Review Plan

CommunityPopular

FlorianBruniaux

review-plan

Structured plan review across 4 axes before writing any code (inspired by Garry Tan's workflow)

Overview

Publisher	FlorianBruniaux
Repository	`claude-code-ultimate-guide`
Skill name	`review-plan`
Stars	6K
Forks	782
Bundled files	Instructions only
License	CC-BY-SA-4.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by FlorianBruniaux on GitHub. Read the source before you install it.

Installation

Install the Review Plan AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples/skills/review-plan

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-ultimate-guide.git /tmp/claude-code-ultimate-guide
mkdir -p .claude/skills
cp -r /tmp/claude-code-ultimate-guide/examples/skills/review-plan .claude/skills/review-plan

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review Plan in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Review Plan on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Review Plan is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Review Plan Before Implementation

Review the current plan thoroughly before making any code changes. For every issue or recommendation, explain the concrete tradeoffs, give an opinionated recommendation, and ask for user input before assuming a direction.

Engineering Preferences

Use these to guide your recommendations (override with project-specific CLAUDE.md preferences if they exist):

DRY is important: flag repetition aggressively
Well-tested code is non-negotiable: prefer too many tests over too few
Code should be "engineered enough": not under-engineered (fragile, hacky) and not over-engineered (premature abstraction, unnecessary complexity)
Err on the side of handling more edge cases, not fewer
Bias toward explicit over clever; thoughtfulness over speed

Review Pipeline

Work through each section sequentially. After each section, pause and ask for feedback before moving on.

1. Architecture Review

Evaluate:

Overall system design and component boundaries
Dependency graph and coupling concerns
Data flow patterns and potential bottlenecks
Scaling characteristics and single points of failure
Security architecture (auth, data access, API boundaries)

2. Code Quality Review

Evaluate:

Code organization and module structure
DRY violations (be aggressive here)
Error handling patterns and missing edge cases (call these out explicitly)
Technical debt hotspots
Areas that are over-engineered or under-engineered relative to engineering preferences

3. Test Review

Evaluate:

Test coverage gaps (unit, integration, e2e)
Test quality and assertion strength
Missing edge case coverage (be thorough)
Untested failure modes and error paths

4. Performance Review

Evaluate:

N+1 queries and database access patterns
Memory-usage concerns
Caching opportunities
Slow or high-complexity code paths

Issue Reporting Format

For every specific issue found (bug, smell, design concern, or risk):

Describe the problem concretely, with file and line references
Present 2-3 options, including "do nothing" where that's reasonable
For each option, specify: implementation effort, risk, impact on other code, and maintenance burden
Give your recommended option and why, mapped to engineering preferences above
Ask explicitly whether the user agrees or wants to choose a different direction before proceeding

Workflow

Do not assume priorities on timeline or scale
After each section, pause and ask for feedback before moving on
Use AskUserQuestion for structured option selection

Before Starting

Ask if the user wants one of two options:

BIG CHANGE: Work through this interactively, one section at a time (Architecture → Code Quality → Tests → Performance) with at most 4 top issues in each section
SMALL CHANGE: Work through interactively ONE question per review section

Tips

Combine with .claude/rules/ files for project-specific review criteria
Engineering preferences above can be overridden by your project's CLAUDE.md
For deeper analysis, use this command with Opus model

Sources

Inspired by Garry Tan's Plan Mode prompt (Feb 2026)
Adapted for Claude Code's native config system

$ARGUMENTS

Frequently asked questions

What does the Review Plan AI skill do?

Structured plan review across 4 axes before writing any code (inspired by Garry Tan's workflow)

Why use Review Plan on TypingMind?

Because you install it once and use it with any model. Review Plan is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Review Plan in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples/skills/review-plan. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Review Plan?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Review Plan?

As many as you like. As long as a model supports skills, you can use Review Plan with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Review Plan AI skill free?

Yes. It is published on GitHub by FlorianBruniaux under the CC-BY-SA-4.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Benchmark Models

garrytan

CommunityPopular

Cross-model benchmark for gstack skills. (gstack)

Benchmark

Performance regression detection. (gstack)

Ios Design Review

Visual design audit for iOS apps on real hardware. (gstack)

Ios Fix

Autonomous iOS bug fixer. (gstack)

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Review Plan Before Implementation

Engineering Preferences

Review Pipeline

1. Architecture Review

2. Code Quality Review

3. Test Review

4. Performance Review

Issue Reporting Format

Workflow

Before Starting

Tips

Sources

Frequently asked questions

Related AI Skills

Set up your own AI workspace now