Code Review logo

Code Review

Community
andreaswasita
code-review

Reviews diffs by severity to produce actionable feedback.

Overview

Publisherandreaswasita
Repositorycopilot-agents-dojo
Skill namecode-review
Stars
54
Forks
15
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 andreaswasita 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/andreaswasita/copilot-agents-dojo/tree/main/skills/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/andreaswasita/copilot-agents-dojo.git /tmp/copilot-agents-dojo
mkdir -p .claude/skills
cp -r /tmp/copilot-agents-dojo/skills/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 Skill

Reviews diffs and PRs the way a senior engineer would: intent first, structure second, line-by-line third. Produces feedback grouped by severity (🔴 must / 🟡 should / 🟢 nit) with concrete suggestions. Does NOT rewrite the author's code — it directs, it does not replace.

When to Use

  • Reviewing a pull request, branch diff, or staged changes.
  • Auditing changes before merge.
  • Self-reviewing the agent's own output before presenting it.
  • Hunting for security, correctness, or performance regressions.
  • The user asks "does this look right?" about a code change.

Prerequisites

  • The view, grep, and glob Copilot tools to read code.
  • git available so diffs can be inspected (git diff main, git log).
  • Read access to the repository being reviewed.
  • For PR-scoped review: gh CLI authenticated to fetch PR metadata.

How to Run

text
1. Read the PR title, description, and linked issue.
2. List changed files (`git diff main --stat`) and assess scope.
3. Walk the diff with the `view` tool, file by file.
4. Apply the severity rubric below.
5. Emit a structured review block with concrete fixes.

Quick Reference

PhaseToolWhat to check
IntentPR description, linked issueWhy does this change exist?
Scopegit diff main --statFiles changed match stated intent
Correctnessview on hot pathsLogic, null/edge handling, off-by-one
Securitygrep for secrets, raw SQL, evalInjection, auth bypass, leaked secrets
Performanceview on loops, queriesN+1, unbounded allocations, missing indexes
Testsview on test filesNew paths actually covered

Procedure

Step 1: Understand Intent

Read the PR description, commit messages, and any linked issue. If intent is unclear, stop and ask the author — reviewing code whose purpose you don't understand wastes everyone's time.

Step 2: Structural Pass

Use git diff main --stat to size the change. Check:

  • Does the file list match the stated scope?
  • Are new dependencies justified?
  • Does the change fit existing patterns in the repo?
  • Is the deletion ratio healthy? (Good PRs often delete as much as they add.)

Step 3: Line-by-Line Pass

Walk each changed file with view. Apply the rubric:

CategoryLook for
CorrectnessLogic errors, off-by-one, null handling, missing edge cases
SecurityInjection, auth bypass, secrets in code, weak input validation
PerformanceN+1 queries, unbounded allocations, missing indexes
ReadabilityNaming, complexity, comments (too few or too many)
TestingNew paths actually covered, tests meaningful (not assert-true)
Error handlingErrors handled or silently swallowed

Step 4: Emit Structured Feedback

markdown
## Review Summary

### 🔴 Must Fix (Blocking)
- `path/to/file.ts:42` — <issue> + **Suggestion:** <concrete fix>

### 🟡 Should Fix (Non-Blocking)
- `path/to/file.ts:88` — <issue> + **Suggestion:** <better approach>

### 🟢 Nit (Optional)
- `path/to/file.ts:120` — <style or preference point>

### ✅ What's Good
- <Highlight something done well — positive reinforcement matters.>

Pitfalls

  • DO NOT rubber-stamp ("LGTM 👍") without reading the diff — worse than no review.
  • DO NOT block a PR over formatting if a linter exists — that is the linter's job.
  • DO NOT rewrite the author's code in the review thread. Suggest direction; do not freelance.
  • DO NOT miss the forest for the trees. Catching a typo while missing a SQL injection is a bad trade.
  • DO NOT review code you do not understand. Read the surrounding code first.

Verification

  • Every changed file was opened with view at least once.
  • Each issue cites a file and line number.
  • Severity buckets used (🔴 / 🟡 / 🟢 / ✅).
  • At least one positive observation included.
  • If 🔴 issues exist, the PR is explicitly marked NOT ready to merge.

Frequently asked questions

What does the Code Review AI skill do?

Reviews diffs by severity to produce actionable feedback.

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/andreaswasita/copilot-agents-dojo/tree/main/skills/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 andreaswasita 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 👇