This project provides a curated marketplace of plugins, skills, and commands designed to enhance the capabilities of Claude Code. It targets users seeking to extend Claude Code's functionality with opinionated, personally-vetted tools for development workflows, analysis, and planning, offering a modular way to integrate advanced features.

How It Works

The core approach is a plugin system for Claude Code, organized as a marketplace. Users can add the umputun/cc-thingz marketplace and then install individual plugins (skills, commands, hooks) that reflect the author's daily workflow. This modular design allows users to pick and choose specific enhancements, integrating them directly into their Claude Code environment.

Quick Start & Requirements

• Primary install: Add the marketplace via /plugin marketplace add umputun/cc-thingz, then install desired plugins (e.g., /plugin install brainstorm@umputun-cc-thingz). Manual installation involves copying files to ~/.claude/ directories.
• Prerequisites: Claude Code CLI, gh CLI (for review plugin), tmux, kitty, or wezterm terminal emulator (for interactive features like git-review and plan-annotate), and a configured $EDITOR (defaults to micro). OpenAI Codex CLI is required for the ask-codex skill.
• Links: No specific demo or documentation links are provided beyond the commands themselves.

Highlighted Details

• The review plugin offers comprehensive PR analysis (architecture, scope creep), interactive git diff annotation, and a strict writing style guide, utilizing gh CLI and git worktrees.
• The planning plugin facilitates structured implementation planning via interactive review loops and autonomous plan execution using isolated subagents, featuring an editor-based annotation tool (plan-annotate.py).
• The release-tools plugin automates release workflows, including semantic versioning, platform detection (GitHub/GitLab/Gitea), and auto-generated release notes from PRs/commits.
• The thinking-tools plugin provides analytical capabilities like consulting OpenAI Codex, performing dialectic analysis, and systematic root-cause investigation using the 5-Why methodology.
• The skill-eval hook enforces skill evaluation before every Claude Code response, ensuring available tools are considered.

Maintenance & Community

No specific details regarding contributors, sponsorships, or community links (e.g., Discord/Slack) are present in the provided README.

Licensing & Compatibility

The project is released under the MIT License, which is generally permissive for commercial use and closed-source linking.

Limitations & Caveats

Certain interactive features require specific terminal emulators (tmux, kitty, wezterm). Some skills have external dependencies like the OpenAI Codex CLI. The README notes that community contribution sources were not accurately tracked historically, potentially impacting attribution for older components. The collection is described as "unapologetically opinionated," reflecting the author's specific workflow.