12-skill space engineering pack: propulsion, orbital mechanics, structures, thermal, satellite comms, power systems, GNC, payloads, mission architecture, ground systems, launch operations, and space environment. Synthetic NASA for Claude Code.
Adversarial multi-model code review and model dispatch. Orchestrates Claude, Codex CLI, and Gemini CLI for cross-examined code review with 5 specialized reviewers.
★not rated 21 15d agoA
tokens not measured
originalMIT
Comprehensive toolkit for creating production-ready Claude Code resources: agents, skills, plugins, commands, hooks, MCP tools, MCP servers, and patterns. Expert guidance with templates, examples, and best practices following Anthropic specifications.
★not rated 21 15d agoA
tokens not measured
originalMIT
Language-specific development experts covering 13 programming languages including Python, TypeScript, JavaScript, Go, Rust, C++, and more. Includes refactoring specialist.
★not rated 21 15d agoA
tokens not measured
originalMIT
The ultimate Claude Code toolkit for Unity game development. Production-ready agents, commands, skills, and safety hooks for building mobile games with natural language.
★not rated 21 4mo agoA
tokens not measured
originalMIT
UI/UX Design Plugin - Visual fidelity from Figma/mockups, design system enforcement, React UI prototyping with live browser gallery, pattern memory, and brand icon asset generation.
★not rated 21 20d agoA
tokens not measured
originalMIT
Developer tooling setup and management (SOPS secrets encryption, Claude Code environment setup, multi-ecosystem quality stack for JVM/Node.js/Python, Taskfile task runner setup and audit, Tilt local Kubernetes development setup and audit, browser-companion live-preview server for agent↔browser workflows via the…
★not rated 21 20d agoA
tokens not measured
originalMIT
Autonomous AI research harness for Claude Code. Plan -> Research -> Build -> Audit -> Run -> Assess -> Codify, with adversarial subagent review, a taste corpus, a [LEARN] memory system over SQLite/FTS5, and a spot-first GPU procurement router.
★not rated 21 1mo agoA
tokens not measured
originalApache-2.0
Reach an away user by phone from a live Claude Code session: the agent (or the Stop hook) phones you, you answer by voice, and the idle session wakes and acts on your spoken reply.
★not rated 21 2mo agoA
tokens not measured
originalApache-2.0
Two-way voice phone calls plus tiered alerts for your AI agent, over free self-hosted SIP. The agent rings your phone and talks to you when it needs a decision, and it is presence-aware so it only calls when you are away from the keyboard. Runs the engine in Docker, so there is no local build.
★not rated 21 2mo agoA
tokens not measured
originalApache-2.0
Clone any website with a team of AI agents — pixel-perfect UI clone plus reverse-engineered architecture docs. Built on Claude Code's dynamic Workflow engine with an unskippable test gate; fully pausable and resumable.
★not rated 20 2mo agoA
tokens not measured
originalMIT
52 SEO commands for Claude Code — site audits, Ahrefs backlinks, GSC analytics, SERP research, content briefs, technical SEO, schema validation, and more.
★not rated 20 2mo agoA
tokens not measured
originalMIT
Makes Claude write like a sharp, plain-spoken human. Loads 29 researched anti-AI-writing patterns at session start and checks every file it writes for tells.
★not rated 20 15d agoA
tokens not measured
originalMIT
An MCP plugin that connects AI agents to Wildberries and Ozon seller accounts through their Seller APIs. It supports marketplace work such as sales, inventory, prices, finances, and reviews, with schema-based methods, pagination, multiple accounts, and safeguards for write actions.
★not rated 20▲
+3 1mo agoA
tokens not measured
originalMIT
Zero-code bug triage for PMs. Checks in parallel whether old bugs still reproduce, reviews the verdicts, and syncs results back to Jira, Linear, or GitHub Issues.
★not rated 19 13d agoA
tokens not measured
originalMIT
Stress-test a high-stakes decision with a council of up to 17 personas that debate, rebut, and return a verdict. For product direction, strategy, and career calls where being wrong is expensive.
★not rated 19 13d agoA
tokens not measured
originalMIT
Customer discovery that does not invent quotes. Turns one interview into a structured snapshot with every quote verified against the transcript, then runs the full cycle: frame, interview, synthesize, package.
★not rated 19 13d agoA
tokens not measured
originalMIT
★not rated 19 3mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: