Back to directory

Illustrated-Agent-Skills

Illustrated-Agent-Skills is the companion resource repository for a Chinese book about using AI agent skills productively, containing the book's appendices, full writing-workflow skills, chapter example code and data, and the skills used to generate the book's own illustrations.

Illustrated-Agent-Skills

Illustrated-Agent-Skills accompanies a Chinese book about using AI agent skills for productivity, collecting material too long for print or better suited to online reference: the book's full appendices, complete writing-workflow skill files, chapter example code and data, and the skill used to generate the book's own illustrations.

The appendices cover a glossary of English-Chinese terminology, an installation guide for platforms such as Claude.ai, Claude Code, VS Code and OpenCode, a list of Chinese-market model API platforms, and full versions of four writing-workflow skills the author uses daily. The skills directory includes ready-to-install skills for illustrating a manuscript, analyzing source material, turning interview recordings into structured writing, and generating outline drafts.

One included skill, for adversarial multi-round manuscript polishing, is marked by the author as a learning exercise only, since it depends on sub-agent context isolation that current agent platforms do not support.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.