此内容尚未提供您的语言版本,正在以英文显示。

Ralph Review Trio

插件已验证活跃

Sequential three-tier code review (Haiku surface → Sonnet logic → Opus deep), restart-on-fail. Battle-tested across hundreds of solo issues.

1 个 Skill 0 个 MCP

目的

To automate and standardize the code review process, ensuring code quality and adherence to standards before human review.

功能

Three-tier code review process
Automated surface, logic, and deep analysis
Restart-on-fail workflow
Structured RESULT block reporting
Agent-based review for multiple stages

使用场景

Automating pre-merge code quality checks.
Ensuring adherence to architectural and logic standards.
Validating code changes before human reviewer engagement.
Providing structured feedback on code quality.

非目标

Writing code or making changes directly.
Replacing human code review entirely.
Operating on work-in-progress branches.
Reviewing documentation-only changes in depth.

安装

/plugin install ralph-review-trio@davepoon-buildwithclaude

包含 1 个扩展

Skill (1)

Ralph Review Trio 技能

Run a sequential three-tier code review on a finished implementation branch — Haiku (surface) → Sonnet (logic) → Opus (deep). Restarts from Tier 1 on any tier failure. Use when a solo branch or PR is code-complete and you want structured pre-merge verification before human review.

质量评分

已验证

98 /100

1 day ago 分析

信任信号

最近提交5 days ago

GitHub 所有者 davepoon

星标2.9k

许可证MIT

网站buildwithclaude.com

状态

查看源代码

类似扩展

Karpathy Coder

100

Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.

插件

alirezarezvani

Autoresearch Agent

100

Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).

插件

alirezarezvani

Context7 Plugin

100

Upstash Context7 MCP 服务器，用于查找最新文档。直接从源代码存储库将特定版本的文档和代码示例拉取到您的 LLM 上下文中。

插件

upstash

Agents Design Experience

Agents for UI/UX design, accessibility, and user experience optimization

插件

davepoon

Plugin Development Toolkit

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

插件

anthropics

Review Agent Governance

Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.

插件

wshobson