AI Agent Skills

Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.

LLMs and Machine Learning done easily

通过 COM 自动化操控 Adobe Photoshop 的 CLI harness。支持项目管理、图层操作、选区控制、文字编辑、图像调整和多格式导出。

WPS Office CLI — JSON数据驱动PPT自动生成 + 命令行操控WPS文字/表格/演示文稿

AI-assisted coding with Claude Code, Cursor, Copilot, Codex, Aider, or Windsurf. Use to build or debug generated code.

Awesome OpenClaw examples: 101 tested, real-world OpenClaw usecases built with ClawHub skills, runnable scripts, prompts, KPIs, and sample outputs.

Humanode Network node code.

Flow Playground. Browser-based IDE for writing, compiling, and testing Cadence smart contracts directly in a browser

Github Action to perform automated code review on pull requests

A modular rules & skills system for Claude Code — organize, share, and supercharge your AI coding workflow

A developer framework for building Discord Activities. Handles OAuth, proxying, and participant tracking so you can focus on what matters.

decode's Kitaru operator surface for headless replay and what-if — three-runs (observed / baseline-rerun / fork), CLI replay with --args/--overrides, checkpoint override…

Review code changes for bugs, security issues, performance problems, and style violations. Use when asked to review code, a PR, or recent changes.

Write a short implementation plan or a longer execution plan before coding. Use when starting new work, when a ticket needs clearer boundaries, when a change spans multi…