[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJ1GYBPK5C4KW4ZS99CSSH":3,"skill-same:01M6MJ1GYBPK5C4KW4ZS99CSSH":63},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6MJ1GYBPK5C4KW4ZS99CSSH","extracting-with-ocr",null,"Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzberg\u002Fskills\u002Fextracting-with-ocr\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"ocr","with","extracting","extracting with ocr","performance","tuning","text","use","embedded","images","language","pages","performance tuning","layer","when","2026-11-10 10:12:30",false,"---\nname: extracting-with-ocr\ndescription: Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.\n---\n\n# Extracting with OCR\n\nUse this when a document is image-based: scanned PDFs, photographed pages,\nscreenshots, JPEG\u002FPNG\u002FTIFF with text. Kreuzberg auto-OCRs raster images and\nauto-detects PDFs that lack a text layer. Force it on when extraction\nreturned empty\u002Fgarbled text from a PDF that \"looks\" textual.\n\n## When to force OCR\n\n- Extraction returned an empty `content` field, but the file opens visually.\n- The PDF text layer is junk (copy-paste from a viewer produces gibberish).\n- You want consistent output across mixed scanned + digital PDFs.\n\n```bash\nkreuzberg extract scan.pdf --force-ocr=true\nkreuzberg extract scan.pdf --ocr=true --ocr-language eng\n```\n\nIf a page has an unreliable text layer, `--force-ocr=true` re-rasterizes\nand runs OCR on every page.\n\n## Backends\n\nTesseract is the default and ships with the CLI — no extra install. Other\nbackends are opt-in:\n\n| Backend       | Flag                                  | Install                                          | Notes                                                          |\n| ------------- | ------------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- |\n| Tesseract     | `--ocr-backend tesseract` (default)   | bundled                                          | Best general-purpose, 100+ languages via tessdata.             |\n| PaddleOCR     | `--ocr-backend paddle-ocr`            | bundled (ONNX Runtime)                           | Strong on Asian scripts. Not available on WASM or Windows.     |\n| EasyOCR       | `--ocr-backend easyocr`               | Python binding (`pip install kreuzberg[easyocr]`)| Heavier model. CUDA accel via `easyocr_kwargs={\"gpu\": True}`.  |\n| VLM (vision)  | layout + a multimodal LLM via config  | configured per backend                           | Use when OCR fails on dense or handwritten layouts.            |\n\nPick Tesseract first. Switch only when accuracy is unacceptable.\n\n## Language packs\n\nTesseract uses ISO 639-2 codes. Default is `eng`. Combine with `+`:\n\n```bash\nkreuzberg extract menu.jpg --ocr=true --ocr-language \"eng+deu\"\nkreuzberg extract bilingual.pdf --ocr-language \"eng+jpn\"\nkreuzberg extract any.pdf --ocr-language all   # all installed packs\n```\n\nInstall missing packs at the OS level:\n\n```bash\n# macOS\nbrew install tesseract-lang\n\n# Debian\u002FUbuntu\nsudo apt install tesseract-ocr-deu tesseract-ocr-jpn tesseract-ocr-fra\n\n# Specific lang only\nsudo apt install tesseract-ocr-\u003Ciso639-2>\n```\n\nKreuzberg fails fast with a helpful error if you request a language pack\nthat is not installed. Read the error — it names the missing file.\n\n## Useful flags\n\n- `--ocr=true` — enable OCR (auto-enabled for images and scanned PDFs).\n- `--force-ocr=true` — OCR every page even if a text layer exists.\n- `--disable-ocr=true` — never OCR (extract embedded text only or fail).\n- `--ocr-language \u003Clang>` — single code or `+`-joined list, or `all`.\n- `--ocr-backend \u003Ctesseract|paddle-ocr|easyocr>` — pick backend.\n- `--ocr-auto-rotate=true` — pre-rotate via the auto-rotate model.\n- `--acceleration \u003Ccpu|coreml|cuda|tensorrt|auto>` — ONNX accelerator for\n  paddle-ocr \u002F auto-rotate \u002F layout models.\n\n## Performance tips\n\n- Cache is on by default. Repeated extraction of the same file + config is\n  instant. Do not pass `--no-cache=true` unless you have a reason.\n- For batch OCR, use `kreuzberg batch *.pdf --ocr=true` — internal worker\n  pool parallelizes across CPU cores. Cap with `--max-concurrent N` if\n  memory is tight.\n- Raise `--target-dpi` (default 300) only for low-resolution scans. Higher\n  DPI is slower; 200 is usually enough for printed text.\n- Enable `--ocr-auto-rotate=true` only when pages may be rotated; the\n  classifier adds latency.\n- On Apple Silicon, `--acceleration coreml` typically beats CPU for\n  paddle-ocr and layout detection.\n\n## Config file alternative\n\nLong flag chains belong in `kreuzberg.toml` — auto-discovered from cwd\nupward.\n\n```toml\nforce_ocr = true\noutput_format = \"markdown\"\n\n[ocr]\nbackend = \"tesseract\"\nlanguage = \"eng+deu\"\nauto_rotate = true\n```\n\nThen just run:\n\n```bash\nkreuzberg extract document.pdf\n```\n\n## Common failure modes\n\n- **\"missing tessdata\"** — install the language pack at OS level (see above).\n- **Empty content on a scanned PDF without `--force-ocr`** — the file has a\n  bogus zero-width text layer. Re-run with `--force-ocr=true`.\n- **OCR on a rotated page** — add `--ocr-auto-rotate=true` or pre-rotate.\n- **Garbled CJK output** — ensure the right language pack is installed and\n  passed via `--ocr-language`; consider `paddle-ocr` for Chinese\u002FJapanese.\n\nSee `references\u002Fcli-reference.md` and `references\u002Fconfiguration.md` in the\nsibling `kreuzberg` skill for the full flag and config schema.\n","# Extracting with OCR\n\nUse this when a document is image-based: scanned PDFs, photographed pages,\nscreenshots, JPEG\u002FPNG\u002FTIFF with text. Kreuzberg auto-OCRs raster images and\nauto-detects PDFs that lack a text layer. Force it on when extraction\nreturned empty\u002Fgarbled text from a PDF that \"looks\" textual.\n\n## When to force OCR\n\n- Extraction returned an empty `content` field, but the file opens visually.\n- The PDF text layer is junk (copy-paste from a viewer produces gibberish).\n- You want consistent output across mixed scanned + digital PDFs.\n\n```bash\nkreuzberg extract scan.pdf --force-ocr=true\nkreuzberg extract scan.pdf --ocr=true --ocr-language eng\n```\n\nIf a page has an unreliable text layer, `--force-ocr=true` re-rasterizes\nand runs OCR on every page.\n\n## Backends\n\nTesseract is the default and ships with the CLI — no extra install. Other\nbackends are opt-in:\n\n| Backend       | Flag                                  | Install                                          | Notes                                                          |\n| ------------- | ------------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- |\n| Tesseract     | `--ocr-backend tesseract` (default)   | bundled                                          | Best general-purpose, 100+ languages via tessdata.             |\n| PaddleOCR     | `--ocr-backend paddle-ocr`            | bundled (ONNX Runtime)                           | Strong on Asian scripts. Not available on WASM or Windows.     |\n| EasyOCR       | `--ocr-backend easyocr`               | Python binding (`pip install kreuzberg[easyocr]`)| Heavier model. CUDA accel via `easyocr_kwargs={\"gpu\": True}`.  |\n| VLM (vision)  | layout + a multimodal LLM via config  | configured per backend                           | Use when OCR fails on dense or handwritten layouts.            |\n\nPick Tesseract first. Switch only when accuracy is unacceptable.\n\n## Language packs\n\nTesseract uses ISO 639-2 codes. Default is `eng`. Combine with `+`:\n\n```bash\nkreuzberg extract menu.jpg --ocr=true --ocr-language \"eng+deu\"\nkreuzberg extract bilingual.pdf --ocr-language \"eng+jpn\"\nkreuzberg extract any.pdf --ocr-language all   # all installed packs\n```\n\nInstall missing packs at the OS level:\n\n```bash\n# macOS\nbrew install tesseract-lang\n\n# Debian\u002FUbuntu\nsudo apt install tesseract-ocr-deu tesseract-ocr-jpn tesseract-ocr-fra\n\n# Specific lang only\nsudo apt install tesseract-ocr-\u003Ciso639-2>\n```\n\nKreuzberg fails fast with a helpful error if you request a language pack\nthat is not installed. Read the error — it names the missing file.\n\n## Useful flags\n\n- `--ocr=true` — enable OCR (auto-enabled for images and scanned PDFs).\n- `--force-ocr=true` — OCR every page even if a text layer exists.\n- `--disable-ocr=true` — never OCR (extract embedded text only or fail).\n- `--ocr-language \u003Clang>` — single code or `+`-joined list, or `all`.\n- `--ocr-backend \u003Ctesseract|paddle-ocr|easyocr>` — pick backend.\n- `--ocr-auto-rotate=true` — pre-rotate via the auto-rotate model.\n- `--acceleration \u003Ccpu|coreml|cuda|tensorrt|auto>` — ONNX accelerator for\n  paddle-ocr \u002F auto-rotate \u002F layout models.\n\n## Performance tips\n\n- Cache is on by default. Repeated extraction of the same file + config is\n  instant. Do not pass `--no-cache=true` unless you have a reason.\n- For batch OCR, use `kreuzberg batch *.pdf --ocr=true` — internal worker\n  pool parallelizes across CPU cores. Cap with `--max-concurrent N` if\n  memory is tight.\n- Raise `--target-dpi` (default 300) only for low-resolution scans. Higher\n  DPI is slower; 200 is usually enough for printed text.\n- Enable `--ocr-auto-rotate=true` only when pages may be rotated; the\n  classifier adds latency.\n- On Apple Silicon, `--acceleration coreml` typically beats CPU for\n  paddle-ocr and layout detection.\n\n## Config file alternative\n\nLong flag chains belong in `kreuzberg.toml` — auto-discovered from cwd\nupward.\n\n```toml\nforce_ocr = true\noutput_format = \"markdown\"\n\n[ocr]\nbackend = \"tesseract\"\nlanguage = \"eng+deu\"\nauto_rotate = true\n```\n\nThen just run:\n\n```bash\nkreuzberg extract document.pdf\n```\n\n## Common failure modes\n\n- **\"missing tessdata\"** — install the language pack at OS level (see above).\n- **Empty content on a scanned PDF without `--force-ocr`** — the file has a\n  bogus zero-width text layer. Re-run with `--force-ocr=true`.\n- **OCR on a rotated page** — add `--ocr-auto-rotate=true` or pre-rotate.\n- **Garbled CJK output** — ensure the right language pack is installed and\n  passed via `--ocr-language`; consider `paddle-ocr` for Chinese\u002FJapanese.\n\nSee `references\u002Fcli-reference.md` and `references\u002Fconfiguration.md` in the\nsibling `kreuzberg` skill for the full flag and config schema.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzberg\u002Fskills\u002Fextracting-with-ocr",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill extracting-with-ocr",{"tool":55,"command":56},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill extracting-with-ocr",{"tool":58,"command":59},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill extracting-with-ocr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzberg\u002Fskills\u002Fextracting-with-ocr\u002FSKILL.md",true,[],[64,74,82,90,98,106],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":73},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":73},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":73},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":73},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":73},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":68,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":73},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]