Parse documents from Claude Code

One install command. Ask Claude to parse any document — DOCX, PPTX, XLSX, PDF, and more.

Install the Skill

Run one command inside Claude Code to add AILANG Parse:

claude install github:sunholo-data/ailang-parse-skill

This registers the AILANG Parse skill in your Claude Code environment. Once installed, Claude automatically invokes it whenever you ask about document parsing, extraction, or conversion. No configuration files to edit.

The skill ships with helper scripts for health checks, parsing, cost estimation, and device auth. Claude uses these automatically — you just ask in plain English.

Usage Examples

After installing, just tell Claude what you need. The skill triggers on any document parsing task:

> Parse this contract and extract all track changes
> What tables are in quarterly_report.xlsx?
> Convert presentation.pptx to markdown
> Extract comments from legal_draft.docx with authors
> Parse invoice.pdf and return structured JSON

Claude handles file upload, format detection, output formatting, and error recovery. You get structured blocks back — ready to use in your code or pipe into another tool.

What the Skill Can Do

13 Input Formats

  • Office: DOCX, PPTX, XLSX, ODT, ODP, ODS
  • Text: CSV, Markdown, HTML, EPUB
  • AI-powered: PDF, PNG, JPG

4 Output Formats

  • blocks — structured JSON with typed block ADT (Text, Heading, Table, Image, List, Section, Change, Audio, Video)
  • markdown — clean Markdown rendering
  • html — semantic HTML
  • a2ui — A2UI protocol for agent UIs

Key Features

  • Deterministic Office parsing — no AI needed, no network calls, no per-page billing
  • AI-powered PDF/image parsing — pluggable models (Gemini, Claude, Ollama)
  • Track changes, comments, merged cells — structural features from direct XML access
  • Cost estimation before parsing — check AI vs deterministic and latency before committing
  • Device auth flow — seamless API key management from the terminal

Authentication

The skill uses an RFC 8628 device authorization flow — no API keys to copy-paste:

  1. Your first parse request triggers the auth flow automatically
  2. Claude shows you a URL and a short code
  3. Open the URL and sign in — authorization is automatic
  4. Your API key is stored locally — all subsequent requests are instant

Keys use the dp_ prefix and are stored as DOCPARSE_API_KEY in your environment. Free tier gives you 1,000 requests/month to start.

Already have a key? Set DOCPARSE_API_KEY in your shell environment and the skill will use it directly, skipping the device flow.

API Endpoints Available

The skill can access these endpoints on your behalf:

EndpointMethodPurpose
/api/v1/parsePOSTParse any document into structured blocks
/api/v1/estimatePOSTCheck cost and latency before parsing
/api/v1/formatsGETList all supported input/output formats
/api/v1/samplesGETTest with built-in sample files
/api/v1/capabilitiesGETFull capability manifest for agent discovery
/api/v1/healthGETService status and version

All responses include typed error codes with suggested_fix fields that Claude can act on directly. If a parse fails, Claude reads the fix and retries automatically.

MCP Server

AILANG Parse also works as an MCP (Model Context Protocol) server, exposing its parsing tools to any MCP-compatible AI agent:

# Coming soon
ailang-parse --mcp

The /api/v1/tools endpoint already serves tool definitions in Claude, OpenAI, and MCP formats. Any agent that speaks MCP can discover and call AILANG Parse without custom integration.

Try in Browser API & SDKs

Frequently Asked Questions

How do I install the AILANG Parse skill for Claude Code?

Run claude install github:sunholo-data/ailang-parse-skill in your terminal. Once installed, Claude Code can parse documents directly during your coding session — extract tables, track changes, comments, and convert between formats without leaving the terminal.

What can the AILANG Parse Claude Code skill do?

The skill gives Claude Code the ability to parse DOCX, PPTX, XLSX, and other Office formats into structured data. You can ask Claude to extract a specific table, list all tracked changes with authors, pull out comments, or convert a document to Markdown. It uses the same parsing engine as the API with full structural fidelity.

Does the Claude Code skill send my documents to external servers?

By default, the skill calls the AILANG Parse cloud API. If you need full privacy, you can point the skill at a self-hosted instance by setting the AILANG_PARSE_URL environment variable. With a local Docker instance, your documents never leave your machine.

Can I use AILANG Parse with other AI coding assistants besides Claude Code?

Yes. AILANG Parse also runs as an MCP server that works with Cursor, Windsurf, and any MCP-compatible IDE tool. Additionally, the REST API can be called from any custom agent or script.