Review logo

Review

Organization
greptileai
review

Review the current branch with Greptile

Overview

Publishergreptileai
Repositoryskills
Skill namereview
Stars
425
Forks
45
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by greptileai on GitHub. Read the source before you install it.

Installation

Install the Review 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.
    https://github.com/greptileai/skills/tree/main/plugins/greptile/skills/review
  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/greptileai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/greptile/skills/review .claude/skills/review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review 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 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 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.

Run a Greptile review on the current branch, against its base branch.

Build the command from $ARGUMENTS, if the user supplied any:

  • A branch name they want to review against becomes --branch '<BRANCH>', quoted the same way as the instructions below.
  • Anything else they wrote is what they want the reviewer to focus on. Pass it as --instructions '<their words>' using single quotes, so the reviewer receives their exact text. If their text contains a ', replace each one with '\'' and change nothing else. Never use double quotes: $ and backticks are live inside them, so $PATH would silently disappear from the instructions and $(...) would stop the run at a permission prompt.
GREPTILE_NO_AUTO_INSTALL=1 GREPTILE_NO_UPDATE_CHECK=1 node "${CLAUDE_PLUGIN_ROOT}/scripts/greptile.mjs" review --agent

Outside Claude Code (Codex), replace ${CLAUDE_PLUGIN_ROOT} with the plugin root: the absolute path two folders above this SKILL.md.

Always pass --agent; it selects plain output intended for AI agents.

GREPTILE_NO_AUTO_INSTALL=1 suppresses the Mermaid renderer download. When a review summary carries a diagram, the CLI otherwise fetches a small binary (mmdr) into ~/.cache/greptile/bin/ to rasterize it. That is worth doing in a terminal a person is watching; it is not worth doing here. Claude Code runs this command without a TTY, so the inline-image path is dead either way and the diagram degrades to a link to an SVG file — while the download itself would still stall a review the user is waiting on. The diagram's Mermaid source reaches you in the review text regardless.

GREPTILE_NO_UPDATE_CHECK=1 is belt-and-braces. The CLI infers how it was installed from its own path, and versions before the plugin was recognised read a copy running from inside this plugin as a standalone install — which would name an installer that cannot update the plugin's copy. The notice is already suppressed here because --agent is non-interactive, so this only matters if the command is ever run without it, or the invocation is copied elsewhere. Updates arrive with the plugin either way.

Give the Bash call a 600000 ms timeout. A review commonly runs longer than the two-minute default.

If the run reports that no one is signed in, it prints not signed in. Set GREPTILE_API_KEY or run 'greptile login --api-key'. Prefer OAuth over an API key: tell the user to run /greptile:login (in Codex, the login skill), and stop there rather than starting a browser sign-in inside this command.

This dispatches a headless review: it reviews the working branch and does not need an open pull request. The review is stored on the user's Greptile account, so the greptile MCP tools in this plugin can read it back — list_code_reviews and get_code_review return it with source: "headless".

After the review completes, summarize the findings and offer to fix them. Use get_code_review for the full body of any finding you need more detail on.

Frequently asked questions

What does the Review AI skill do?

Review the current branch with Greptile

Why use Review on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/greptileai/skills/tree/main/plugins/greptile/skills/review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Review?

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?

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

Is the Review AI skill free?

Yes. It is published on GitHub by greptileai under the MIT 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 👇