← Browse
skill-tuner
StartupBros-com ★ 0
skill-tuner compares paired evaluations of agent-consumed documents using statistical confidence intervals and user-defined non-inferiority margins to determine whether changes actually improved outcomes. It reads Anthropic's skill-creator benchmark output and claude plugin eval results, then supplies confidence-based verdicts (win/loss/inconclusive/tie) with provenance tracking and adversarial defect detection to catch false positives.
Install
> /plugin marketplace add StartupBros-com/skill-tuner
> /plugin install skill-tuner
What it's made of
2 skills
- Commands
- 0
- Agents
- 0
- Skills
- 2
- 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
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 (StartupBros-com).