Pdf Reader
- 324 installs
- 18.1k repo stars
- Updated July 2, 2026
- rightnow-ai/openfang
pdf-reader is an OpenFang agent skill that extracts text, tables, forms, and document structure from PDF specs, contracts, and research papers for developers who need reliable PDF content analysis during scoping and requ
About
pdf-reader is a bundled OpenFang skill in the rightnow-ai/openfang repository, one of 60 pre-installed expert knowledge skills in the agent operating system. The skill acts as a PDF analysis specialist that preserves logical document structure including headings, sections, lists, and table relationships while distinguishing exact extracted text from interpretation. Developers reach for pdf-reader when scoping features, validating requirements, summarizing stakeholder PDFs, or preparing invoice, contract, and financial report data for Markdown, JSON, or CSV output. The skill flags unreliable extractions such as scanned images, maintains original ordering unless reorganization is requested, and pairs with OpenFang memory_store for semantic recall in RAG-style workflows.
- Text and layout extraction
- Multi-page document parsing
- Requirement summarization
- Table and section detection
- Source-grounded Q&A over PDFs
Pdf Reader by the numbers
- 324 all-time installs (skills.sh)
- +9 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #184 of 688 Office & Documents skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/rightnow-ai/openfang --skill pdf-readerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 324 |
|---|---|
| repo stars | ★ 18.1k |
| Last updated | July 2, 2026 |
| Repository | rightnow-ai/openfang ↗ |
How do you extract tables and structure from PDF contracts?
Extract text, tables, and structure from PDF specs, contracts, or research papers while scoping features, validating requirements, or summarizing stakeholder documents.
Who is it for?
Developers parsing PDF specifications, contracts, invoices, or research papers who need structure-preserving extraction before analysis or storage.
Skip if: Skip pdf-reader when source documents are already plain Markdown or JSON, or when only a quick one-line summary is needed without table fidelity.
When should I use this skill?
Trigger pdf-reader when the user uploads or references PDF specs, contracts, research papers, or reports needing text, table, or form extraction.
What you get
Structured text extractions, reconstructed tables, form field data, and Markdown, JSON, or CSV outputs with unreliable sections flagged.
- structured text extraction
- table data
- Markdown or JSON export
By the numbers
- Bundled among 60 pre-installed skills in the OpenFang agent operating system
Files
PDF Content Extraction and Analysis
You are a PDF analysis specialist. You help users extract, interpret, and summarize content from PDF documents, including text, tables, forms, and structured data.
Key Principles
- Preserve the logical structure of the document: headings, sections, lists, and table relationships.
- When extracting data, maintain the original ordering and hierarchy unless the user requests a different organization.
- Clearly distinguish between exact text extraction and your interpretation or summary.
- Flag any content that could not be extracted reliably (e.g., scanned images without OCR, corrupted sections).
Extraction Techniques
- For text-based PDFs, extract content while preserving paragraph boundaries and section headings.
- For scanned PDFs, use OCR tools (
tesseract,pdf2image+ OCR, or cloud OCR APIs) and note the confidence level. - For tables, reconstruct the row/column structure. Present tables in Markdown format or as structured data (CSV/JSON).
- For forms, extract field labels and their filled values as key-value pairs.
- For multi-column layouts, identify column boundaries and read content in the correct order.
Analysis Patterns
- Summarization: Provide a hierarchical summary — one-line overview, then section-by-section breakdown.
- Data extraction: Pull specific data points (dates, amounts, names, addresses) into structured formats.
- Comparison: When comparing multiple PDFs, align them by section or topic and highlight differences.
- Search: Locate specific information by keyword, page number, or section heading.
- Metadata: Extract document properties — author, creation date, page count, PDF version, embedded fonts.
Handling Complex Documents
- Legal documents: identify parties, key dates, obligations, and defined terms.
- Financial reports: extract tables, charts data, key metrics, and footnotes.
- Academic papers: identify abstract, methodology, results, conclusions, and references.
- Invoices/receipts: extract line items, totals, tax amounts, vendor info, and payment terms.
Output Formats
- Markdown for readable summaries with preserved structure.
- JSON for structured data extraction (tables, forms, metadata).
- CSV for tabular data that will be processed further.
- Plain text for simple content extraction.
Pitfalls to Avoid
- Do not assume all text in a PDF is selectable — some documents are scanned images.
- Do not ignore headers, footers, and page numbers that may interfere with content flow.
- Do not merge table cells incorrectly — verify row/column alignment before presenting extracted tables.
- Do not skip footnotes or appendices unless the user explicitly requests only the main body.
Related skills
Lark DocGenerate, update, and maintain structured documentation directly inside Lark/Feishu using natural language and agentic workflows.494kLark DriveLet their coding agents read, create, update and search documents stored in Lark (Feishu) Drive directly from prompts.493kLark SheetsConnect Claude, Cursor or other agents directly to Feishu/Lark spreadsheets for live data reads, writes, and structured automation.493kLark WikiGenerate, update, and sync structured knowledge bases inside Lark (Feishu) directly from code, specs, or agent output.493kLark WhiteboardGenerate, edit, and collaborate on visual diagrams and flowcharts directly inside Claude, Cursor or other agents.493kLark SlidesInstantly generate polished, professional slide decks from specs, roadmaps, or meeting notes using Lark/Feishu.493kHow it compares
Choose pdf-reader over generic file-read skills when PDF table reconstruction, form fields, and structure preservation matter for contracts or specifications.
FAQ
What PDF content types does pdf-reader handle?
pdf-reader extracts text, tables, forms, and structured sections from PDF documents, preserving logical hierarchy and distinguishing exact extracted text from agent interpretation or summary.
How does pdf-reader treat scanned or low-quality PDFs?
pdf-reader flags content that could not be extracted reliably, such as scanned image regions, instead of silently misaligning tables or inventing missing text.
What output formats does pdf-reader support?
pdf-reader can deliver extracted PDF content as Markdown, JSON, or CSV depending on whether the developer needs readable summaries, structured records, or tabular exports.