Skip to content

Agent skills for files and documents

44 agent skills that read, write and convert files, PDFs, spreadsheets and documents. Each one shows what it can run and how to install it in Claude Code, Codex, Cursor and other agents.
  1. Expert-level Windows batch file (.bat/.cmd) skill for writing, debugging, and maintaining CMD scripts

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  2. Convert a text-based document to markdown following instructions from prompt, or if a documented option is passed, follow the instructions f

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  3. Two related workflows for a locally-cloned codebase, in one skill

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  4. Uploads a local file (screenshot, image, PDF, zip, video) to GitHub user-attachments, downloads GitHub user-attachments, and embeds local fi

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  5. Use when an outage, production incident, or significant service degradation has occurred and the team needs a blameless post-mortem / RCA do

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  6. Convert Markdown files to HTML similar to `marked.js`, `pandoc`, `gomarkdown/markdown`, or similar tools; or writing custom script to conver

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  7. Skill for using the command-line tool pdftk (PDFtk Server) for working with PDF files

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  8. Intelligent README.md generation prompt that analyzes project documentation structure and creates comprehensive repository documentation

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  9. Create, set up, or update the personal context portfolio: structured markdown files describing who you are, how you work, your teams, and yo

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  10. Process media files (video, audio, images, documents) using Transloadit

    • Open source
    • 41.3K GitHub stars
    • Design and media
  11. Update a markdown file section with an index/table of files from a specified folder.

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  12. Azure AI Document Intelligence SDK for Java (com.azure:azure-ai-documentintelligence)

    • Open source
    • 3.2K GitHub stars
    • Cloud and infrastructure
  13. Azure AI Document Translation SDK for batch translation of documents with format preservation

    • Open source
    • 3.2K GitHub stars
    • Files and documents
  14. Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence)

    • Open source
    • 3.2K GitHub stars
    • Cloud and infrastructure
  15. Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files

    • Open source
    • 1.2K GitHub stars
    • Files and documents
  16. Document and type a Sentry API endpoint

    • Open source
    • 1.2K GitHub stars
    • Files and documents
  17. Use when the user has a messy tabular data dump (CSV/TSV/parquet/Excel/JSON) and wants it iteratively cleaned to an inferred data contract —

    • Open source
    • 183 GitHub stars
    • Files and documents
  18. Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/r

    • Open source
    • 111 GitHub stars
    • Files and documents
  19. Run the full OpenTrace knowledge-graph pipeline over a folder or repo — index, clustering, highlight surfacing, and the markdown / graphml /

    • Open source
    • 111 GitHub stars
    • Files and documents
  20. This skill should be used when a PDF made with bidi2pdf (CLI, Ruby API or bidi2pdf-rails) is blank, half empty, unstyled, missing images or

    • Open source
    • 58 GitHub stars
    • Files and documents
  21. This skill should be used when a PDF needs more than one render call - waiting for an element, clicking something open, running a script, sw

    • Open source
    • 58 GitHub stars
    • Files and documents
  22. This skill should be used when writing or fixing RSpec specs that render PDFs or drive pages with bidi2pdf - asserting text, page count or i

    • Open source
    • 58 GitHub stars
    • Files and documents
  23. This skill should be used when a web page, a URL or an HTML file has to become a PDF with bidi2pdf's command line, including a PDF of a page

    • Open source
    • 58 GitHub stars
    • Files and documents
  24. A data analysis skill for understanding datasets, analyzing data, building data processing pipelines, and summarizing analytical results

    • Open source
    • 34 GitHub stars
    • Analytics and data
  25. 医疗票据整理助手,用于自动分类、OCR识别和信息抽取。当用户需要处理医疗票据时使用,支持文件夹或压缩包输入,自动分类存放到不同文件夹,抽取病历信息(住院日期、医院名称),生成发票汇总CSV表格。

    • Open source
    • 34 GitHub stars
    • Files and documents
  26. Import local files (PDF, Word, PowerPoint, Excel, images, video, scripts) from a staging inbox folder or explicit path into structured markd

    • Open source
    • 31 GitHub stars
    • Files and documents
  27. Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI

    • Open source
    • 30.2K GitHub stars
    • Marketing and SEO
  28. Mounts Cloud Storage buckets on Google Cloud as a POSIX file system with Cloud Storage FUSE (gcsfuse)

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  29. Use when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB ind

    • Open source
    • 4K GitHub stars
    • Design and media

See every kind of AI for files and documents: tools, agents, MCP servers and skills.Ranked: the best AI for files and documents.