Review Pr logo

Review Pr

OrganizationPopular
sashiko-dev
review-pr

Performs scrutinizing code reviews against project standards (e.g., GEMINI.md) and design docs. Intelligently detects relevant design files, categorizes findings (Safety, Complexity, Style), and generates actionable diffs. Use when the user asks to review a PR, diff, or specific codebase components.

Overview

Publishersashiko-dev
Repositorysashiko
Skill namereview-pr
Stars
1.2K
Forks
215
Bundled files
2
LicenseApache-2.0
Links
  • 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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sashiko-dev on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/sashiko-dev/sashiko.git /tmp/sashiko
mkdir -p .claude/skills
cp -r /tmp/sashiko/skills/review-pr .claude/skills/review-pr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review Pr 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 Pr 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 Pr 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 PR Skill

Core Directives

When asked to perform a code review, follow these steps strictly:

1. Context Gathering & Design Detection

  • Read Baseline Standards: Immediately read GEMINI.md (or the equivalent local project standard file) to establish the coding standards, style guidelines, and mandatory architectural rules.
  • Analyze Code Scope: Look at the files modified in the PR or the specific code components requested for review. Identify the core features or modules being touched (e.g., cli, auth, db).
  • Detect Design Documents: Automatically locate the project's design directory. Look for directories named designs/, docs/design/, rfcs/, or architecture/.
  • Map and Read Design Docs: Map the modified files/modules to specific design documents. For example, if sashiko-cli.rs is modified, look for a file like DESIGN_CLI_TOOL.md. Read the matched design documents to understand the intended architecture and behavior.

2. Analysis

Perform a deep, scrutinizing code review of the target code against the gathered context. Evaluate for:

  • Design Alignment: Does the implementation match the intent described in the design documents?
  • Safety & Security: Are there any risky operations (e.g., unchecked unwraps, poor error handling, thread safety issues, SQL injection risks, insecure dependency usage, or credential leakage)?
  • Regression Analysis: Assess if the changes could break existing functionality. Check for impacts on related modules, performance regressions, or unintended side effects in shared components.
  • Idiomatic Conventions: Does the code use the language idiomatic patterns and the project-specific coding standards defined in GEMINI.md?
  • SOLID/DRY Principles: Reference references/principles.md and evaluate the code for adherence to SOLID and DRY principles within the Rust context.
  • Test Coverage: Are unit or integration tests missing for new logic?

3. Reporting

Output your findings in a structured, categorized markdown format. Use the following emoji prefixes for each finding to indicate severity/type:

  • 🔴 Safety / Bugs / Security: Broken behavior, potential crashes, security risks, or unhandled errors.
  • 🟠 Regressions: Potential to break existing functionality or introduce performance bottlenecks.
  • 🟡 Complexity / Logic / SOLID: High cyclomatic complexity, functions that are too long, risky architectural choices, or violations of SOLID principles.
  • 🔵 Style / Nits / DRY: Style violations, naming issues, duplicated code (DRY violations), or minor optimizations.
  • 🟢 Design Alignment: Noting where the code successfully or unsuccessfully aligns with the mapped design documents.

Keep descriptions terse and focused on the why and the fix.

4. Fix Generation

For every actionable finding, provide a unified diff in a markdown code block that the author can directly apply or paste into a PR comment.

  • Ensure diffs are accurate and apply cleanly.
  • Never use "..." or placeholders in diffs. Provide the exact text replacement.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Review Pr AI skill do?

Performs scrutinizing code reviews against project standards (e.g., GEMINI.md) and design docs. Intelligently detects relevant design files, categorizes findings (Safety, Complexity, Style), and generates actionable diffs. Use when the user asks to review a PR, diff, or specific codebase components.

Why use Review Pr on TypingMind?

Because you install it once and use it with any model. Review Pr 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 Pr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sashiko-dev/sashiko/tree/main/skills/review-pr. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Review Pr?

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 Pr?

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

Is the Review Pr AI skill free?

Yes. It is published on GitHub by sashiko-dev under the Apache-2.0 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇