benchmark-models

Cross-model benchmark skill for comparing Claude, GPT/Codex, and Gemini on the same prompt and optionally an LLM-judge quality pass.

garrytan/gstackUpdated Apr 22, 2026

Works with

Claude CodeCursorClineWindsurfCodexGooseGitHub CopilotZed

0

total installs

0

this week

0

upvotes

Install Skill

Run in your terminal

$npx skills add https://github.com/garrytan/gstack --skill gstack

0

installs

0

this week

stars

Installation Guide

How to use benchmark-models on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your machine
  • Node.js 16+ with npm — verify with node --version
  • Active project directory where you want to add benchmark-models
2

Run the install command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/garrytan/gstack --skill gstack

Fetches benchmark-models from garrytan/gstack and configures it for Cursor.

3

Select Cursor when prompted

The CLI shows a list of agents. Use arrow keys and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ────────────────
│ · Cline · Codex · Goose · Windsurf
│ ●Cursor(selected)
│ · Cursor · Aider · Continue
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/benchmark-models

Restart Cursor to activate benchmark-models. Access via /benchmark-models in your agent's command palette.

Security Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.

Documentation

Cross-model benchmark skill for comparing Claude, GPT/Codex, and Gemini on the same prompt and optionally an LLM-judge quality pass. Imported from benchmark-models/SKILL.md in garrytan/gstack.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

Get started →

Use Cases

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

Improve work quality by 30-40% with less effort

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client with skill support
  • Clear understanding of task or problem to solve
  • Willingness to iterate and refine outputs

Time Estimate

15-45 minutes depending on use case complexity

Steps

  1. 1Install skill using provided installation command
  2. 2Test with simple use case relevant to your work
  3. 3Evaluate output quality and relevance
  4. 4Iterate on prompts to improve results
  5. 5Integrate into regular workflow if valuable

Common Pitfalls

  • Expecting perfect results without iteration
  • Not providing enough context in prompts
  • Using skill for tasks outside its intended scope
  • Accepting outputs without review and validation

Best Practices

✓ Do

  • +Start with clear, specific prompts
  • +Provide relevant context and constraints
  • +Review and refine all outputs before using
  • +Iterate to improve output quality
  • +Document successful prompt patterns

✗ Don't

  • Don't use without understanding skill limitations
  • Don't skip validation of outputs
  • Don't share sensitive information in prompts
  • Don't expect skill to replace human judgment

💡 Pro Tips

  • Be specific about desired format and style
  • Ask for multiple options to choose from
  • Request explanations to understand reasoning
  • Combine AI efficiency with human expertise

When to Use This

✓ Use when

Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.

✗ Avoid when

Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.

Learning Path

  1. 1Familiarize yourself with skill capabilities and limitations
  2. 2Start with low-risk, non-critical tasks
  3. 3Progress to more complex and valuable use cases
  4. 4Build expertise through regular use and experimentation

Related Skills

Reviews

4.565 reviews
  • C
    Chaitanya PatilDec 20, 2024

    Solid pick for teams standardizing on skills: benchmark-models is focused, and the summary matches what you get after install.

  • A
    Advait SinghDec 20, 2024

    Useful defaults in benchmark-models — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • C
    Charlotte GuptaDec 16, 2024

    benchmark-models has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • D
    Dev JainDec 8, 2024

    benchmark-models is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • A
    Arya RahmanDec 8, 2024

    Solid pick for teams standardizing on skills: benchmark-models is focused, and the summary matches what you get after install.

  • L
    Layla ChoiNov 27, 2024

    benchmark-models fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • J
    James AbbasNov 27, 2024

    I recommend benchmark-models for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • D
    Dev ReddyNov 19, 2024

    benchmark-models reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • R
    Rahul SantraNov 11, 2024

    I recommend benchmark-models for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • L
    Layla KimNov 11, 2024

    benchmark-models has been reliable in day-to-day use. Documentation quality is above average for community skills.

showing 1-10 of 65

1 / 7

Discussion

Comments — not star reviews
  • No comments yet — start the thread.