rpi-review

Review implementation plans and research documents against codebase evidence with severity-classified findings.

5|Updated Sep 24, 2017
One-click install
npx skills add https://github.com/madyankin/dotfiles --skill rpi-review-madyankin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rpi-review
Source: https://github.com/madyankin/dotfiles/tree/main/.config/agents/skills/rpi-review
Command: npx skills add https://github.com/madyankin/dotfiles --skill rpi-review-madyankin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and research documents often contain unverified claims, stale file references, and gaps that only surface during implementation. This Skill validates those artifacts against the actual repository before any code is written, catching critical errors early. ## Core Features & Use Cases - Evidence-Based Validation: Verifies every claim in plan and research documents against real code, optionally delegating to codebase locator, analyzer, and pattern-finder agents. - Severity-Classified Findings: Classifies issues as critical, major, or minor, each with evidence (file:line references) and an exact fix recommendation. - Structured Review Output: Produces a consistent review report with status, findings, required changes, and split automated/manual verification checklists, plus an optional compounding handoff for plan-implement-review loops. - Use Case: Before implementing a multi-phase refactor described in _scratchpad/plans/, run this Skill to confirm the referenced files exist, phases are executable, and success criteria are verifiable. ## Quick Start Review the implementation plan at _scratchpad/plans/my-plan.md and validate its claims against the codebase.

Frequently Asked Questions about rpi-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review an implementation plan before coding?▼

Point the Skill at a plan file in _scratchpad/plans/ and it reads the document fully, validates claims against the codebase, and returns findings classified as critical, major, or minor with concrete fix recommendations.

How to verify research document claims against actual code?▼

The Skill extracts explicit claims from research docs in _scratchpad/research/ and checks them against repository reality, optionally spawning codebase locator, analyzer, and pattern-finder agents to confirm file references and implementation details.

What does the review output format look like?▼

The review returns a summary with an overall status (approved, approved_with_changes, or required_changes), findings grouped by severity, required changes, and verification checklists split into automated and manual steps.

Can it review plans and research docs together?▼

Yes, it supports mixed review passes covering both plan and research artifacts in one run, applying the appropriate coverage checks for each artifact type.

When should I not use this review skill?▼

It is scoped to RPI planning and research artifacts, not general code review of implemented changes. It also avoids duplicating other general-purpose review skills on the same artifact pass.