ade

Parse documents and extract schema-shaped data with grounded evidence via the ADE v2 APIs.

2.4k|255|Updated Mar 12, 2025
One-click install
npx skills add https://github.com/landing-ai/ade-cli --skill ade-landing-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ade
Source: https://github.com/landing-ai/ade-cli
Command: npx skills add https://github.com/landing-ai/ade-cli --skill ade-landing-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning PDFs and images with tables, figures, and charts into structured, citable data usually requires brittle parsing code and repeated API calls that re-bill on every retry. This Skill drives the ADE (Agentic Document Extraction) v2 APIs through the ade CLI, persisting every run in a local job-item store so repeat runs are free, interrupted runs resume, and every extracted value can cite element ids with page-and-box evidence. ## Core Features & Use Cases - Document parsing: ade parse converts documents into grounded Markdown and elements, with results stored under ~/.ade/jobs/<job-item-id>/ and deduplicated by invocation identity. - Schema extraction: ade extract pulls JSON-schema-shaped fields from a parse, computing per-field evidence (spans joined to pages and boxes) offline, and flagging ungroundable or empty fields explicitly. - Local search and citation: ade find searches elements without API calls, ade crop renders element regions as PNGs, and ade view builds a self-contained HTML viewer with deep links for citations. - Use Case: Given a folder of invoices, parse each once, extract totals and line items against a JSON schema, then answer questions citing element ids and deep links — re-running any step consumes no credits. ## Quick Start Ask the agent to run ade parse on your document, then ade extract with your JSON schema, always passing --json so results arrive as stable structured output.

Frequently Asked Questions about ade

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract structured data from a PDF with the ade CLI?▼

Run ade parse -d file.pdf to get a job item id, then ade extract JOB_ITEM_ID --schema schema.json --json. The extraction payload is on stdout, and per-field evidence joins spans to pages and boxes automatically.

Does re-running ade parse or extract consume credits again?▼

No. Commands are guarantees keyed by invocation identity, so re-running an identical command is served from the local store at ~/.ade with no API call. Only passing --force re-bills.

What happens if an ade run is interrupted or times out?▼

Interrupts and wait expiry stop only the local polling; the server-side run continues and bills. Re-running the exact same command resumes the recorded run via its claim ticket and never resubmits.

Can ade extract from markdown that did not come from ade parse?▼

Yes, use --markdown FILE or --markdown-url URL as a bring-your-own-markdown input. Evidence degrades to spans-only since there is no parse grounding to join against, and the viewer renders the markdown pane alone.

How do agents discover the ade CLI command surface?▼

Run ade help --json once; it returns every command, flag, --json result shape, exit state, and the store layout. Every command then emits one stable JSON object on stdout.