By wquguru
Manage iterative development workflows with multi-PRD parallel support using commands to create PRDs, prepare, execute, and check status via an autonomous agent.
Exoshell (exoskeleton + shell) draws inspiration from Moltbot's origin story — the project that evolved from "Clawdbot" (a claw-wielding chatbot) to "Moltbot" (referencing a lobster's molting process). Just as lobsters shed their shells to grow, developers using Exoshell continuously upgrade their capabilities by adopting new AI-assisted workflows and Claude plugins. The name captures both the biological metaphor of growth through transformation and the technical reality of building a pluggable "shell" of development skills.
Exoshell(外骨骼 + 命令行环境)的灵感源自 Moltbot 的起源故事——这个项目从"Clawdbot"(挥舞钳子的聊天机器人)演化为"Moltbot"(指代龙虾的蜕壳过程)。正如龙虾通过蜕壳实现成长,使用 Exoshell 的开发者通过采用新的 AI 辅助工作流和 Claude 插件来持续升级自己的能力。这个名字既捕捉了"通过转变实现成长"的生物学隐喻,也体现了构建可插拔的开发技能"外壳"的技术现实。
/plugin marketplace add wquguru/exoshell
/plugin install <plugin-name>@exoshell
| Status | Description |
|---|---|
planned | Planned, not yet started | 已规划,尚未开始 |
wip | Work in Progress | 开发中 |
ready | Ready to use | 可以使用 |
| Plugin | Status | Description | Docs |
|---|---|---|---|
| ralph-ryan | wip | Ralph autonomous agent for iterative development with multi-PRD parallel support. Commands: /ralph-ryan:prd, /ralph-ryan:prep, /ralph-ryan:run, /ralph-ryan:status. | README |
MIT
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.
npx claudepluginhub wquguru/exoshell --plugin ralph-ryanLazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.