richpdf
Extracts structured knowledge and assets from complex document formats.
Install
mkdir -p .claude/skills/richpdf && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15625" && unzip -o skill.zip -d .claude/skills/richpdf && rm skill.zipInstalls to .claude/skills/richpdf
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Extract structured wiki-ready markdown from any document — PDF (text or image/scanned), markdown clippings, or plain text. Captures text, embedded images/diagrams, and code samples per page. Images saved to raw/assets/ and referenced inline with the page they came from. Use when user says "/richpdf", "ingest", "process this pdf", "ingest this document", or provides a file path.Key capabilities
- →Extract 5 key ideas per page from documents
- →Capture embedded images and diagrams
- →Save images to `raw/assets/` and reference them inline
- →Detect and extract code samples with language identification
- →Process text-based PDFs using pymupdf
- →Process image/scanned PDFs using vision for text and code
How it works
This skill extracts structured markdown from documents by identifying key ideas, embedded images, and code samples per page, saving images to a dedicated asset directory and referencing them inline.
Inputs & outputs
When to use richpdf
- →Converting PDFs to markdown
- →Extracting images from scanned documents
- →Documenting code samples from PDFs
- →Ingesting reference materials
About this skill
richpdf / ingest
Extracts structured, wiki-ready markdown from any document. Per page it captures:
- 5 key ideas
- All embedded images and diagrams (saved to
raw/assets/, described by vision) - All code samples (detected by font analysis or fenced blocks, language identified)
Each image and code sample is placed inline immediately after the key ideas of the page it came from — so the extracted knowledge stays in context.
Requirements (PDF extraction)
pip install pymupdf anthropic
Usage (PDFs)
python .agent/skills/richpdf/extract.py <file_path> [output_dir]
file_path— path to document (PDF, .md, .txt)output_dir— where to save the wiki.md(default:wiki/sources/)- Images always saved to
raw/assets/
For clippings and articles: read the file directly — no script needed.
How assets are detected
| Source type | Text | Code blocks | Images/Diagrams |
|---|---|---|---|
| PDF (text-based) | pymupdf text extraction | Font analysis — monospace spans flagged as code | pymupdf image extraction per page |
| PDF (image/scanned) | Vision reads whole page | Vision wraps code in ``` fences | Whole page sent to vision; individual images also extracted |
| Markdown clipping | Direct read | ``` fenced blocks | ![[wikilink]] and  references captured |
| Plain text | Direct read | ``` fenced blocks | n/a |
Images under 5KB (icons, bullets, decorations) are skipped automatically.
Asset file naming
raw/assets/{Source-Title}-p{page}-img{index}.{ext}
After extraction
Follow all steps in the Ingest operation defined in AGENT.md.
When not to use it
- →When only raw text extraction is needed without structured markdown
- →When images under 5KB (icons, bullets, decorations) are required
- →When the user does not want images saved to `raw/assets/`
Prerequisites
Limitations
- →Images under 5KB are automatically skipped
- →Output directory for markdown defaults to `wiki/sources/`
- →Images are always saved to `raw/assets/`
How it compares
This skill provides a structured, wiki-ready markdown output with inline image and code references, which is more organized and contextual than simple text or image extraction.
Compared to similar skills
richpdf side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| richpdf (this skill) | 0 | 3mo | Review | Intermediate |
| doc | 0 | 3mo | Review | Intermediate |
| feature-doc-updates | 0 | 2mo | No flags | Beginner |
| repo-markdown-quality | 0 | 1mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by 0r1xByte
View all by 0r1xByte →You might also like
doc
ansys
Write, review, or edit PyMechanical documentation. Use when writing reStructuredText (RST) files, Python docstrings, Sphinx configurations, example scripts, README files, or any doc content for the PyMechanical library. This covers NumPy docstrings, RST file formatting, Google developer style guide
feature-doc-updates
liudger
Ensure README and documentation are updated when adding features in python-bsblan. Use when implementing new behavior, parameters, API surface changes, or user-visible capabilities.
repo-markdown-quality
ventura8
______________________________________________________________________
pdf-creator
seaworld008
Create PDF documents from markdown with proper Chinese font support using weasyprint. This skill should be used when converting markdown to PDF, generating formal documents (legal, trademark filings, reports), or when Chinese typography is required. Triggers include "convert to PDF", "generate PDF",
zensical
the78mole
> **Scope**: Gives GitHub Copilot precise knowledge of the Zensical documentation setup in > this repository so it can make correct edits to `zensical.toml`, add pages, adjust navigation, > and help with theming without ever reverting to the legacy MkDocs workflow.
document-pro
bighardperson
文档处理技能 - 让 AI 能够读取、解析、提取 PDF、DOCX、PPT 等文档的关键信息。当用户要求分析文档、提取内容、总结报告时触发此技能。