Skip to main content
skill CX Codex

oma-pdf — Claude Code skill: what it does, how to install

oma-pdf converts PDF documents into structured Markdown while preserving tables, headings, and lists. Runs when preparing files for LLM context or RAG pipelines.

MIT ★ 1,472 updated 2026-11-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add first-fluke/oh-my-agent
/plugin install oma-research@oh-my-agent
Open on GitHub

What oma-pdf does

The skill extracts document structure through opendataloader-pdf and formats the generated Markdown with mdformat. Before converting the entire document, it inspects the first few pages to detect whether a usable text layer exists. If the text reads cleanly, it executes a lightweight standard conversion.

Scanned pages or image-only files trigger an OCR pipeline using opendataloader-pdf-hybrid on local port 5002. When tables lose their structure, the skill retries extraction with --table-method cluster or HTML formatting. Without uv installed on the host system, external CLI execution fails immediately.

What it helps with

  • extract text, lists, and headings from PDF into Markdown
  • recover complex or broken PDF tables using cluster extraction
  • parse scanned or image-based PDFs with local OCR
  • normalize Markdown output using mdformat

Example prompts for the agent

  • Convert financial_report.pdf into Markdown and place it in output/
  • Parse scanned document archive.pdf with OCR and extract all tables
  • Extract pages 1 to 5 from manual.pdf into plain text

How to install oma-pdf

1Plugin marketplace

/plugin marketplace add first-fluke/oh-my-agent
/plugin install oma-research@oh-my-agent

This installs the whole oma-research plugin with all its skills

2Skills CLI (Vercel)

npx skills add first-fluke/oh-my-agent --skill oma-pdf -a claude-code

3Manually: put the files in place

~/.claude/skills/oma-pdf/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/oma-pdf/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about oma-pdf

How do I install oma-pdf in Claude Code?

Run npx skills add first-fluke/oh-my-agent --skill oma-pdf -a claude-code in your terminal.

What does oma-pdf do?

It converts PDF documents into clean Markdown, HTML, JSON, or text for LLM prompts and retrieval workflows.

What dependencies does oma-pdf require?

It requires uv to execute opendataloader-pdf and mdformat via uvx. Scanned files need the opendataloader-pdf[hybrid] extra for OCR support.

Source text

SKILL.md · MIT
---
name: oma-pdf
description: Extract PDF text, headings, tables, and images into Markdown using
  opendataloader-pdf. Use for PDF parsing, not PDF layout creation.
---

# PDF Skill - PDF to Markdown Conversion

## Scheduling

### Goal
Convert PDF files into structured Markdown or another requested extraction format while preserving readable document structure for LLM context, RAG, or downstream review.

### Intent signature
- User asks to convert, parse, read, extract, or transform a PDF.
- User needs PDF text, headings, lists, tables, or images prepared for AI consumption.
- User mentions "PDF to markdown", "parse PDF", "read this PDF", or equivalent wording.

### When to use
- Converting PDF documents to Markdown for LLM context or RAG
- Extracting structured content such as tables, headings, lists, images, footnotes, or hyperlinks
- Preparing PDF data for AI consumption
- Checking whether a PDF has a text layer before choosing OCR

### When NOT to use
- Generating or creating PDFs -> use document-generation tools
- Editing existing PDFs -> out of scope
- Reading an already-text file -> use direct file reading
- Processing HWP, HWPX, DOCX, XLSX, or slide decks -> use the matching document skill

### Expected inputs
- `input_path`: PDF file or folder path
- `output_dir`: optional target directory
- `format`: optional output format, default `markdown`
- `ocr_languages`: optional OCR language list for scanned or image-based PDFs
- `extraction_options`: optional flags for tagged structure, image extraction, or hybrid conversion

### Expected outputs
- Markdown, text, JSON, HTML, or combined extraction output
- Normalized Markdown when Markdown is produced
- A short report with output path, page count, and conversion issues

### Dependencies
- `uvx opendataloader-pdf` for standard conversion
- `uvx --from "opendataloader-pdf[hybrid]" opendataloader-pdf-hybrid` for OCR or hybrid conversion (the hybrid server is a console script of the `[hybrid]` extra, not a standalone package)
- `uvx mdformat` for Markdown normalization
- Local filesystem access to input and output paths
- Optional OCR runtime via the hybrid server

### Control-flow features
- Branches on text-layer quality, tagged PDF availability, scan/OCR needs, and user-requested output format
- Calls external CLI tools through `uvx`
- Reads local files and writes local extraction outputs
- Uses a hybrid server only when OCR or complex extraction needs justify it

## Structural Flow

### Entry
1. Confirm that the input path exists and is a PDF file, PDF folder, or supported batch input.
2. Check file size and warn when the input is large enough to risk slow conversion or memory pressure.
3. Resolve `output_dir` and the expected output filename.

### Scenes
1. **PREPARE**: Validate the input path, output target, and requested extraction options.
2. **ACQUIRE**: Assess whether the PDF has a readable text layer by extracting a text preview.
3. **ACT**: Convert using standard mode, tagged-structure mode, or hybrid OCR mode.
4. **VERIFY**: Run `mdformat` for Markdown output and inspect the result for readable structure.
5. **FINALIZE**: Report output path, page count, format, and any extraction quality issues.

### Transitions
- If the preview text is readable, use standard conversion.
- If the PDF is tagged and standard output is garbled, retry with `--use-struct-tree`.
- If tables are missing or broken, retry with `--table-method cluster` or `--markdown-with-html` before escalating to hybrid mode.
- If the PDF is scanned or image-based, start or reuse the hybrid OCR server and convert with hybrid mode.
- If conversion fails because the PDF is encrypted, stop and ask for the password or an unlocked copy.
- If conversion hits memory or size limits, process smaller page ranges into distinct output directories (or append `--to-stdout`) so repeated runs do not overwrite the same basename.
- When a transition above leaves standard conversion, record the selected mode with subject `pdf.route-selection` per `../_shared/runtime/route-selection.md` (mode, and the probe or output defect that required it).

### Failure and recovery
| Failure | Recovery |
|---------|----------|
| `uvx` unavailable | Ask user to install `uv` before conversion |
| `opendataloader-pdf-hybrid` not found | Invoke via `uvx --from "opendataloader-pdf[hybrid]" opendataloader-pdf-hybrid`; the bare package name does not exist on PyPI |
| Password-protected PDF | Ask for password or unlocked PDF |
| Garbled output | Retry with tagged structure or hybrid mode |
| Missing tables | Retry with `--table-method cluster` or `--markdown-with-html` first; hybrid mode for scanned tables |
| OCR language mismatch | Retry with explicit OCR languages, for example `ko,en` |
| Large file or memory pressure | Split into page ranges using distinct output directories or `--to-stdout`; never reuse one output directory for the same basename |

### Exit
- Success: output file exists, Markdown is formatted when applicable, and extracted structure is readable.
- Partial success: output exists but quality issues are reported explicitly.
- Failure: no reliable output is produced and the blocking cause is reported.

## Logical Operations

### Actions
| Action | SSL primitive | Evidence |
|--------|---------------|----------|
| Validate path and options | `VALIDATE` | Input preflight in execution protocol |
| Probe text layer | `READ` | Text preview extraction |
| Choose conversion strategy | `SELECT` | Standard, tagged, or hybrid mode decision |
| Run converter | `CALL_TOOL` | `uvx opendataloader-pdf` |
| Start OCR server | `CALL_TOOL` | `uvx --from "opendataloader-pdf[hybrid]" opendataloader-pdf-hybrid` |
| Write output artifact | `WRITE` | Markdown, text, JSON, or HTML output |
| Normalize Markdown | `CALL_TOOL` | `uvx mdformat` |
| Inspect extraction quality | `VALIDATE` | Structure/readability verification |
| Report result | `NOTIFY` | Final user-facing summary |

### Tools and instruments
- `opendataloader-pdf`: primary PDF extraction CLI
- `opendataloader-pdf-hybrid`: hybrid OCR and complex extraction path
- `mdformat`: Markdown normalization
- Filesystem commands such as `file`, `wc`, or `pdfinfo` may be used for preflight when available

### Canonical command path
```bash
uvx opendataloader-pdf "{input_path}" -f text --pages 1-3 --to-stdout -q   # text-layer probe (no temp files)
uvx opendataloader-pdf "{input_path}" --format markdown --output-dir "{output_dir}"
uvx mdformat "{output_path}"
```

For scanned/image-based PDFs, start OCR first and then convert through hybrid mode:
```bash
uvx --from "opendataloader-pdf[hybrid]" opendataloader-pdf-hybrid --port 5002 --force-ocr --ocr-lang "{languages}"
uvx opendataloader-pdf --hybrid docling-fast --hybrid-mode full "{input_path}" --format markdown --output-dir "{output_dir}"
```

On-request flags — `--sanitize` (PII masking), `--pages` (range extraction), `--threads` (parallel pages), `--detect-strikethrough`, hybrid `--enrich-formula` / `--enrich-picture-description` — are detailed in `resources/execution-protocol.md`. The two enrichment flags require client-side `--hybrid-mode full`.

### Resource scope
| Scope | Resource target |
|-------|-----------------|
| `LOCAL_FS` | Input PDFs and generated output files |
| `PROCESS` | `uvx` subprocesses and optional hybrid server |
| `MEMORY` | Extracted previews and validation notes |
| `OTHER` | OCR model/runtime behavior inside hybrid mode |

### Preconditions
- The input PDF path exists and is readable.
- The output location is writable or can be created.
- Required CLIs are available through `uvx`.
- OCR is only attempted when hybrid mode is available or can be started.
- Defaults come from the `pdf:` section of `.agents/oma-config.yaml`, falling back to `config/pdf-config.yaml` for unset keys; explicit user options override both, and `output.overwrite: false` requires confirmation before replacing an existing output file.

### Effects and side effects
- Creates or overwrites extraction output depending on configuration and user intent.
- May start a local hybrid OCR server on the configured port.
- May consume significant CPU, memory, or time for large or scanned PDFs.
- Does not intentionally modify the source PDF.

### Guardrails
1. Do not invent missing content when extraction is incomplete.
2. Always report garbled text, missing tables, OCR uncertainty, or partial extraction.
3. Prefer standard conversion first when the text layer is readable.
4. Use OCR only when the PDF is scanned, image-based, or standard extraction quality is insufficient.
5. Keep detailed command sequences in `resources/execution-protocol.md` rather than duplicating every variant here.

## References
- Execution protocol: `resources/execution-protocol.md`
- Configuration: read the `pdf:` section of `.agents/oma-config.yaml` first, then fall back to `config/pdf-config.yaml` for any key it does not set. User overrides belong in `.agents/oma-config.yaml`, since `oma update` overwrites the skill config.
- Context loading: `../_shared/core/context-loading.md`
- Quality principles: `../_shared/core/quality-principles.md`

© First Fluke · MIT · first-fluke/oh-my-agent

Similar skills

All skills for Writing and docs →

From the same set69

The whole set →
oma-image oma-image routes image generation requests across Codex, Pollinations and Gemini, and turns a reference picture into a new variation matching its style or layout. CX Codex +1 ★ 1,472repo stars oma-architecture oma-architecture is a Claude Code skill that helps design module and service boundaries, compare alternatives, and document architecture decisions as ADRs. CX Codex +1 ★ 1,472repo stars oma-coordination The oma-coordination skill guides manual coordination across specialist agents on multi-domain projects. It covers task planning, progress checks, contract alignment, and a final QA review. CX Codex +1 ★ 1,472repo stars oma-hwp oma-hwp turns Korean HWP, HWPX and HWPML documents into Markdown via kordoc. Extracts text, tables, lists, images and footnotes. CX Codex +1 ★ 1,472repo stars oma-market oma-market runs community-signal research on customer pain, trends, and competitors, then saves a market brief for the requested topic. CX Codex +1 ★ 1,472repo stars oma-video Builds videos through the OMA video CLI or works on an existing clip: pulling frames, cutting silence, assembling dubbed audio. CX Codex +1 ★ 1,472repo stars oma-skill-creator oma-skill-creator is a Claude Code skill that creates, formats, and validates OMA skills in SSL-lite format inside .agents/skills/. CX Codex +1 ★ 1,472repo stars oma-frontend oma-frontend is a Claude Code skill for building and editing frontend UI in React, Next.js, and TypeScript projects, including components, pages, styles, and client logic. CX Codex +1 ★ 1,472repo stars

Project sponsors

Companies that keep this analytics open