by adewale · Agent Tool · ★ 54
Skill Eval Harness Skill Eval Harness is a Python CLI for testing whether an Agent Skill changes observable output. It reads , emits answer-key-safe task rows, grades files under , and writes benchmark reports you can diff across variants. The main question is narrow: when the same case runs with and without the skill, what changed, what passed, and did the eval itself leak the answer? Core loop Describe cases in : prompt, split, fixture files, variants, assertions, and ablations. Prepare tasks with ; generation rows omit and judge rubrics unless you explicitly request them.
| Stars | 54 |
| Forks | 3 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70.4903517817242/100 |
| Last Updated | 2026-07-08 |
| Created | 2026-06-09 |
| Platforms | python |
| Est. Tokens | ~25k |
These tools work well together with skill-eval-harness for enhanced workflows:
Explore other popular agent tool tools:
skill-eval-harness is Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters. It is categorized as a Agent Tool with 54 GitHub stars.
skill-eval-harness is primarily written in Python. It covers topics such as agent-skills, evals, python.
You can find installation instructions and usage details in the skill-eval-harness GitHub repository at github.com/adewale/skill-eval-harness. The project has 54 stars and 3 forks, indicating an active community.
skill-eval-harness is released under the MIT license, making it free to use and modify according to the license terms.