Skip to content
Agentmart
Submit a tool

document-extractor

Extracts key information from documents (PDFs, images, text files) in a folder and creates structured markdown summaries with the same filename but .md…

Skill by Abilityai

IndexedApache-2.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/abilityai-document-extractor

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Extracts key information from documents (PDFs, images, text files) in a folder and creates structured markdown summaries with the same filename but .md extension. Use when you need to analyze and extract insights from multiple documents in a directory.

Use cases: documents

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/document-extractor

Tools it pre-approves 4

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Write,
  • Bash,
  • Glob

What's inside

Skill name
document-extractor
Description
Extracts key information from documents (PDFs, images, text files) in a folder and creates structured markdown summaries with the same filename but .md extension. Use when you need to analyze and extract insights from multiple documents in a directory.
License
Apache-2.0
Allowed tools
Read,, Write,, Bash,, Glob
Metadata
version: 1.0
Instructions
101 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Document Extractor

Analyze documents in a specified folder and create structured markdown extracts that capture the most important information from each document.

## Workflow

### 1. Initial Setup
- Get current date/time: `date '+%Y-%m-%d %H:%M:%S %Z'`
- List all files in the specified folder
- Create output directory: `Files/[folder_name]/` in the workspace

### 2. Document Processing

For each document:
1. Read using the Read tool
2. Collect metadata (file hash, modification date, extraction timestamp)
3. Identify document type and extract key information
4. Write to `Files/[folder_name]/[original_name].md`

### 3. Information Categories

**Legal/Official Documents:** Document type/number, dates, issuing authority, key terms, obligations, deadlines

**Financial Documents:** Account numbers (masked), transactions, amounts, payment dates, tax info

**Insurance Documents:** Policy numbers, coverage types/limits, premiums, deductibles, exclusions

**Contracts/Agreements:** Party names, duration, obligations, payment terms, termination clauses

**Personal Documents:** Document numbers (masked), validity periods, restrictions

### 4. Output Template

```markdown
# [Document Title/Type]

## Document Information
- **Document Type**: [Type]
- **File Name**: [Original filename]
- **File Hash**: [MD5/SHA256 hash]
- **Last Modified**: [File modification date]
- **Extraction Date**: [Current timestamp]

## Key Information
[Main extracted data organized by relevance]

## Important Dates
- **Issue Date**: [Date]
- **Expiry Date**: [Date if applicable]
- **Next Action Required**: [Date/Description if applicable]

## Notes and Observations
- [Important observations]
- [Unusual clauses]
- [Action items]

---
*Extracted: [timestamp] | Original: [path]*
```

### 5. Security
- Mask sensitive info (show last 4 digits only)
- Note when information has been redacted
- Flag potential security concerns

### 6. Summary Report
After processing all documents, create `Files/[folder_name]/summary.md` with:
- Total documents processed
- Document categories found
- Key findings
- Items requiring attention

## Useful Commands

```bash
# Get timestamp
date '+%Y-%m-%d %H:%M:%S %Z'

# Get file hash (macOS)
md5 -q /path/to/file
shasum -a 256 /path/to/file | cut -d' ' -f1

# Get modification date (macOS)
stat -f "%Sm" -t "%Y-%m-%d %H:%M:%S" /path/to/file

# List documents
find /path/to/folder -type f \( -name "*.pdf" -o -name "*.txt" -o -name "*.jpg" -o -name "*.png" \)
```

## Error Handling

| Error | Cause | Solution |
|-------|-------|----------|
| File unreadable | Corrupted or encrypted file | Skip file, note in summary, try alternative viewer |
| PDF extraction fails | Scanned image PDF | Use OCR or note as "image-based PDF" |
| Output folder not writable | Permission issue | Check permissions on Files/ directory |
| Sensitive data detected | PII or credentials visible | Mask appropriately, flag for review |
| Duplicate files | Same content, different names | Note duplicates in summary, extract once |
| Unknown file type | Unsupported format | Skip with note, or convert to supported format first |

From Abilityai/trinity-skills, Apache-2.0.

More from Abilityai/trinity-skills

Signals

Stars
0
Forks
1
Open issues
1
Last commit (this folder)
Aug 4, 2026 (2 months ago)
Last release
Oct 21, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0
License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Abilityai

Cite this page

document-extractor skill. Agent Mart. https://agentmart.dev/skills/abilityai-document-extractor (last updated 2026-10-24)