Code Review logo

Code Review

Organization
SylphAI-Inc
code-review

Perform a thorough, structured code review of a diff or pull request

Overview

PublisherSylphAI-Inc
Repositoryatskills
Skill namecode-review
Stars
88
Forks
6
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 SylphAI-Inc on GitHub. Read the source before you install it.

Installation

Install the Code 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/SylphAI-Inc/atskills/tree/main/examples/code-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/SylphAI-Inc/atskills.git /tmp/atskills
mkdir -p .claude/skills
cp -r /tmp/atskills/examples/code-review .claude/skills/code-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code 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 Code 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 Code 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.

Code Review Workflow

Review the given diff, pull request, or set of changed files as a careful senior engineer would — looking for correctness, safety, and maintainability issues, not just style nits.

Steps

  1. Understand intent first. Read the PR description / commit messages / linked issue before reading the diff line-by-line. Know what problem the change is supposed to solve before judging whether it solves it.

  2. Trace the change end-to-end. For each modified function/module, identify every caller and every downstream consumer of its output. A change that looks correct in isolation can still break a caller that assumed the old behavior.

  3. Check correctness before style. In priority order:

    • Logic errors — off-by-one, incorrect conditionals, wrong operator, inverted boolean logic.
    • Error handling — are error/exception paths handled, or silently swallowed? Are edge cases (empty input, null/None, zero, max values) covered?
    • Concurrency/state — race conditions, shared mutable state, missing locks/transactions where needed.
    • Security — unsanitized input reaching a query/shell/template, secrets in code, missing auth checks on new endpoints.
    • Resource handling — unclosed files/connections, unbounded loops/memory growth, missing timeouts.
  4. Check test coverage. Does the diff include tests for the new/changed behavior? Do the tests actually exercise the changed logic, or do they just assert trivial properties (tautological tests)? Are edge cases from step 3 covered?

  5. Check for duplication and reuse. Does this diff reimplement something that already exists elsewhere in the codebase (a date formatter, a retry helper, an API client)? Prefer reusing/extending existing utilities over introducing parallel implementations.

  6. Check the blast radius. Is the change scoped to what the task requires, or does it touch unrelated files/formatting/comments? Flag unrelated changes explicitly — they hide the real diff and increase review risk.

  7. Only then, style and readability. Naming, comments, consistency with surrounding code conventions. Note these, but don't let them dominate the review — they're the last priority, not the first.

  8. Write the review as specific, actionable comments. For each issue found:

    • Point to the exact file/line.
    • State what's wrong (not just "this looks off") and why it matters (what could break, and under what condition).
    • Suggest a concrete fix or ask a clarifying question if intent is genuinely ambiguous.
    • Distinguish blocking issues ("must fix before merge") from non-blocking suggestions ("consider," "nit:").

Output Format

Summarize as:

  1. TL;DR — does this change look safe to merge, with or without required fixes?
  2. Blocking issues — must be resolved before merge, with file/line references.
  3. Non-blocking suggestions — nice-to-haves, style, minor improvements.
  4. Questions — anything genuinely ambiguous that needs the author's input before you can finish the review.

Frequently asked questions

What does the Code Review AI skill do?

Perform a thorough, structured code review of a diff or pull request

Why use Code Review on TypingMind?

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

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

Which AI models can use Code 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 Code Review?

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

Is the Code Review AI skill free?

Yes. It is published on GitHub by SylphAI-Inc 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 👇