Skill UI

Specialized skill to rewrite and humanize AI-generated natural language files (like notes or documentation). It removes common 'AI-isms' such as sycophantic openings, stock vocabulary, over-explaining, and excessive signposting. Users can choose between a fast, deterministic regex cleanup or a deep LLM rewrite (default mode) using Claude to enhance burstiness and match a natural human voice, all while strictly preserving code blocks, URLs, and headings.

A powerful plugin enabling Claude Code to delegate complex tasks to external AI CLIs (such as OpenAI Codex or Google Antigravity/Gemini) without exiting the conversation. It supports multi-model workflows, allowing users to seek a second opinion, cross-check deep analysis, or delegate side tasks (like research or code review). The core value is that Claude synthesizes the raw outputs, providing a critical review and reconciliation of findings across all consulted models.

Context Kit is an external framework designed to organize and manage personal, durable context data (like identity details, memories, and domain knowledge) into secure Markdown artifacts. It helps users set up robust knowledge bases for coding agents (e.g., Claude Code), guiding them on best practices for data privacy, local storage, and safe integration, while preventing sensitive data leaks.

A sophisticated presentation template designed for technical content, mimicking the clean, professional aesthetic of GitHub blogs or product changelogs. It features a dark GitHub-dark background, vibrant purple and blue radial ambient lighting, a multi-color gradient title, and dedicated GitHub-style code blocks. Perfect for tech talks, deep-dive tutorials, and developer documentation.

This guide details how to effectively delegate complex, multi-step tasks to various specialized AI agents (Codex, Pi, Claude, Hermes). It covers best practices for maintaining conversation context, handling TUI prompts (e.g., avoiding newlines, using quotes), techniques for reliable polling, and choosing the optimal agent for coding, design, or general purpose work. Essential for advanced AI workflow automation.

This guide details the comprehensive workflow for distributing a single AI skill across various local agent skill directories (Codex, Claude, Pi, Hermes). It addresses canonical locations, symlink management, and specific synchronization commands to ensure that all agents detect the latest skill version while correctly navigating common development pitfalls.

This skill helps developers create highly focused, folder-specific documentation (`CLAUDE.md` and `AGENTS.md`). It systematically analyzes all files in a target directory to extract project purpose, operational constraints, naming conventions, and critical decisions. This deep context ensures that future AI agents (like Claude or Codex) operate with localized knowledge, preventing them from relying on global, generalized instructions and improving their accuracy in that specific domain.

A lightweight CLI tool for systematically comparing various coding AI agents (such as Claude Code, Aider, and Codex) head-to-head. It measures crucial metrics—pass rate, API cost, execution time, and consistency—on reproducible tasks defined via YAML manifests. Use this to objectively select the best agent for your codebase or to validate model updates before production deployment.

Design a persistent multi-agent operating system on Claude Code with kernel routing, specialist agents, slash commands, file-based memory, and scheduled automation for long-lived projects.

Transforms Claude Code into a fully autonomous agent with persistent memory, scheduled operations, computer use, and task queueing. Replaces standalone agent frameworks using native crons, dispatch, MCP tools, and memory. Ideal for continuous automation and self-directed agent loops.

This utility provides garbage collection for Claude Code configurations. It periodically scans various directories—including skills, memory files, hooks, permissions, and caches—to identify orphaned, stale, or redundant configuration items. Crucially, the process is designed to be non-destructive, always requiring explicit human confirmation for every deletion to ensure a safe, audited cleanup process.

Guides the installation, update, and reconfiguration of ECC within Claude Code, Codex, and Kimi, respecting each harness's native plugin, scope, and hook capabilities. Provides interactive wizards adapted to the current harness, with dry-run previews, single confirmation, and verification.