ai-agents-skills

bggg-skills is a collection of independently installable Codex Skills for creative and operational work. It includes workflows for converting images into layered PSD files, rebuilding designs as editable PPTX decks, improving other skills, researching and processing TikTok content, and analyzing or tracking Amazon Sif keywords. Users copy or symlink only the skill directories they need into their Codex skills folder. Some workflows require additional Python packages listed within their own directories.

This collection gives compatible AI agents a staged workflow for film and television development, from screening source novels to analyzing plot structure, evaluating adaptation potential, planning vertical dramas, and drafting scripts. Its 31 skills are separated by creative task, while orchestration skills can split long text, coordinate analysis, and combine results. The package covers short-form vertical series, longer dramas, television, and film, but it is an instruction library for writing and evaluation rather than a video production application.

paper2anything packages five independent skills for turning an academic PDF into a PowerPoint deck, conference poster, single-page project site, Xiaohongshu post, or WeChat article. It is useful when a research team needs several dissemination formats from the same paper without rebuilding each workflow separately. Paper extraction uses MinerU credentials, and some rendering or visual-check paths also require local tools such as LibreOffice, Poppler, and Node.js.

This repository bundles two reusable agent skills rather than a single application. Blueprinter generates technical diagrams in a flat engineering-blueprint style with HTML and CSS. Brief initializes and operates a React/Vite report site, turns source material such as articles or codebase analysis into standalone reports, publishes them into the site, and starts a local preview. It is useful for extending an existing agent with repeatable diagramming and report-publishing workflows.