# Document Parser

> Parse and extract structured content from PDFs, Word documents, and other file formats. Converts documents into clean, machine-readable text for analysis, summarization, data extraction, and content processing workflows.

- **Type:** Skill
- **Install:** `agentstack add skill-sandbaseai-sandbase-skills-document-parser`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [sandbaseai](https://agentstack.voostack.com/s/sandbaseai)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [sandbaseai](https://github.com/sandbaseai)
- **Source:** https://github.com/sandbaseai/sandbase-skills/tree/main/research/document-parser
- **Website:** https://skills.sh/sandbaseai/sandbase-skills/multi-source-search

## Install

```sh
agentstack add skill-sandbaseai-sandbase-skills-document-parser
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Document Parser

Parse and extract structured content from PDFs, Word documents, and other file formats. Converts documents into clean, machine-readable text for analysis, summarization, data extraction, and content processing workflows. Read [the API map](references/sandbase-api-map.md) before selecting a capability.

## Call SandBase capabilities

For every selected tool, call `sandbase_describe_tool` first and use only arguments in its current input schema. Then call `sandbase_call_tool` with the exact `tool_name`.

## Available Tools

- `agentbody_document_parse`

## Workflow

1. Understand the user's research question, target, and context.
2. Call `sandbase_describe_tool` for each selected tool to confirm parameter schema.
3. Call `sandbase_call_tool` with the exact tool_name and schema-defined arguments.
4. Synthesize findings into a clear, evidence-backed answer.
5. Cite sources, note evidence gaps, and separate observations from interpretations.

## Guidelines

- Always call `sandbase_describe_tool` before using any capability.
- Cite sources and preserve attribution (URLs, usernames, dates, metrics).
- Separate factual observations from analysis and recommendations.
- If data is unavailable, note the gap and continue with available evidence.
- Read-only research only. Never take actions on platforms.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [sandbaseai](https://github.com/sandbaseai)
- **Source:** [sandbaseai/sandbase-skills](https://github.com/sandbaseai/sandbase-skills)
- **License:** Apache-2.0
- **Homepage:** https://skills.sh/sandbaseai/sandbase-skills/multi-source-search

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-sandbaseai-sandbase-skills-document-parser
- Seller: https://agentstack.voostack.com/s/sandbaseai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.