Format Conversion

nutrient-document-processing skill for PDF processing and document automation with the Nutrient DWS API. Convert, OCR, extract, redact, sign, watermark, and fill files like PDFs, DOCX, XLSX, PPTX, HTML, and images.

The xlsx skill helps agents read, edit, repair, create, and convert .xlsx, .xlsm, .csv, and .tsv files when the required deliverable is a spreadsheet. It is strongest for template-preserving updates, formula-safe workbook edits, messy tabular cleanup, and practical spreadsheet workflows backed by repo scripts for packing, validation, and recalculation.

The pdf skill guides PDF Processing tasks like text extraction, merge and split operations, rendering pages to images, and PDF form workflows. It is especially useful for checking fillable fields, extracting form metadata, and validating non-fillable form layouts with scripts.

pdf skill for PDF Processing workflows: extract text and metadata, split or merge files, render pages, create PDFs, and fill forms using SKILL.md, forms.md, reference.md, and helper scripts.

html-to-image-automation helps agents convert HTML to images through Composio's Html To Image toolkit via Rube MCP, using schema-first tool discovery before execution.

convertapi-automation helps Claude run ConvertAPI format-conversion workflows through Composio Rube MCP, with tool discovery, connection checks, and schema-based execution.

conversion-tools-automation helps Claude agents run Format Conversion workflows with Rube MCP and Composio Conversion Tools by discovering live schemas before execution.

cloudconvert-automation helps agents run CloudConvert format conversion via Rube MCP by searching live tool schemas first, checking the cloudconvert connection, and avoiding stale API fields.

defuddle extracts clean markdown from web pages with the Defuddle CLI, removing clutter for research, docs, and articles. Use it for standard HTML pages, install with npm, and skip URLs ending in .md.

json-canvas helps create and edit valid .canvas files for Obsidian-style boards, with correct nodes, edges, IDs, coordinates, groups, and references.

baoyu-youtube-transcript helps extract YouTube transcripts, subtitles, and cover images from a URL or video ID. It supports language selection, translation, markdown or SRT output, cached reformatting, and a fallback from InnerTube API to yt-dlp for more reliable transcript retrieval.

baoyu-url-to-markdown converts live URLs to Markdown with a vendored baoyu-fetch CLI using Chrome CDP, site adapters, and generic fallback. Review Bun runtime needs, first-time EXTEND.md setup, and usage for X, YouTube, Hacker News, and rendered pages.

baoyu-markdown-to-html converts Markdown into styled HTML for WeChat-style publishing. It supports themes, code highlighting, math, PlantUML, footnotes, image handling, and optional link citations, with runtime execution through bun or npx -y bun.

baoyu-format-markdown formats plain text or messy Markdown into cleaner, publishable Markdown while preserving meaning. It repairs frontmatter, headings, lists, code blocks, quotes, and CJK spacing, making it useful for Format Conversion without rewriting content.

baoyu-danger-x-to-markdown converts X posts, threads, and some articles into Markdown with YAML front matter. It uses scripts in `scripts/` with `bun` or `npx -y bun`, supports cookie-based access and consent flow, and fits repeatable Format Conversion workflows better than a generic prompt.

dummy-dataset generates realistic test data in CSV, JSON, SQL, or Python script form. It helps with mock datasets, demos, database seeding, QA, and data cleaning by letting you define columns, row counts, and constraints for believable sample records.

web-to-markdown is a Format Conversion skill that turns live web pages into clean Markdown through the local web2md CLI, using a Chromium-family browser for JS-rendered pages, interactive flows, and batch URL conversion. It only runs when explicitly invoked by name.

The speech-to-text skill transcribes supported audio files into plain text, with options for timestamps, speaker labels, and JSON output. It is designed for practical speech-to-text usage in repeatable workflows, including interviews, meetings, podcasts, lectures, and automation tasks where consistent transcription matters.

read-file helps an agent read and inspect CSV, JSON, Parquet, Avro, Excel, SQLite, spatial files, or remote URLs with DuckDB. Use it to preview rows, check schema, profile data, and answer what’s in this file. It’s best for read-file usage on real data artifacts, not source code.

The kreuzberg skill helps you install and use Kreuzberg for document extraction across 91+ formats, including PDFs, Office files, images, HTML, email, and archives. It covers Python, Node.js/TypeScript, Rust, and CLI workflows for OCR, tables, metadata, batch processing, and practical parsing guidance.

The transcribe-video skill turns video or audio files into .srt, .vtt, and .txt outputs with AWS Transcribe. Use it for transcribe-video usage when you need captions, a searchable transcript, or a clean text version of spoken content. It also fits transcribe-video for Format Conversion workflows.

tzst is a CLI-focused skill for installing, creating, listing, testing, and extracting .tzst or .tar.zst archives with the right commands, flags, and safe defaults. Use it for tzst install, tzst usage, filtering, conflict handling, streaming, and File Automation workflows.

pymatgen is a Python materials science toolkit for crystal structures, phase diagrams, electronic structure, and file conversion. This pymatgen skill helps with scientific workflows using CIF, POSCAR, VASP, and Materials Project data.

The pdf skill is a practical guide for PDF Processing when you need to read, extract, transform, or create PDF files in a workflow you can ship. It covers text extraction, merging, splitting, rotation, form filling, encryption, image extraction, and OCR for scanned PDFs. Use it when you need a repeatable pdf guide instead of a one-off prompt.