nanaism/yomiyasu

This page introduces an external open-source repository. It is not an HDATF product.

What it does

An agent skill that rewrites AI generated Japanese into Japanese that reads naturally and carries more information per line. It targets practical documents such as technical articles, design and specification documents, pull request descriptions and internal reports, and is loaded into coding environments such as Codex, Claude Code and Cursor. The README argues that replacing banned words alone leaves the typical awkwardness in place.

How it helps ATF

ATF Works keeps documents, wiki pages and work records that are read in more than one language, and a draft an agent writes still needs editing before anyone reads it. Holding that editing as a skill with stated rules, rather than as one prompt, is a shape worth comparing.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• evondev/evondevKit
  A ui and ux skill for Claude Code that builds and polishes application screens such as dashboards, lists, tables, forms, settings and modals using the project's own component library and colours. The README marks it as beta, says it works well for light theme application screens after tests on seventy prompts across real projects, and notes that most testing so far used Vietnamese prompts.
• rehan-remade/universal-modder
  Skills, tools and shared knowledge for AI coding agents modifying user-owned PC games. The workflow covers code inspection, fal asset generation, testing in the running game and recording lessons for subsequent agents.
• kaankiziltug/logo-design-skill
  An agent skill covering logo-design briefs, concepts, SVG construction, testing and delivery. It includes a classified logo reference library and tools for audits and presentation sheets.
• steipete/agent-scripts
  Shared agent instructions, reusable workflow skills, portable helper scripts, and local validation hooks for multiple development workspaces.
• tigerless-labs/autoharness
  A self-learning skill layer for Claude Code. It distills skills from real sessions, merges same-scenario ones, updates them in use and prunes unused ones, touching only the skills it wrote.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.