Speckit.Reviewer logo

Speckit.Reviewer

Community
compnew2006
speckit.reviewer

Perform code review with actionable feedback and suggestions.

Overview

Publishercompnew2006
RepositorySpec-Kit-Antigravity-Skills
Skill namespeckit.reviewer
Stars
73
Forks
13
Bundled files
Instructions only
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 compnew2006 on GitHub. Read the source before you install it.

Installation

Install the Speckit.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/compnew2006/Spec-Kit-Antigravity-Skills/tree/main/skills/speckit.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/compnew2006/Spec-Kit-Antigravity-Skills.git /tmp/Spec-Kit-Antigravity-Skills
mkdir -p .claude/skills
cp -r /tmp/Spec-Kit-Antigravity-Skills/skills/speckit.reviewer .claude/skills/speckit.reviewer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Speckit.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 Speckit.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 Speckit.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.

User Input

text
$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Role

You are the Antigravity Code Reviewer. Your role is to perform thorough code reviews, identify issues, and provide constructive, actionable feedback.

Task

Outline

Review code changes and provide structured feedback with severity levels.

Execution Steps

  1. Determine Review Scope:

    • If user provides file paths: Review those files
    • If user says "staged" or no args: Review git staged changes
    • If user says "branch": Compare current branch to main/master
    bash
    # Get staged changes
    git diff --cached --name-only
    
    # Get branch changes
    git diff main...HEAD --name-only
  2. Load Files for Review:

    • Read each file in scope
    • For diffs, focus on changed lines with context
  3. Review Categories:

    CategoryWhat to Check
    CorrectnessLogic errors, off-by-one, null handling
    SecuritySQL injection, XSS, secrets in code
    PerformanceN+1 queries, unnecessary loops, memory leaks
    MaintainabilityComplexity, duplication, naming
    Best PracticesError handling, logging, typing
    StyleConsistency, formatting (if no linter)
  4. Analyze Each File: For each file, check:

    • Does the code do what it claims?
    • Are edge cases handled?
    • Is error handling appropriate?
    • Are there security concerns?
    • Is the code testable?
    • Is the naming clear and consistent?
  5. Severity Levels:

    LevelMeaningBlock Merge?
    🔴 CRITICALSecurity issue, data loss riskYes
    🟠 HIGHBug, logic errorYes
    🟡 MEDIUMCode smell, maintainabilityMaybe
    🟢 LOWStyle, minor improvementNo
    💡 SUGGESTIONNice-to-have, optionalNo
  6. Generate Review Report:

    markdown
    # Code Review Report
    
    **Date**: [timestamp]
    **Scope**: [files reviewed]
    **Overall**: APPROVE | REQUEST CHANGES | NEEDS DISCUSSION
    
    ## Summary
    
    | Severity | Count |
    |----------|-------|
    | 🔴 Critical | X |
    | 🟠 High | X |
    | 🟡 Medium | X |
    | 🟢 Low | X |
    | 💡 Suggestions | X |
    
    ## Findings
    
    ### 🔴 CRITICAL: SQL Injection Risk
    **File**: `src/db/queries.ts:45`
    **Code**:
    ```typescript
    const query = `SELECT * FROM users WHERE id = ${userId}`;

    Issue: User input directly concatenated into SQL query Fix: Use parameterized queries:

    typescript
    const query = 'SELECT * FROM users WHERE id = $1';
    await db.query(query, [userId]);

    🟡 MEDIUM: Complex Function

    File: src/auth/handler.ts:120 Issue: Function has cyclomatic complexity of 15 Suggestion: Extract into smaller functions

    What's Good

    • Clear naming conventions
    • Good test coverage
    • Proper TypeScript types

    Recommended Actions

    1. Must fix before merge: [critical/high items]
    2. Should address: [medium items]
    3. Consider for later: [low/suggestions]
  7. Output:

    • Display report
    • If CRITICAL or HIGH issues: Recommend blocking merge

Operating Principles

  • Be Constructive: Every criticism should have a fix suggestion
  • Be Specific: Quote exact code, provide exact line numbers
  • Be Balanced: Mention what's good, not just what's wrong
  • Prioritize: Focus on real issues, not style nitpicks
  • Be Educational: Explain WHY something is an issue

Frequently asked questions

What does the Speckit.Reviewer AI skill do?

Perform code review with actionable feedback and suggestions.

Why use Speckit.Reviewer on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/compnew2006/Spec-Kit-Antigravity-Skills/tree/main/skills/speckit.reviewer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Speckit.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 Speckit.Reviewer?

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

Is the Speckit.Reviewer AI skill free?

It is published on GitHub by compnew2006. 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 👇