Document Extraction (ADE)
Template-free PDF/image/spreadsheet parsing to structured Markdown+JSON with schema extraction and bounding boxes.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 3f1b034
Designed the same invoice-field-extraction task twice: baseline reached for OCR + regex/LLM guesswork, the skill's Pydantic-to-JSON-Schema + client.extract() path returns the fields plus per-field chunk traceability and confidence scores out of the box.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Document Extraction (ADE) does
Wraps LandingAI's Agentic Document Extraction (ADE) API/SDK to parse PDFs, images, spreadsheets, and presentations into structured Markdown with per-chunk grounding, then extract specific fields via a JSON Schema or Pydantic model. Also covers classifying and splitting mixed document batches, generating a table of contents, and async jobs for large files. Triggers on schema-based extraction, page classification, document splitting, TOC generation, or any mention of bounding boxes/grounding/word locations.
How to install Document Extraction (ADE)
git clone https://github.com/landing-ai/ade-document-processing-skills
cd ade-document-processing-skills
mkdir -p ~/.claude/skills
cp -r plugins/ade-document-processing/skills/document-extraction ~/.claude/skills/document-extraction
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Document Extraction (ADE)
-
/document-extractionTemplate-free PDF/image/spreadsheet parsing to structured Markdown+JSON with schema extraction and bounding boxes.
It also activates on plain-language prompts like these:
-
Extract the invoice number, date, and total from this PDF -
Split this folder of mixed invoices and receipts by type -
Pull the exact text location for each clause in this contract
Frequently asked questions
- Is the Document Extraction (ADE) skill free?
- Yes. The skill itself is free from landing-ai/ade-document-processing-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Document Extraction (ADE) work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Designed the same invoice-field-extraction task twice: baseline reached for OCR + regex/LLM guesswork, the skill's Pydantic-to-JSON-Schema + client.extract() path returns the fields plus per-field chunk traceability and confidence scores out of the box.
- What is the Document Extraction (ADE) SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Document Extraction (ADE)?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Document Extraction (ADE) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.