Skill Forge Benchmark · AgriciDaniel/skill-forge
Benchmark Claude Code skill performance across versions
Runs repeated trials of a Claude Code skill to measure pass rate, execution time and token usage, then compares the results against a previous version or baseline to see whether the skill actually improved.
Good for
- Track a skill's pass rate and execution time
- Compare performance between two skill versions
- Verify whether a skill change actually improved results
- Source repository
- AgriciDaniel/skill-forge
- Category
- Science
Open-source skills are maintained by their authors and listed as published, with attribution. Results depend on how well the skill fits your task and material.
A good place to start
Benchmark this skill's pass rate and speed before and after my latest changes.
Make your next great thing.
Bring a question, a file, or an idea that’s not quite there yet.