Menu
Download a PDF from a URL and extract its full text โ ideal for research papers, reports, and documentation. Returns page count and extracted text.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Conduct a structured discovery interview to produce a precise, confirmed ProblemBrief.
Delegate complex, multi-file coding tasks to an autonomous coding agent that can iterate and self-correct. Uses Claude Code if ANTHROPIC_API_KEY is set, otherwise falls back to Gemini via generate_code + execute.
Produce a comprehensive, detail-preserving research report from all phase findings and agent evidence.
Execute arbitrary Python code in an isolated subprocess. Use for data transformation, statistical analysis, geospatial processing, knowledge graph modeling, ontology engineering, RDF serialization, data visualization, document parsing, and any computation task. Always print() results to capture them.
Download a dataset from a URL and inspect its actual contents โ schema, column types, shape, sample rows, and null counts. Supports CSV, Parquet, Excel, JSON, and JSONL. Use this to look inside a dataset, not just its landing page.
Navigate to and extract content from specific web URLs. Good for reading data portals, documentation, and landing pages.
| description | Download a PDF from a URL and extract its full text โ ideal for research papers, reports, and documentation. Returns page count and extracted text. |
| name | pdf_extraction |
| source | built-in |
| tags | ["pdf","research","papers","documents","extraction"] |
| tools | ["url_fetch"] |
Apply when the work item requires reading the actual content of a research paper, technical report, regulation document, methodology specification, or any content published as a PDF. Use when web_browse returns only a landing page or abstract and the full text is needed. Signals: "read the paper", "extract from the report", "check the methodology", "find the exact wording in".
Produce a citation block (title, authors, year, URL) and a structured extraction containing: relevant section names, verbatim quotes for all critical facts, and a plain-language summary of what the document contributes to the task.
