suyuan2022/suyuan-skill

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

What it does

A collection of Claude Code and Codex skills covering output refinement, independent code reviews, task triage, visual HTML explanations, and local cleanup audits.

How it helps ATF

Harness can reference independent review and task-triage skill structures. LabChin can reference the visual explanation format for research communication.

License

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

More in this category

• brycewang-stanford/Auto-Empirical-Research-Skills
  A catalog of agent skills for empirical social-science research, spanning data cleaning through paper submission. Its README describes skill search by method, stage, language, and license, alongside evaluation and benchmark resources.
• elvisun/newsjack
  A collection of agent skills for public-relations work. The README describes news monitoring, topic and competitor searches, story-origin checks, relevance filtering, and triage of potential publicity opportunities.
• ChenLiu-1996/figures4papers
  A collection of Python scripts for figures published at top AI conferences and journals, covering bar, radar, line, concept and trend plots, packaged with a scientific figure making skill and reference docs.
• Tencent/teamai-cli
  TeamAI is a CLI that manages a team's skills, rules, MCP settings and knowledge across AI agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. Admins publish to a shared git repo, and members' sessions pull the updates.
• davila7/claude-code-templates
  A CLI and web catalog that installs ready made Claude Code components, including agents, commands, settings, hooks, MCP integrations and project templates, and also monitors Claude Code.

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.