by chrisvoncsefalvay · Claude Skill · ★ 33
a\ (autostar) If you can measure it, you can improve it. Soft RLVR for the masses. a\ turns any measurable goal into a structured optimisation loop. You define what "good" looks like. a\ runs experiments, scores the results, learns from every attempt, and converges on the best version within your budget. No reward model to train. No environment to build. No GPU cluster to provision. Just a goal, an evaluator, and an agent that knows how to search.
| Stars | 33 |
| Forks | 2 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 71.4114645699352/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-09 |
| Created | 2026-03-27 |
| Platforms | claude-code, python |
| Est. Tokens | ~11k |
Explore other popular claude skill tools:
autostar is Autoresearch ALL THE THINGS. RLVR for the masses.. It is categorized as a Claude Skill with 33 GitHub stars.
autostar is primarily written in Python. It covers topics such as agent-skills, autoresearch, claude-code.
You can find installation instructions and usage details in the autostar GitHub repository at github.com/chrisvoncsefalvay/autostar. The project has 33 stars and 2 forks, indicating an active community.
autostar is released under the MIT license, making it free to use and modify according to the license terms.