--- title: "Document Extraction (ADE) - Air Market" description: "You have a folder of PDFs, scans, spreadsheets or slide decks and you need what is inside them as usable text or fields. This reads them and gives back structured content, and it can tell you which p…" canonical: "https://airmarket.ai/app/document-extraction" --- [Air Market](/) / [Data & Analytics](/category/data) / Document Extraction (ADE) Skill by [Andrew Ng](/@andrewyng) # Document Extraction (ADE) Pull clean text and named fields out of stacks of documents ## What this does You have a folder of PDFs, scans, spreadsheets or slide decks and you need what is inside them as usable text or fields. This reads them and gives back structured content, and it can tell you which page and spot each piece came from. It handles very long documents and can sort a mixed batch into invoices, receipts, statements and so on. Reach for it when the pile is too big to read by hand. ### Top 3 things it does for you - Turn a PDF or scan into readable Markdown - Pull named fields off invoices and forms - Sort a mixed pile of documents by type ## Information **Document Extraction (ADE) at a glance** | | | | --- | --- | | Kind | Skill | | Publisher | [Andrew Ng](/@andrewyng) | | Category | [Data & Analytics](/category/data) | | Works with | Agent Skills - an open standard supported by 40+ agents | | Size | 72 KB | | Licence | MIT | | Repository | [andrewyng/context-hub](https://github.com/andrewyng/context-hub/tree/04c149cd82d23d037e157d5920b80b0ca10d84b5/content/landingai/skills/ade/document-extraction) | | GitHub stars | 13,938 (as of Nov 2026) | | Installs | 62, counted by skills.sh (Nov 2026) | ## Security report **Verified.** AIR scanned this exact version of Document Extraction (ADE) and flagged nothing. AIR's verdict: **safe**. **What Document Extraction (ADE)'s check was run against** | | | | --- | --- | | Commit | 04c149cd82d23d037e157d5920b80b0ca10d84b5 | | Content hash | edc31338d5ba11796b0fdaa747f5077459f0d19097a485e6965db9a403d50231 | | Files read | [Browse the files at this exact commit](https://github.com/andrewyng/context-hub/blob/04c149cd82d23d037e157d5920b80b0ca10d84b5/content/landingai/skills/ade/document-extraction/SKILL.md) | A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned. [Read the full security report for Document Extraction (ADE)](/security/document-extraction) ## About Document Extraction (ADE) This turns documents into something a program can work with. Give it PDFs, images, spreadsheets or presentations and it parses them into structured Markdown that keeps the sense of the layout, rather than a flat dump of words. When you know what you are looking for, you can ask for specific fields instead of the whole document: invoice fields, form entries, table contents. It can also take a mixed batch and classify and separate it by type, so invoices and receipts, or statements and forms, end up apart. Large documents can be processed asynchronously. It can return visual grounding along with the content, so you know the page and the region an extracted value came from. That is what you want when you need to highlight a value on the original page or show where the data appeared. It is built for working over sets of documents by writing code that runs across them, rather than loading each document into the conversation. ## What's inside - SKILL.md - instructions - .env-sample - .gitignore - references/chunk-types.md - reference - references/extraction-schemas.md - reference - references/file-formats.md - reference - references/troubleshooting.md - reference - references/use-cases.md - reference ## Questions ### Is Document Extraction (ADE) safe to install? AIR scanned this exact version of Document Extraction (ADE) and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit 04c149cd82d2, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/document-extraction. ### How do I install Document Extraction (ADE)? Open https://airmarket.ai/app/document-extraction on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/andrewyng/context-hub/tree/04c149cd82d23d037e157d5920b80b0ca10d84b5/content/landingai/skills/ade/document-extraction. Install from that link, not the branch. ## Related on Air Market - [More Data & Analytics listings](/category/data) - [Everything by Andrew Ng](/@andrewyng) --- Canonical URL: