alchaincyf/nuwa-skill

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

What it does

nuwa-skill is an agent skill that takes a person's name and runs research, distillation and verification to capture their mental models, decision heuristics and expression style. The agent can then answer questions using that person's thinking framework.

How it helps ATF

It mainly imitates how a person thinks, so its link to our products is loose. Its flow from a name to research and verification could be a small reference for how LabChin moves from a question to searched sources.

License

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

More in this category

• android/skills
  A set of Agent Skills, written as SKILL.md files, that guide agents on Android development tasks following developer.android.com guidance. It focuses on workflows where evaluations show LLMs underperform, and skills are added with the Android CLI.
• JuliusBrussee/caveman
  A skill and proxy for AI coding agents that make the agent talk in short, caveman-style sentences to use fewer tokens. It can also wrap other agents.
• google/skills
  A collection of Agent Skills for Google products, including Google Cloud. Skills cover topics such as authentication, onboarding, solution architecture, building and deploying AI agents, multi-agent security and hybrid search with AlloyDB, and can be chosen individually at install.
• addyosmani/agent-skills
  A set of engineering skills for AI coding agents that packages workflows and quality gates for each development phase. Slash commands such as /spec, /plan, /build, /test, /review and /ship activate the matching skills.
• composio-community/awesome-codex-skills
  A curated list of Codex skills for automating workflows in the Codex CLI and API, grouped into areas such as development tools, productivity, communication and data analysis, with a script that installs a chosen skill.

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.