Code Review And Quality

Community

hylarucoder

code-review-and-quality

Reviews a code change for correctness, security, maintainability, architecture, performance, and verification gaps, or performs a local code-smell review. Use for review this diff/PR、变更评审、代码审查、代码整洁度. Return evidence-backed findings and a scoped verdict; diagnose without editing unless fixes are requested. Use hai-architecture for system design, react-component-diagnosis for a component deep dive, and write-technical-acceptance-report for executed requirement acceptance.

Overview

Publisher	hylarucoder
Repository	`hai-stack`
Skill name	`code-review-and-quality`
Stars	284
Forks	15
Bundled files	5
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.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by hylarucoder on GitHub. Read the source before you install it.

Installation

Install the Code Review And Quality 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/hylarucoder/hai-stack.git /tmp/hai-stack
mkdir -p .claude/skills
cp -r /tmp/hai-stack/skills/code-review-and-quality .claude/skills/code-review-and-quality

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Review And Quality 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 And Quality 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 And Quality 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 and Quality

Purpose

Find defects and costly design regressions in a defined change. Preserve the useful five-axis review method of the existing skill while scaling the work to actual risk. A review verdict is not permission to merge, publish, or message others.

Modes

Change review: review the named diff/PR/commit. If unspecified, inspect the local staged and unstaged changes plus relevant new files; state the baseline and scope.
Maintainability: inspect the named files/functions for code smells. Read references/maintainability.md and its relevant language/examples guidance. Preserve behavior.
Review and fix: when the user asks for repairs, implement clear in-scope fixes after diagnosis and verify them. An audit-only request remains read-only.

Workflow

Read repository instructions, intended behavior, diff, and relevant specs/contracts. Record which files and paths were actually reviewed. Preserve unrelated work.
Read tests and their assertions, then trace changed behavior into callers, state, error paths, persistence, and external effects where relevant. A passing test is only as good as its coverage.
Review relevant axes:
- Correctness: intended behavior, boundary cases, failure handling, state transitions, concurrency/idempotency where relevant.
- Security: real trust/permission boundaries and untrusted data flow.
- Maintainability: clear responsibility and vocabulary; unnecessary branches, abstractions, duplicated authority; project conventions over arbitrary style rules.
- Architecture: ownership, dependency direction, contract changes, and whether complexity was reduced or merely relocated.
- Performance: evidenced unbounded work, query growth, allocation/render pressure; do not invent latency estimates without measurement.
For each candidate, verify the triggering scenario and changed code. Distinguish regressions, pre-existing issues, and unverified suspicions. Cite real file:line evidence.
Rank by user impact and change cost. Omit cosmetic preferences unless requested. Do not reject a coherent change solely for its line count, number of implementations, or lack of abstraction.
For requested repairs, apply the smallest complete fix and run appropriate checks. Use hai-tdd for behavior changes where a real RED is possible; structural work uses compiler, existing tests, and focused checks. Do not mix unrelated redesign into a bug fix.
Read references/output-template.md and deliver findings, actual verification, and a scoped verdict. No findings means none were found in the inspected scope, not proof of perfection.

Verification and boundaries

Review code and run relevant non-mutating checks when useful. Do not claim tests passed unless executed or clearly label the author's/historical evidence. Code inspection does not prove a deployed workflow passed; requirement-by-requirement acceptance belongs to write-technical-acceptance-report.

Unexplained runtime failures → hai-debug. A structural decision exposed by review → hai-architecture; a local naming decision → hai-naming; deep React analysis → react-component-diagnosis. Reuse collected evidence when handing off.

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 Code Review And Quality AI skill do?

Why use Code Review And Quality on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hylarucoder/hai-stack/tree/main/skills/code-review-and-quality. 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 And Quality?

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 And Quality?

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

Is the Code Review And Quality AI skill free?

It is published on GitHub by hylarucoder. 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

To Spec

mattpocock

CommunityPopular

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

To Tickets

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket…

Triage

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

Claude Handoff

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Code Review and Quality

Purpose

Modes

Workflow

Verification and boundaries

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now