zjp1997720/zhijian-skills

Canonical source and governance toolkit for Zhijian AI public Agent Skills

What it solves

It provides a centralized, trusted source for installing specialized "Agent Skills"—modular capabilities that extend the functionality of AI agents, specifically focusing on Codex operations, workflow orchestration, and content processing.

How it works

The project acts as a canonical portfolio and registry. Users can use a command-line interface (npx skills add) to browse a catalog of sixteen predefined skills and install specific ones (like wechat-styler or codex-doctor) directly into their agent environment or harness.

Who it’s for

Developers and users of AI agents (particularly those using Codex) who need pre-verified, focused tools for tasks like model routing, knowledge system building, and editorial publishing.

Highlights

  • Diverse Skill Set: Covers areas including Codex control, model reasoning, information design, and content archiving.
  • Simplified Deployment: Allows for quick installation of specific skills via a single CLI command.
  • Integrated Management: Includes tools for auditing, disabling, and verifying local skills (codex-skill-admin).
  • Unified Registry: Maintains a single source of truth for versions, validation, and documentation for all bundled skills.

Related

  • Project
    DannyMac180/skills

    A collection of public AI agent skills, including tools for dynamic multi-agent workflows and personalized learning explanations.

  • Project
    KKKKhazix/khazix-skills

    A collection of standardized AI agent skills (instruction sets) for goal definition, disk cleanup, deep research, and project documentation maintenance.

  • Project
    jamditis/claude-skills-journalism

    A genuine open‑source repo that bundles reusable “Agent Skills” for Claude Code (and Codex) to help journalists and newsroom teams automate tasks such as fact‑checking, source verification, FOIA filing, data‑journalism, PDF design, and multi‑agent workflows. Install via Claude’s plugin commands or copy individual `SKILL.md` folders; the repo includes a catalog, docs site, and up‑to‑date skill set.

  • Project
    vercel-labs/agent-skills

    A collection of ready‑made “skill packs” for AI coding agents that add Vercel‑centric and front‑end best‑practice capabilities (cost audit, React/Next.js performance checks, UI/UX accessibility reviews, documentation style enforcement, one‑click Vercel deployment, etc.). Install with `npx skills add vercel-labs/agent-skills` and the agent will automatically apply the appropriate skill when you ask it to deploy, optimise, or review code.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills and workflows for AI agents to automate tasks ranging from content creation and 3D generation to complex software engineering.