Code Review Standards logo

Code Review Standards

Organization
initializ
code-review-standards

Discover and apply organization coding standards from .forge-review/ configuration

Overview

Publisherinitializ
Repositoryforge
Skill namecode-review-standards
Stars
242
Forks
14
Bundled files
Instructions only
LicenseApache-2.0
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 initializ on GitHub. Read the source before you install it.

Installation

Install the Code Review Standards 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/initializ/forge/tree/main/forge-skills/local/embedded/code-review-standards
  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/initializ/forge.git /tmp/forge
mkdir -p .claude/skills
cp -r /tmp/forge/forge-skills/local/embedded/code-review-standards .claude/skills/code-review-standards
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Review Standards 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 Standards 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 Standards 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 Standards

Teaches the agent to discover and apply organization-specific coding standards stored in a .forge-review/ directory in the target repository. This skill provides configuration templates and standard rule files that teams can customize.

Overview

The .forge-review/ directory is a convention for storing code review configuration alongside the codebase. When present, the code-review skill automatically loads these standards and applies them during reviews.

This skill:

  • Documents the .forge-review/ directory structure and file formats
  • Provides templates for bootstrapping review standards in new repositories
  • Teaches the agent how to discover and interpret standards files

Directory Structure

.forge-review/
├── config.yaml                  # Review configuration
├── .forge-review-ignore         # Files/patterns to skip during review
└── standards/                   # Coding standards (one file per topic)
    ├── general.md               # General coding rules
    ├── security.md              # Security rules
    ├── go.md                    # Go-specific rules
    ├── python.md                # Python-specific rules
    ├── typescript.md            # TypeScript rules
    └── testing.md               # Testing rules

Tool: review_standards_init

Initialize a .forge-review/ directory in the current repository with default templates.

This is a binary-backed tool that uses filesystem operations (mkdir, write) to scaffold the standards directory. The agent reads templates bundled with this skill and writes them to the target repository.

Input:

ParameterTypeRequiredDescription
target_dirstringnoTarget directory (default: current working directory)
languagesarraynoLanguage-specific standards to include: go, python, typescript. Default: all
overwritebooleannoOverwrite existing files. Default: false

Output: List of created files and a summary of the initialized configuration.

Detection Heuristics

The agent selects this tool when it detects:

  • Requests to "set up code review", "initialize review standards", "configure review"
  • Questions about .forge-review/ directory structure
  • Requests to create or customize coding standards

Tool: review_standards_check

Check whether the current repository has a .forge-review/ configuration and report its status.

Input:

ParameterTypeRequiredDescription
target_dirstringnoDirectory to check (default: current working directory)

Output: JSON object with configuration status, found files, and any validation issues.

Detection Heuristics

The agent selects this tool when it detects:

  • Questions about whether review standards are configured
  • Requests to validate review configuration
  • Troubleshooting review behavior

Configuration Reference

config.yaml

yaml
# .forge-review/config.yaml
version: "1"

# Default review settings
review:
  # Focus areas to always include (bugs, security, style, performance, maintainability)
  default_focus:
    - bugs
    - security

  # Severity threshold: only report findings at or above this level
  # Options: nitpick, info, warning, error
  min_severity: info

  # Maximum findings to report per review
  max_findings: 50

# Language-specific settings
languages:
  go:
    standards_file: standards/go.md
    enabled: true
  python:
    standards_file: standards/python.md
    enabled: true
  typescript:
    standards_file: standards/typescript.md
    enabled: true

# File patterns to always skip (supplements .forge-review-ignore)
skip_patterns:
  - "vendor/**"
  - "node_modules/**"
  - "*.generated.go"
  - "*.min.js"
  - "**/*.pb.go"

.forge-review-ignore

Gitignore-style patterns for files that should be skipped during review:

# Dependencies
vendor/
node_modules/

# Generated code
*.generated.go
*.pb.go
*_gen.go

# Build artifacts
dist/
build/
*.min.js
*.min.css

# Test fixtures
testdata/
**/fixtures/**

# Documentation
*.md
LICENSE

Standards Files

Standards files are markdown documents with rules organized by category. Each rule should be clear and actionable. The code-review skill injects these into the LLM prompt during review.

Format:

markdown
# Category Name

## Rule Title

Description of the rule and why it matters.

**Good:**
\`\`\`go
// example of correct code
\`\`\`

**Bad:**
\`\`\`go
// example of incorrect code
\`\`\`

Templates

This skill bundles template files in the templates/ directory. Use review_standards_init to copy them into a target repository, or browse them directly for reference.

Available templates:

  • templates/.forge-review/config.yaml — Default configuration
  • templates/.forge-review/.forge-review-ignore — Default ignore patterns
  • templates/.forge-review/standards/general.md — General coding standards
  • templates/.forge-review/standards/security.md — Security review rules
  • templates/.forge-review/standards/go.md — Go-specific standards
  • templates/.forge-review/standards/python.md — Python-specific standards
  • templates/.forge-review/standards/typescript.md — TypeScript standards
  • templates/.forge-review/standards/testing.md — Testing standards

Safety Constraints

  • This skill only reads and writes configuration files in .forge-review/
  • It never modifies source code
  • Standards files are only used as additional context for LLM-based review; they do not block merges or fail CI on their own
  • Overwrite protection is on by default (overwrite: false)

Frequently asked questions

What does the Code Review Standards AI skill do?

Discover and apply organization coding standards from .forge-review/ configuration

Why use Code Review Standards on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-review-standards. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Code Review Standards?

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 Standards?

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

Is the Code Review Standards AI skill free?

Yes. It is published on GitHub by initializ under the Apache-2.0 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 👇