REPO REVIEWS

Context7 is an MCP server that injects up-to-date library documentation directly into your LLM's context, solving the stale training data problem that makes AI code assistants hallucinate APIs. I spent time with the repo to figure out if the hype is justified or if this is another vibe-coding gimmick.

The claude-code-expert skill from raintree-technology gives Claude deep context about its own CLI, hooks, MCP, and skill system — useful if you're building or debugging Claude Code configurations. It's part of a larger 40+ skill framework that's worth understanding before you install.

GSD is a meta-prompting and spec-driven development system for Claude Code that tries to solve context rot and keep AI-assisted development coherent across long sessions. With 54K stars and active daily commits, it's worth an honest look at whether the hype holds up.

This skill wires Claude Code directly into your running Chrome instance via the claude-in-chrome MCP extension, letting agents navigate pages, fill forms, and execute JavaScript without spinning up a headless browser. If you're already using Crewly or just want Claude to stop asking you to manually do web tasks, it's worth a look.

gstack is a collection of 23 Claude Code slash commands that simulate specialized engineering roles — CEO, designer, QA lead, security officer. With 69K stars and a compelling pitch, I dug into whether it's genuinely useful or just well-marketed dotfiles.

The claude-codex skill lets you delegate prompts from Claude Code to your local Codex CLI — second opinions, code review, implementation runs — without touching credentials. It's a narrow, well-scoped bridge between two AI coding tools, and it mostly does what it says.

gstack is a collection of 23 Claude Code slash commands that simulate a virtual engineering team — CEO, designer, QA lead, security officer, and more. With 69K stars and active development, I dug into whether this is genuinely useful tooling or just well-marketed prompt engineering.

The claude-codex skill bridges Claude Code and the Codex CLI, letting you delegate tasks, run second-opinion reviews, and pipe results back into your workspace without leaving your current session. Here's whether it's actually worth adding to your stack.

Pruna is a Python framework that wraps quantization, pruning, compilation, caching, and more into a single unified API for optimizing ML models. I dug into the repo to figure out whether it's genuinely useful or just another abstraction layer you'll regret adding.

The claude-code skill from InternScience promises Claude Code integration with subagent management and AI-assisted coding workflows. After digging into the actual implementation, here's what you're really getting — and whether 157 stars means anything.