Shinpr Rashomon
- 15 repo stars
- Updated July 15, 2026
- shinpr/rashomon
shinpr-rashomon is a Claude Code plugin that measures prompt and skill improvements using blind A/B comparison and parallel worktree runs.
About
shinpr-rashomon is a Claude Code plugin for developers and small teams who treat agent skills and prompts like code that needs regression checks. Instead of guessing which rewrite is better, you run structured comparisons—often in parallel via worktrees—so two variants solve the same task under the same constraints. That fits naturally after you draft a skill in Build, when you are validating a prototype, and again before you rely on a prompt in daily Ship workflows. The plugin emphasizes measurement over opinion: evaluate execution quality, compare outcomes, and keep what wins. It is not a marketplace of skills or an OpenAPI generator; it is an evaluation harness focused on prompts, skills, and repeatable agent work. Install it when you are iterating on SKILL.md files, system prompts, or multi-step agent behaviors and need evidence before you standardize on one version.
- Blind A/B comparison for prompts and skills so bias does not skew results
- Parallel execution through worktrees for isolated variants
- Evaluate skill and prompt improvements with comparable runs
- Built for iteration on agent workflows, not single-shot codegen
- Community plugin bundle (1 plugin) from shinpr/rashomon
Shinpr Rashomon by the numbers
- Data as of Jul 28, 2026 (Skillselion catalog sync)
/plugin install shinpr-rashomon@shinpr/rashomonAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 15 |
|---|---|
| Last updated | July 15, 2026 |
| Repository | shinpr/rashomon ↗ |
What it does
Run blind A/B comparisons on prompts and agent skills so you can prove which version actually performs better before you ship it.
Who is it for?
Best when you're iterating on Claude Code skills or system prompts and want lightweight eval before rolling changes into your default workflow.
Skip if: Skip if you only need a single integration or SDK scaffold with no A/B testing or skill benchmarking.
What you get
You pick winning prompts and skills from blind, parallel comparisons with comparable execution evidence instead of anecdotal preference.
- Blind A/B comparison results between prompt or skill variants
- Evidence from parallel executions to choose a winning variant
- Repeatable eval workflow for future skill iterations
By the numbers
- Repository: shinpr/rashomon
- Plugin count: 1
- Catalog source: community auto-ingest
Recommended Plugins
Aglabo DeckrdDocument-Driven Development framework for AI-assisted BDD workflows1
Alonw0 Python Debugger SkillA skill for Python debugging methods and best practices10
Asynkron Asynkron.TestrunnerA.NET global tool that wraps dotnet test, captures TRX results, tracks test history, and displays regression charts3
Avdlee Swift Testing Agent SkillAn agent skill focused entirely on Swift Testing, helping you write better tests, migrate from XCTest, improve test architecture, and adopt modern Swift testing patterns with confidence.431
Bocato Swift Testing Agent SkillAgent Skill providing expert Swift Testing guidance for AI coding tools: covering test doubles, fixtures, async patterns, XCTest migration, and testing best practices.78
Brandcast Signage Agent Benchmark KitAutomated quality assurance for Claude Code agents using LLM-as-judge evaluation.3How it compares
Evaluation harness for prompts and skills, not an MCP server or curated skill marketplace.
FAQ
Who is Shinpr Rashomon for?
Developers using Claude Code who maintain custom skills or prompts and want measurable A/B comparisons before standardizing on one version.
When should I use Shinpr Rashomon?
Use it whenever you change a skill or prompt and need blind side-by-side runs—especially before ship, after prototyping two approaches, or when iterating agent tooling.
How do I add Shinpr Rashomon to my agent?
Install the shinpr/rashomon Claude Code plugin from the community listing, enable it in your Claude Code plugins configuration, and invoke its comparison workflow when you have two variants to test in parallel worktrees.