← Browse
blind-scoring
shashank-sn ★ 0
This Claude Code skill compares multiple versions of a text by assigning neutral labels and shuffling them so the scorer never knows which version is the original or which edit is being evaluated. It runs multiple trials with fresh scorers per trial, applies a fixed rubric consistently, and reports per-trial scores alongside the mean with sample size and statistical limitations.
Install
> /plugin marketplace add shashank-sn/workflows/tree/HEAD/research/blind-scoring
> /plugin install blind-scoring
Source: https://github.com/shashank-sn/workflows/tree/HEAD/research/blind-scoring
What it's made of
1 skill
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (shashank-sn).