes\n   and relative manifest paths.\n\nDo not copy design assets in this phase. The generator copies them in Phase 3.\n\n### Phase 2 — Author all semantic sources\n\nRead `references\u002Fauthoring-and-verification.md` completely now.\n\n1. Apply [[explainer-reading-site-page]] once per report, in parallel when the host\n   supports isolated subagents. Each worker writes `src\u002F\u003Cslug>.md` and returns only\n   the source path, title, and a 2–3 line card summary.\n2. Pass each worker only the absolute report\u002Foutput paths, the absolute canonical\n   source-structure path, locator kind and EPUB map when applicable, site title,\n   profile kicker, source-media availability, matching audio filename or `none`,\n   and the exact canonical site-wide authoring\n   conventions from `references\u002Fauthoring-and-verification.md`. The conventions\n   are an explicit dispatch input because isolated workers cannot infer them from\n   sibling output.\n3. Do not have workers author head markup, presentation-only classes outside the\n   page skill's semantic vocabulary, figure rewrites, or prev\u002Fnext links. Runtime\n   navigation comes from the manifest written in Phase 3.\n4. Compose `src\u002Findex.md` inline from worker replies and the consumer vocabulary.\n   Do not re-read report sources for cards. The landing is semantic Markdown and is\n   built like every other page.\n5. Apply [[explainer-reading-site-consistency-sweep]] to **every** `src\u002F*.md` at\n   once, including the landing. Pass the fixed profile and the same canonical\n   conventions used for page dispatch, the canonical source-structure path, plus\n   the site title and consumer landing vocabulary. Apply its targeted findings to\n   `src\u002F` and rerun it until clean. This fan-in gate catches source-attribution\n   errors, required markup omissions, and cross-page structural drift that are\n   valid Markdown and therefore invisible to the generator. Do not begin Phase 3\n   while findings remain.\n6. Run any deterministic locator validator supplied by the consumer. The EPUB\n   consumer rejects unknown canonical locators here before Pandoc; PDF and paper\n   consumers need no extra command because `.p` is self-validating.\n\n### Phase 3 — Build once, then write navigation data\n\nBuild every `src\u002F*.md` in one pass:\n\n```bash\nexplainer-html-docs\u002Fscripts\u002Fbuild-site.sh \u003CWORK_DIR>\u002Fsrc \u003CWORK_DIR>\u002Fsite \\\n  --assets explainer-html-docs\u002Fassets \\\n  --context explainer-reading-site-library-base\u002Fassets \\\n  --filter explainer-reading-site-library-base\u002Ffilters\u002Freading-site.lua \\\n  --component reading-nav\n```\n\nResolve dependency directories as sibling skills under the installed skills root.\nThe command builds `src\u002Findex.md` and every report source, and copies `base.css`,\n`base.js`, `reading-site.css`, `reading-nav.css`, and `reading-nav.js`.\n\nA bad source must fail loudly. Fix the named source and rerun the build; do not bypass\nunknown variants or missing player sources.\n\nAfter the build, write `site\u002Fassets\u002Fnav-manifest.js` from the Phase 1 order and Phase\n2 titles. It assigns `window.__HTMLDOCS_NAV`; include every report page exactly once\nand omit the landing. This generated data is the only page-order source. Never author\nneighbor links into individual pages.\n\n### Phase 4 — Verify and hand off\n\nApply every item in the success checklist in\n`references\u002Fauthoring-and-verification.md`. Do not claim success from a build command\nalone.\n\nThen tell the user the site is ready under `\u003CWORK_DIR>\u002Fsite\u002F` and offer\n[[explainer-reading-site-deploy]]. If the shared library has never been deployed,\n[[explainer-reading-site-initialize]] must run first. Never deploy from this skill;\nthe user reviews the built artifact before it goes public.\n\n## Core invariants\n\n- `overview` is first and is the landing hero CTA.\n- Every existing report appears exactly once in a deterministic order and has a\n  non-empty kicker.\n- Reports are not color-coded by chapter, section, or perspective.\n- `src\u002F` contains semantic Markdown; `site\u002F` contains generated output. Source\n  and editorial body headings use distinct structure-provenance classes.\n- Source-derived headings match the consumer's canonical source-structure\n  artifact; editorial headings are visibly attributed in both the article and TOC.\n- One `explainer-html-docs` build produces the landing and all report pages.\n- Every source-PDF page reference in prose uses the canonical `.p` form, and no\n  page anchor appears in a heading.\n- Every EPUB source reference uses `.source-locator` with a canonical\n  `data-locator` present in the consumer's map, and no fabricated `.p` appears.\n- The whole-source consistency sweep passes after parallel authoring and before the\n  one site build.\n- `nav-manifest.js` is the only page-navigation source.\n- Shared assets are reused through `--assets`, `--context`, and\n  `--component reading-nav`; consumers do not fork them.\n- The site stays readable with JavaScript disabled and contains every local figure\n  and audio file it references.\n","# explainer-reading-site-generate-base — shared build pipeline\n\nThis skill owns the pipeline shared by [[book-explainer-generate-site]],\n[[paper-explainer-generate-site]], and future consumers that turn a work directory's\n`reports\u002F` into a reading-guide site.\n\nThe consumer owns only:\n\n- its trigger;\n- an ordered `[{ slug, kicker }]` page profile;\n- the absolute path to its canonical source-structure artifact;\n- its locator kind (`pdf-page` or `epub`) and EPUB locator map when applicable;\n- its optional original-media source and destination;\n- three landing-page nouns: guide kicker, cards-section heading, and count-chip unit.\n\nThis base owns scaffold, semantic authoring, the single generator build, landing page,\nnavigation manifest, verification, and deployment handoff. The output is\n`\u003CWORK_DIR>\u002Fsite\u002F`; deployment is a separate\n[[explainer-reading-site-deploy]] action.\n\n## Required reading by phase\n\n- **Before resolving pages or adding a consumer:** read\n  [`references\u002Fprofile-contract.md`](references\u002Fprofile-contract.md) completely.\n  It defines the ordered-list invariants, current PDF\u002FPaper profiles, and landing\n  vocabulary.\n- **At the start of Phase 2:** read\n  [`references\u002Fauthoring-and-verification.md`](references\u002Fauthoring-and-verification.md)\n  completely. It contains per-page delegation inputs, landing source notation,\n  nav-manifest format, gotchas, and the full success checklist.\n\nDo not read the second reference during Phase 1 inventory unless you need to inspect\nthe later output contract.\n\n## Preconditions and ownership\n\nThe input is `\u003CWORK_DIR>` with at least one `reports\u002F*.md` and the consumer's\ncanonical source-structure artifact. `audio\u002F`, PDF `ocr\u002Ffigures\u002F`, and EPUB\n`epub\u002Fmedia\u002F` are optional. If\nreports or the structure artifact are missing, stop and ask the consumer's\nsummarize skill to run first. Audio is produced through\n[[explainer-audio-guide]], which owns the whole audio phase chain.\n\nBoth dependency skills must be installed:\n\n- [[explainer-html-docs]] supplies `base.css`, `base.js`, the deterministic\n  semantic-Markdown generator, and the `reading-nav` component.\n- [[explainer-reading-site-library-base]] supplies the shared content layer\n  `reading-site.css`.\n\nIf either dependency is missing, stop and report it; never guess a path or fork the\nassets.\n\nPages are **authored, not converted**, and are written as semantic Markdown. The\n[[explainer-reading-site-page]] procedure restructures each report for web reading.\nThe generator then owns head markup, theme boot, asset order, classes, table wrapping,\nand figure-path rewriting. A 1:1 Markdown conversion or hand-written HTML is not the\ndeliverable.\n\n## Pipeline\n\nRun these phases in order. Do not build before every semantic source, including the\nlanding, is ready.\n\n### Phase 1 — Scaffold\n\n1. Inventory `reports\u002F*.md`, audio files (`.m4a`, `.mp3`, `.wav`), PDF\n   `ocr\u002Ffigures\u002F*`, and EPUB `epub\u002Fmedia\u002F*` as applicable.\n2. Read `references\u002Fprofile-contract.md` and resolve the consumer profile into one\n   deterministic ordered `[{ slug, kicker }]` list. Fix it now; it is the source of\n   truth for cards and navigation.\n3. Resolve the consumer's canonical source-structure artifact and verify it exists.\n   Keep its absolute path as the source-topology authority for every page worker\n   and the fan-in sweep; never infer source structure from authored pages.\n4. If `site\u002F` already exists, ask before clearing `site\u002F` and `src\u002F`. Recommend a\n   clean rebuild so removed reports\u002Faudio cannot remain as publishable orphans. If\n   the user declines, build over the existing tree and warn about stale files.\n5. Create `src\u002F` and `site\u002Faudio\u002F`; copy all source audio into `site\u002Faudio\u002F`.\n   `src\u002F` and `site\u002F` are reproducible and disposable. Never hand-edit `site\u002F`.\n6. If `ocr\u002Ffigures\u002F` exists, copy the whole directory to `site\u002Ffigures\u002F`. Copy every\n   crop because page authors run independently; the generator rewrites report paths\n   from `..\u002Focr\u002Ffigures\u002F...` to `figures\u002F...`.\n7. If the consumer supplied `epub\u002Fmedia\u002F`, copy it recursively to `site\u002Fmedia\u002F`.\n   The generator rewrites `..\u002Fepub\u002Fmedia\u002F...` to `media\u002F...`; keep original bytes\n   and relative manifest paths.\n\nDo not copy design assets in this phase. The generator copies them in Phase 3.\n\n### Phase 2 — Author all semantic sources\n\nRead `references\u002Fauthoring-and-verification.md` completely now.\n\n1. Apply [[explainer-reading-site-page]] once per report, in parallel when the host\n   supports isolated subagents. Each worker writes `src\u002F\u003Cslug>.md` and returns only\n   the source path, title, and a 2–3 line card summary.\n2. Pass each worker only the absolute report\u002Foutput paths, the absolute canonical\n   source-structure path, locator kind and EPUB map when applicable, site title,\n   profile kicker, source-media availability, matching audio filename or `none`,\n   and the exact canonical site-wide authoring\n   conventions from `references\u002Fauthoring-and-verification.md`. The conventions\n   are an explicit dispatch input because isolated workers cannot infer them from\n   sibling output.\n3. Do not have workers author head markup, presentation-only classes outside the\n   page skill's semantic vocabulary, figure rewrites, or prev\u002Fnext links. Runtime\n   navigation comes from the manifest written in Phase 3.\n4. Compose `src\u002Findex.md` inline from worker replies and the consumer vocabulary.\n   Do not re-read report sources for cards. The landing is semantic Markdown and is\n   built like every other page.\n5. Apply [[explainer-reading-site-consistency-sweep]] to **every** `src\u002F*.md` at\n   once, including the landing. Pass the fixed profile and the same canonical\n   conventions used for page dispatch, the canonical source-structure path, plus\n   the site title and consumer landing vocabulary. Apply its targeted findings to\n   `src\u002F` and rerun it until clean. This fan-in gate catches source-attribution\n   errors, required markup omissions, and cross-page structural drift that are\n   valid Markdown and therefore invisible to the generator. Do not begin Phase 3\n   while findings remain.\n6. Run any deterministic locator validator supplied by the consumer. The EPUB\n   consumer rejects unknown canonical locators here before Pandoc; PDF and paper\n   consumers need no extra command because `.p` is self-validating.\n\n### Phase 3 — Build once, then write navigation data\n\nBuild every `src\u002F*.md` in one pass:\n\n```bash\nexplainer-html-docs\u002Fscripts\u002Fbuild-site.sh \u003CWORK_DIR>\u002Fsrc \u003CWORK_DIR>\u002Fsite \\\n  --assets explainer-html-docs\u002Fassets \\\n  --context explainer-reading-site-library-base\u002Fassets \\\n  --filter explainer-reading-site-library-base\u002Ffilters\u002Freading-site.lua \\\n  --component reading-nav\n```\n\nResolve dependency directories as sibling skills under the installed skills root.\nThe command builds `src\u002Findex.md` and every report source, and copies `base.css`,\n`base.js`, `reading-site.css`, `reading-nav.css`, and `reading-nav.js`.\n\nA bad source must fail loudly. Fix the named source and rerun the build; do not bypass\nunknown variants or missing player sources.\n\nAfter the build, write `site\u002Fassets\u002Fnav-manifest.js` from the Phase 1 order and Phase\n2 titles. It assigns `window.__HTMLDOCS_NAV`; include every report page exactly once\nand omit the landing. This generated data is the only page-order source. Never author\nneighbor links into individual pages.\n\n### Phase 4 — Verify and hand off\n\nApply every item in the success checklist in\n`references\u002Fauthoring-and-verification.md`. Do not claim success from a build command\nalone.\n\nThen tell the user the site is ready under `\u003CWORK_DIR>\u002Fsite\u002F` and offer\n[[explainer-reading-site-deploy]]. If the shared library has never been deployed,\n[[explainer-reading-site-initialize]] must run first. Never deploy from this skill;\nthe user reviews the built artifact before it goes public.\n\n## Core invariants\n\n- `overview` is first and is the landing hero CTA.\n- Every existing report appears exactly once in a deterministic order and has a\n  non-empty kicker.\n- Reports are not color-coded by chapter, section, or perspective.\n- `src\u002F` contains semantic Markdown; `site\u002F` contains generated output. Source\n  and editorial body headings use distinct structure-provenance classes.\n- Source-derived headings match the consumer's canonical source-structure\n  artifact; editorial headings are visibly attributed in both the article and TOC.\n- One `explainer-html-docs` build produces the landing and all report pages.\n- Every source-PDF page reference in prose uses the canonical `.p` form, and no\n  page anchor appears in a heading.\n- Every EPUB source reference uses `.source-locator` with a canonical\n  `data-locator` present in the consumer's map, and no fabricated `.p` appears.\n- The whole-source consistency sweep passes after parallel authoring and before the\n  one site build.\n- `nav-manifest.js` is the only page-navigation source.\n- Shared assets are reused through `--assets`, `--context`, and\n  `--component reading-nav`; consumers do not fork them.\n- The site stays readable with JavaScript disabled and contains every local figure\n  and audio file it references.\n",{"name":5,"description":7,"user-invocable":20},"main","08b762ef2ded20d4feadbe6fb7bfdd28747b0848","skills\u002Fexplainer\u002Fexplainer-reading-site-generate-base",0,"https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio","https:\u002F\u002Fgithub.com\u002Fchoplin","http:\u002F\u002Fwww.chopl.in\u002F","2026-10-27 17:11:10",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add choplin\u002Fexplainer-studio --skill explainer-reading-site-generate-base",{"tool":38,"command":39},"bunx","bunx skills add choplin\u002Fexplainer-studio --skill explainer-reading-site-generate-base",{"tool":41,"command":42},"pnpm","pnpm dlx skills add choplin\u002Fexplainer-studio --skill explainer-reading-site-generate-base","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fexplainer\u002Fexplainer-reading-site-generate-base\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fauthoring-and-verification.md","REFERENCE","参考文档",10482,"https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fexplainer\u002Fexplainer-reading-site-generate-base\u002Freferences\u002Fauthoring-and-verification.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fprofile-contract.md",3207,"https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fexplainer\u002Fexplainer-reading-site-generate-base\u002Freferences\u002Fprofile-contract.md",[57,63,70,77,84,91],{"skillNo":58,"name":59,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M79J25VYQ91K75R5HNDYYV4Z","invalid-skill-frontmatter","https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finvalid-skill-frontmatter\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M79J1ZWAX4EYVXPKTMB2WBMG","pdf-explainer-summarize","Digest a book, manual, or other long non-paper PDF into a source-anchored Markdown overview. Use when the requested deliverable is only a report, digest, or summary. Use paper-explainer-summarize for academic papers, direct reading for short PDFs, and book-explainer for coordinated reports, audio, site, rebuild, or resume.","https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fpdf-explainer\u002Fpdf-explainer-summarize\u002FSKILL.md",[],[],{"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},"01M79J1WEQW2GT78X92RMFY1AF","pdf-explainer-pdf-stitch","Internal Phase 2 worker invoked once by pdf-explainer-summarize after chunk extraction. Reconciles sections across chunk boundaries, deduplicates the material, and writes the canonical structural spine and outline.","https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fpdf-explainer\u002Fpdf-explainer-pdf-stitch\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},"01M79J1RZTE0VSWAJ26BYSPDD9","pdf-explainer-pdf-extract","Internal Phase 1 worker invoked by pdf-explainer-summarize once per page chunk. Reads the chunk visually or from a faithful text layer and writes structured source material with a verbatim heading stream, not a finished report.","https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fpdf-explainer\u002Fpdf-explainer-pdf-extract\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},"01M79J1NVVQY4XP1BQAEJJ4A23","pdf-explainer-pdf-detail","Internal per-chapter worker invoked by book-explainer for PDF input. Re-read one resolved chapter span visually or from a faithful text layer and write a standalone detail report with [pNN] source anchors.","https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fpdf-explainer\u002Fpdf-explainer-pdf-detail\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},"01M79J1JQM36YS9WVXFPFJHWC7","pdf-explainer-generate-site","Compatibility entry point for requesting a local PDF reading site from an existing work directory. Route through book-explainer so Artifact reconciliation and Planning still occur.","https:\u002F\u002Fgithub.com\u002Fchoplin\u002Fexplainer-studio\u002Fblob\u002Fmain\u002Fskills\u002Fpdf-explainer\u002Fpdf-explainer-generate-site\u002FSKILL.md",[],[]]