已有两个或更多 experiment_ids 或底层 candidate_result_paths 时，用于在同一任务和评估 split 下先生成比较方案，用户确认后做确定性模型比较，输出比较表、摘要报告和推荐模型 path。不要用于训练、调参、最终报告或模型采用决策。
How to install uplift-model-result-comparison?
qfin-tech/model-evo/uplift-model-result-comparison
$npx -y skills add qfin-tech/model-evo --skill uplift-model-result-comparisonInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/qfin-tech/model-evo" --skill "qfin-tech/model-evo/uplift-model-result-comparison"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/qfin-tech/model-evo" that are relevant to the current task. Run `npx skills add "https://github.com/qfin-tech/model-evo"` and select the relevant skills, then follow their instructions.
Related
6 picksType
- gpt-image-2Create or edit images with Pilio GPT Image 2 through the unified Pilio developer API.Jul 2026
- spec-driven-implementationDrive a spec-first workflow for substantial features by writing PRODUCT.md before implementation, writing TECH.md when warranted, and keeping both specs…Jul 2026
- review-prReview a pull request diff and write structured feedback to review.json for the workflow to publish.Jul 2026
- write-product-specWrite a PRODUCT.md spec for a significant user-facing feature in Warp, focused on detailed behavior and validation.Jul 2026
- write-tech-specWrite a TECH.md spec for a significant Warp feature after researching the current codebase and implementation constraints.Jul 2026
- fix-errorsFix compilation errors, linting issues, and test failures in the warp Rust codebase. Covers presubmit checks, WASM-specific errors, and running specific tests.Jul 2026
