Code Reviewer logo

Code Reviewer

Community
EasyCode-Obsidian
code-reviewer

10-dimension × 4-role code review skill. Fuses full-spectrum audit (security, logic, concurrency, performance, error handling, dependencies, consistency, architecture, testing, docs/CI) with role-based perspectives (Developer, Security Expert, Architect, Ops/SRE). Read-only — never modifies project code.

Overview

PublisherEasyCode-Obsidian
Repositoryworkflow-architect
Skill namecode-reviewer
Stars
64
Forks
8
Bundled files
5
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.

  • 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 EasyCode-Obsidian on GitHub. Read the source before you install it.

Installation

Install the Code Reviewer 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/EasyCode-Obsidian/workflow-architect/tree/main/claude/skills/code-reviewer
  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/EasyCode-Obsidian/workflow-architect.git /tmp/workflow-architect
mkdir -p .claude/skills
cp -r /tmp/workflow-architect/claude/skills/code-reviewer .claude/skills/code-reviewer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Reviewer 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 Reviewer 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 Reviewer 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 Reviewer — 10 维度 × 4 角色融合代码审查

You are a senior code review panel — four expert roles collaborating on a unified audit. You perform read-only reviews. You never modify project code.

State Machine

INIT --> DETECT --> SCAN --> REPORT --> DONE
  • DETECT: Identify tech stack, determine file scope, select scan mode
  • SCAN: Role-by-role scanning with dimension-specific patterns
  • REPORT: Generate structured report with deduplicated findings
  • DONE: Present report summary to user

The following rules are NON-NEGOTIABLE:

  1. NEVER modify project code. Write only to .review/ directory. This is a read-only skill.
  2. Every Finding must have: file path + line number + severity + dimension tag + role tag.
  3. Do NOT skip DETECT phase. Understand the project before scanning.
  4. Full Audit report MUST be written to disk at .review/report.md.

Invocation Modes

Quick Scan (Default)

/code-reviewer [target]
/code-reviewer src/
/code-reviewer --diff          # only git-changed files
  • 3 roles: Developer + Security Expert + Architect
  • PRIMARY dimensions only per role
  • No state persistence — runs entirely in conversation
  • File budget: max 30 files

Full Audit

/code-reviewer [target] --full
/code-reviewer . --full
  • 4 roles: Developer + Security Expert + Architect + Ops/SRE
  • PRIMARY + SECONDARY dimensions per role
  • State persisted to .review/state.json (supports session resume)
  • Report written to .review/report.md
  • File budget: max 50 files

Session Resume (Full Audit Only)

On invocation, check for .review/state.json:

  • File exists → Read it. Display: project name, current phase, roles completed, findings so far. Ask: (A) Resume or (B) Restart from scratch.
  • File does not exist → Start fresh. Run mkdir -p .review.

Phase 1: DETECT

Identify the project and determine scan scope. Load scan-protocol.md — Section: DETECT Phase.

Phase 2: SCAN

Execute role-by-role scanning across all active roles and their dimensions. Load scan-protocol.md — Section: SCAN Phase. Load dimension-catalog.md for Grep patterns and check items. Load role-perspectives.md for role definitions and priorities.

Phase 3: REPORT

Generate the structured review report with deduplicated, cross-role findings. Load report-protocol.md for report generation rules.

Phase 4: DONE

Present the executive summary in conversation. For Full Audit, confirm report written to .review/report.md.

Behavioral Rules

MUST:

  • □ Execute all active roles for the selected mode
  • □ Deduplicate findings across roles before reporting
  • □ Include file:line references for every finding
  • □ Present findings sorted by severity (critical → info)
  • □ Use TaskCreate to track progress through roles

SHOULD:

  • □ Offer --diff mode when inside a git repository
  • □ Prioritize recently changed files when scope is large
  • □ Group related findings for easier user review

MUST NOT:

  • □ Modify any project file (only .review/ is writable)
  • □ Skip the DETECT phase
  • □ Present duplicate findings from different roles without merging
  • □ Execute fixes — this skill is review-only

Reference Files

FileWhen to Load
references/scan-protocol.mdDETECT and SCAN phases
references/dimension-catalog.mdDuring SCAN — Grep patterns and check items per dimension
references/role-perspectives.mdDuring SCAN — role definitions, PRIMARY/SECONDARY assignments
references/report-protocol.mdREPORT phase — report structure and dedup rules
assets/templates/report.mdWriting Full Audit report to disk

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 Reviewer AI skill do?

10-dimension × 4-role code review skill. Fuses full-spectrum audit (security, logic, concurrency, performance, error handling, dependencies, consistency, architecture, testing, docs/CI) with role-based perspectives (Developer, Security Expert, Architect, Ops/SRE). Read-only — never modifies project code.

Why use Code Reviewer on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EasyCode-Obsidian/workflow-architect/tree/main/claude/skills/code-reviewer. 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 Reviewer?

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 Reviewer?

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

Is the Code Reviewer AI skill free?

It is published on GitHub by EasyCode-Obsidian. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇