Guide to benchmarking gstack skills
Agents & MCPSkill Packaged as a skill by Orbit
Runs the same task through Claude, GPT, and Gemini side by side so you can see which AI model does the best job before you commit to one.
Orbit turned public content into a SKILL.md you can read before adding it.
Checked by Orbit: nothing risky found in what it runs or reads.
What you’ll need
OpenAIRuns the same skill on GPT so you can compare it against Claude
Or: Codex CLI
Google GeminiRuns the same skill on Gemini for the side-by-side comparison
Or: Gemini CLI