991 skills · sorted by relevance
Extract PDF text when the usual file reader returns errors or unusable output. Choose command-line tools or Python libraries for plain text, metadata, tables, and complex layouts, with checks for scanned or copy-protected documents.
Extract data from supplied spreadsheets and documents, check for missing or truncated content, and try alternative reading methods when needed. Results identify source files and clearly separate extracted facts from external information or estimates.
Extract text from PDFs when read_file fails or returns unreadable data. Use dedicated command-line tools or Python libraries to retrieve text and tables, preserve spacing where possible, inspect document properties, and validate the extracted content.
Extract text from local or downloaded PDFs using a sequence of tools. Try file reading, then pdftotext before a Python fallback, check readability, and document failures while clearly separating extracted content from knowledge-based additions.
Extract text from PDFs by checking each tool’s output and switching methods when needed. Guides agents from file reading to pdftotext and PyMuPDF, then checks readability, missing sections, and records extraction failures.
Extract PDF text when read_file returns unreadable binary content or little usable output. Try pdftotext with layout preservation, then use pdfplumber as an alternative when the command is unavailable or produces insufficient text.
Extract readable PDF text when read_file returns binary or image data. Check the filetype parameter, run pdftotext, a command-line text extractor, and inspect output and errors, with temporary file output as an alternative.
Extract readable text from PDFs when normal file reading returns garbled or unusable content. The workflow switches between extraction tools, checks the results, and includes optical character recognition for scanned pages when needed.
Extract text from local PDF files with pdftotext or PyMuPDF, a Python library for reading PDFs. Convert individual files or batches into text files that an agent can read for summarization, analysis, or further data extraction.
Extract plain text from Word DOCX files using shell commands first, then switch to Python's built-in ZIP reader if extraction fails or returns nothing. Supports text output without requiring the external python-docx package.
Analyze a monolithic codebase before splitting it into modules or services. The skill inventories components, examines duplication, hierarchy, and dependencies, then proposes groupings aligned with business domains, with optional checks against business terminology and boundaries.
Organize existing code components into business areas to prepare for service separation. Produce domain maps, component assignment tables, and refactoring plans that align namespaces, the naming structure used to organize code, with business responsibilities.
Check how an agent handles file saves, uploads and archive extraction. Test whether user supplied paths can escape the intended directory, then report confirmed unsafe handling with response evidence and suggested safeguards.
Extract timestamped text from a YouTube video's transcript panel and turn it into summaries, chapter outlines, X threads, blog articles, or notable quotes. Use existing captions to create readable material from video content.
Collect posts from X search, profile, individual post, and list URLs. Organize text, authors, engagement counts, media, hashtags, and mentions into a consistent dataset, with support for collecting additional pages.
Collect product names, prices, images, ratings, and links from e-commerce listings or keyword searches. Apply filters such as price range and brand, and gather structured product records across multiple pages.
Collect product details from public shopping pages using a URL, keyword, or product identifier. Extract prices, stock status, images, ratings, and variants into structured data for product research, comparisons, and catalog collection.
Search Google Maps by business type and location, collect business details, then visit listed websites to find public emails, phone numbers, and social profiles. Merge the results into a contact dataset for local business research and prospect lists.
Automates website navigation, form entry, and information extraction through browser commands. Helps test web applications, reuse saved login state, and capture screenshots, PDFs, or recordings of browser workflows for inspection and documentation.
Assess iOS apps from IPA acquisition through file inspection and runtime testing. The skill helps uncover embedded credentials, insecure network settings, and app link handling issues using tools such as Frida, objection, and binary analysis utilities.
Coordinate meta-analysis, which combines results across studies, from data extraction to reporting. Validate effect sizes, check for duplicates and implausible values, and assess how individual studies or publication bias affect the combined result.
Universal Meta-Analysis Codebook v2.2 - AI-Human collaboration for meta-analysis data extraction. 4-layer design: Identifiers, Statistics, AI Provenance, Human Verification. Integrates with C5/C6/C7 agents and Category I systematic review pipeline. Triggers: meta-analysis, codebook, data extraction, Hedges g, effect size
The English summary is being prepared. Showing the original description.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
The English summary is being prepared. Showing the original description.
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract insights", "mine this", "process this".
The English summary is being prepared. Showing the original description.