kangarooking/kangarooking-skills

My custom AI Agent skills

What it solves

This repository provides a collection of structured, reusable "Agent Skills"—pre-defined workflows that allow AI agents to perform complex, multi-step tasks across various domains like image generation, content creation, and project engineering without needing manual, step-by-step prompting for every session.

How it works

Each skill is stored in a dedicated directory containing a SKILL.md file that defines the execution flow. Some skills include supporting scripts, reference materials, and reusable templates. These skills are compatible with the Agent Skills open standard and can be installed directly into agents like Claude Code and Codex, or manually copied into their respective skill directories.

Who it’s for

  • AI Power Users: Those using Claude Code, Codex, or other standard-compliant agents to automate repetitive complex tasks.
  • Content Creators: People looking for automated workflows for social media growth, viral topic research, and multi-platform content production.
  • Designers: Users needing structured AI workflows for 3D generation, brand identity systems, and visual design.
  • Developers: Engineers wanting to implement structured "Plan-Build-Verify" frameworks for long-term AI development projects.

Highlights

  • Diverse Skill Set: Includes 16+ skills covering image generation (GPT-Image-2), 3D model creation (Tencent Hunyuan), and social media monitoring (X/Twitter).
  • Cross-Platform Content Tools: Workflows for finding viral topics and generating high-potential titles for platforms like YouTube, B站, and X.
  • Agent Engineering Frameworks: Tools like harness-engineering and task-harness to break down long tasks into traceable and verifiable systems.
  • Multi-Modal Capabilities: Skills for downloading videos from multiple platforms and converting them into multi-modal copy using ASR and subtitles.

Related

  • Project
    chujianyun/skills

    A Chinese‑language repo that bundles dozens of reusable “Agent Skills” – small, documented plugins for Claude Code and similar LLM‑agent platforms. Skills cover wiki look‑ups, prompt optimisation, career assessments, diagram generation, document interpretation, audio‑to‑text, image watermarking, web‑scraping, and service run‑books. They are organized under `skills/`, registered in `config/skills.json`, and installed via Claude Code’s marketplace, an installer agent, or the `openskills` CLI.

  • Project
    mxyhi/ok-skills

    OK Skills is a library of 31 ready‑to‑use *skill packs* for AI coding agents (Codex, Claude Code, Cursor, etc.). Each skill lives in its own directory with a `SKILL.md` that tells the agent how to run the underlying script (e.g., browser automation, docs lookup, planning, design). Install by cloning into `~/.agents/skills` (or the Autohand equivalent), copy the `CLAUDE_AGENTS.md` sections into your agent’s config, and then ask the agent to “Use <skill‑name> …”. The repo provides categories such as Research, Planning, Automation, Frontend, and Utilities, and serves developers who want portable, repeatable AI‑agent capabilities instead of ad‑hoc prompts.

  • Project
    KKKKhazix/khazix-skills

    A collection of structured instruction sets for AI agents that provide specialized workflows for goal setting, disk cleanup, research, and writing, following the Agent Skills open standard.

  • Project
    davidondrej/skills

    A curated set of prompt‑based skill definitions for AI coding, research, and ops agents, organized by workflow type and ready to be loaded into Cloudroom or similar agent runtimes.

  • Project
    DannyMac180/skills

    A collection of reusable AI agent skills and plugins for Claude Code and Codex, enabling advanced supervised workflows, mod management, and personalized learning.