document-intelligence — Claude Code skill: use and install
The document-intelligence skill routes document work through Snowflake Cortex AI, from field extraction and OCR to layout-aware parsing. It fits PDFs, scans, images, and office files.
no license 1 installs ★ 1 updated 2026-02-03
npx skills add sfc-gh-nejain/document-intelligence-skill --skill document-intelligence -a claude-codeWhat document-intelligence does
document-intelligence provides a workflow for document processing with Snowflake Cortex AI. It helps an agent identify the file type, clarify the desired output, and select structured extraction or full content parsing. Local files are uploaded to a Snowflake stage before processing. Results can then feed a table, pipeline, or RAG search.
The package points to reference/ai-extract.md for fields and tables and reference/ai-parse-doc.md for text, page structure, and images. Its process includes testing one file with AI_EXTRACT, reviewing the result, refining the request when needed, and moving to a batch run or storage step.
Supported inputs include PDF, PNG, JPEG, TIFF, DOCX, PPTX, HTML, and TXT. AI_EXTRACT also handles CSV, MD, and EML. XLSX and XLS cannot be passed directly to these document AI functions, while DOC and PPT need conversion first.
What it helps with
- extract fields and tables from PDFs
- read text from scanned images
- parse invoices, contracts, and reports
- test extraction on one file before a batch run
- prepare document data for a table or RAG search
Example prompts for the agent
- Use Snowflake
AI_EXTRACTto pull fields and tables from this PDF. - Parse this document with
AI_PARSE_DOCUMENT, keeping its text and page structure. - Run a test on one file, show the result, and refine the request before processing the batch.
How to install document-intelligence
1Skills CLI (Vercel)
npx skills add sfc-gh-nejain/document-intelligence-skill --skill document-intelligence -a claude-code2Manually: put the files in place
~/.claude/skills/document-intelligence/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/document-intelligence/
1Skills CLI (Vercel)
npx skills add sfc-gh-nejain/document-intelligence-skill --skill document-intelligence -a codex2Manually: put the files in place
.agents/skills/document-intelligence/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sfc-gh-nejain/document-intelligence-skill --skill document-intelligence -a cursor2Manually: put the files in place
.cursor/skills/document-intelligence/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sfc-gh-nejain/document-intelligence-skill document-intelligence2Manually: put the files in place
.github/skills/document-intelligence/SKILL.md1Skills CLI (Vercel)
npx skills add sfc-gh-nejain/document-intelligence-skill --skill document-intelligence -a gemini-cli2Platform CLI
gemini skills install https://github.com/sfc-gh-nejain/document-intelligence-skillManually: put the files in place
.devin/skills/document-intelligence/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sfc-gh-nejain/document-intelligence-skill --skill document-intelligence -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about document-intelligence
How do I install document-intelligence in Claude Code?
Run npx skills add sfc-gh-nejain/document-intelligence-skill --skill document-intelligence -a claude-code, then check ~/.claude/skills/document-intelligence/SKILL.md.
What does document-intelligence do?
It guides document processing with Snowflake Cortex AI, including structured extraction, content parsing, OCR, and analysis of images, diagrams, and blueprints.
Which file formats does document-intelligence support?
It supports PDF, PNG, JPEG, TIFF, DOCX, PPTX, HTML, and TXT. AI_EXTRACT also accepts CSV, MD, and EML; XLSX and XLS are not directly supported.