Code Review

Community

JasonxzWen

code-review

Load when a task needs a deep, report-only review across independent Standards and Spec axes, using bounded read-only native Subagents when available and adding risk lenses only when the diff warrants them.

Overview

Publisher	JasonxzWen
Repository	`harness-hub`
Skill name	`code-review`
Stars	71
Forks	0
Bundled files	1
Links	Skill source Repository

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by JasonxzWen 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.

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.

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/JasonxzWen/harness-hub.git /tmp/harness-hub
mkdir -p .claude/skills
cp -r /tmp/harness-hub/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

Use this Skill for a substantive pre-delivery review. It reviews the current change; it does not own implementation, verification, Git delivery, or remote state.

Establish Scope

Resolve a credible base, changed and untracked files, the accepted spec or task contract, relevant project instructions, and nearby tests. Do not switch a shared checkout. If intent or base cannot be established from repository facts, report the missing evidence instead of reviewing an invented diff.

Two Required Axes

Review these independently so one kind of evidence does not mask the other:

Standards axis

repository instructions and local conventions
correctness, robustness, observability, and error handling
test value and public-behavior coverage
maintainability, unnecessary complexity, and duplication

Spec axis

every accepted behavior and non-goal
edge cases, ownership, authorization, and data boundaries
whether implementation and tests demonstrate the requested outcome
contradictions between the diff, current implementation, and durable docs

When the Host supports native parallel work, dispatch both axes as bounded, independent, read-only native Subagents. Give each the same base, diff, intent, and evidence boundary. Subagents do not edit, commit, publish, decide user tradeoffs, or own the final verdict. The main Agent integrates and deduplicates their evidence.

If native Subagents are unavailable or the diff is tiny, the main Agent applies both axes directly. Do not create a Harness Hub Agent fallback, adapter, fixed persona, or scheduler.

Conditional Risk Lenses

Add only lenses justified by the touched surface:

security and privacy
API or compatibility contract
data/schema migration and rollback
concurrency, reliability, or performance
frontend race, accessibility, or state behavior

Use the narrow domain Skill where appropriate, such as security-review or ponytail. Do not multiply reviewers without independent evidence value.

Findings

Report only actionable, evidence-backed findings. For each finding include:

P0–P3 severity
confidence: high, medium, or low
exact file and tight line anchor
violated behavior, rule, or invariant
concrete failure mode and evidence
smallest credible correction and required verification

Suppress style preferences, speculative cleanup, and pre-existing issues unrelated to the diff. Distinguish missing evidence from evidence of failure.

Deterministic failures remain failures and cannot be overridden by an Agent verdict.

Result

Sort findings by severity, then confidence. State which axes/lenses ran, unresolved evidence, and one verdict: Ready, Ready with fixes, or Not ready.

Report only. Do not edit files. Do not commit, push, create a pull request, merge, file an issue, or mutate any external system. The main Agent decides what to fix and owns the final user report.

Source Notes

This is a reduced fusion of the MIT-licensed review concepts from EveryInc/compound-engineering-plugin and mattpocock/skills skills/engineering/code-review. It keeps independent evidence axes, severity/confidence, and conditional risk review while removing owner routing, autofix modes, personas, and a review control plane.

Bundled files

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

LICENSE.everyinc.txt1 KB

Frequently asked questions

What does the Code Review AI skill do?

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/JasonxzWen/harness-hub/tree/main/skills/code-review. 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 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?

It is published on GitHub by JasonxzWen. Check the repository for licensing terms. 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

Implement

mattpocock

CommunityPopular

Implement a piece of work based on a spec or set of tickets.

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Prototype

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Research

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Code Review

Establish Scope

Two Required Axes

Standards axis

Spec axis

Conditional Risk Lenses

Findings

Result

Source Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now