By scientist-hq
Team-blessed RX workflow commands: architect, implement, review, test, qa, pr, commit, and more. The canonical Scientist.com agentic-development command set for the RX Rails monorepo.
You are a Senior Rails Architect with 20+ years of experience building marketplace platforms. Your expertise is in Rails application design, database modeling, and system integration for the RX (Research Exchange) platform.
You are a Senior Rails Debugger with 20+ years of experience diagnosing production issues in large marketplace applications. You are methodical, evidence-driven, and you never guess — you trace.
You are a Dependency Upgrade Expert who makes version bumps safe and boring. You analyze Dependabot PRs (or manual version bumps) and produce a confident MERGE or HOLD verdict by cross-referencing breaking changes against actual codebase usage.
You are creating clean, well-organized git commits from the current working tree changes. Your goal is to break changes into small, logical, bite-sized commits that each address a single concern.
You are a Senior Rails Mentor and codebase historian. Your job is to teach and explain — helping developers deeply understand the code they're working with, how it fits into the broader system, and why it exists the way it does.
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Scientist.com's central catalog of Claude Code skills, slash commands, and agents.
The repo serves two distribution pipelines side by side:
| Tree | Purpose | Install |
|---|---|---|
skills/ | Knowledge skills (sacred rules, patterns, workflows). Multi-agent — works with Claude Code, Cursor, Cline, Codex, and 50+ others via skills.sh. | npx skills add scientist-hq/skills |
plugins/ | Claude Code-specific plugins (slash commands, agents, hooks). Each plugin's commands are namespaced as /<plugin>:<command> automatically. | /plugin marketplace add scientist-hq/skills then /plugin install <plugin>@scientist-hq-skills |
Use whichever fits your tools. Most Claude Code users install both.
skills/)npx skills add scientist-hq/skills
Drops rx and sentry knowledge packages into ./.agents/skills/ in your current project. Multi-agent compatible.
plugins/)In a Claude Code session, register the marketplace once and install the plugins you want:
/plugin marketplace add scientist-hq/skills
/plugin install rx@scientist-hq-skills
/reload-plugins
After install, commands appear in the / menu as /<plugin>:<command>. The rx plugin's commands are invoked as /rx:architect, /rx:pr, /rx:commit, etc.
rx — Team-blessed RX workflow commands (architect, implement, review, test, qa, pr, commit, bug, explain, explore, infra, learn, post-review, recap, bump). The canonical Scientist.com command set for the RX Rails monorepo. Most devs working in RX should install this.rranauro — Worktree-first RX ticket lifecycle: architect, start-ticket, start-review, wait-copilot, update-main-pr, review-copilot, cleanup-worktree, worktree-gc. Personal-share plugin, opt-in — install if this workflow style suits you.Full list lives in .claude-plugin/marketplace.json.
Plugin commands are always namespaced as /<plugin>:<command> automatically by Claude Code. The canonical demonstration: both rx and rranauro ship an architect.md command — same filename, very different agents — and they coexist without collision:
rx/commands/architect.md → invoke as /rx:architect (team's Senior Rails Architect)rranauro/commands/architect.md → invoke as /rranauro:architect (personal architectural-discussion variant)~/.claude/commands/architect.md → still invoke as /architect (no collision with either plugin)A plugin cannot claim the bare /foo slot — only files in ~/.claude/commands/ or a project's .claude/commands/ can. That makes collisions structurally impossible and lets developers keep their own defaults un-namespaced while sharing freely under their plugin namespace.
Plugins fall into two governance tiers. The distinction lives in the review process and the naming convention, not in directory prefixes.
plugins/rx/, plugins/sentry/)For commands or agents the whole team should be able to install. Conventions:
rx, sentry, infra, …)./plugin install.plugins/rranauro/)For commands an individual developer wants to share without making them team policy. Conventions:
rranauro, …) — short, easy to type, no prefix.skills/ — multi-agent knowledge skillsKeep using the existing skills.sh structure (skills/<name>/SKILL.md + subfiles). Knowledge artifacts that should work across agents belong here, not in a plugin.
plugins/<plugin-name>/
.claude-plugin/
plugin.json # name, description, author
commands/ # /<plugin>:<command-name>
foo.md
agents/ # optional
skills/ # optional — plugin-private skill content
hooks/ # optional
See plugins/rx/ for the canonical team-plugin example and plugins/rranauro/ for the personal-share pattern.
npx claudepluginhub scientist-hq/skills --plugin rxWorktree-first RX ticket lifecycle commands: architect → start-ticket → review → cleanup. Personal-share plugin, opt-in, not team policy.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses