MCP App StoreMCP App StoreThis skill equips agents to work with .pptx PowerPoint files: extract text, generate thumbnails, unpack raw OOXML, edit templates, and create new presentations using pptxgenjs or Python tooling. It includes QA workflows (convert to images, visual inspection prompts), design guidance, and scripts for common tasks (text extraction, thumbnails, unpacking).
Trigger when the user mentions slides, decks, presentations, or supplies a .pptx file and asks to read, summarize, edit, combine, or create presentations. Use it for template-based edits, conversions, or when visual QA of slides is required.
Agents that can run Python/NPM and file-conversion tooling work best (Claude Code, Codex/Copilot-style agents, CLI-enabled assistants).
A comprehensive PPTX skill for creating, reading, editing, and QA-ing PowerPoint presentations. Includes 8 scripts for slide manipulation, text extraction, thumbnailing, cleaning orphaned resources, and HTML-to-PPTX conversion. SKILL.md is exceptionally well-written with design guidance and QA workflows. Most scripts failed to run due to missing Python dependencies (python-pptx, defusedxml) which are expected for this type of tooling. No security concerns found.
python-pptxdefusedxmlPillowplaywrightsharp (npm)Well-designed skill with thorough SKILL.md covering design principles, color palettes, typography, and a rigorous QA workflow. Uses defusedxml for safe XML parsing — good security practice. Scripts are functional tools with proper argparse CLIs. The JS file (html2pptx.js) was skipped by the runner but appears well-structured with input validation and error reporting. No security issues detected.
Gmail Automation via Rube MCP
Automate Gmail actions (send, reply, search, labels, drafts, attachments) through a Rube MCP Gmail toolkit with best-practice tool sequences and pitfalls noted.
Nano Banana 2 — Gemini 3.1 Flash Image Preview
Run Google Gemini 3.1 Flash Image Preview via inference.sh CLI: text-to-image, image editing, multi-image input, and Google Search grounding.
PDF Processing (OpenAkita)
Process PDFs: extract text and tables, merge/split/rotate pages, OCR scanned PDFs, manipulate metadata, protect or watermark files, and generate new PDFs progra
XLSX / Spreadsheet Skill
Handle creation, editing, cleaning, and conversion of spreadsheet files (.xlsx, .xlsm, .csv, .tsv) with robust formulas, formatting, and recalculation workflows
Baidu Search
Enable agents to perform real-time Chinese web and image searches via Baidu Qianfan API, including time filtering and relevance/authority signals.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
FastAPI Project Templates
Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
mog — Microsoft Ops Gadget
Command-line toolkit for Microsoft 365 (Mail, Calendar, OneDrive, Contacts, Tasks, Word, PowerPoint, Excel, OneNote) with slug and multi-account support.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
PPT as Code
Creator-first workflow to plan and build HTML-first presentations with staged modes (quick/basic/advanced), optional PPTX export, and clear QA and image plannin
Doc Cleaner
Convert PDF, DOCX, XLSX and text files into clean, structured Markdown with CJK and table support; supports offline or AI-enhanced modes.
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat