research workflow skills

全部科研技能

浏览、筛选并搜索已发布的科研技能,或用 AI 描述需求来定位可复用的研究工作流。

research workflow skills

分类:实验设计

4 个公开技能

/实验设计

experimental-design

技能
GitHub 收录 · 作者未认领

Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.

实验设计
机器学习
可复现性
消融实验
平台收录更新
2026/08/31
GitHub 源库更新
未同步源库时间

/实验设计

Science

技能
GitHub 收录 · 作者未认领

Hypothesis-test-analyze cycles for systematic problem-solving — the meta-skill governing all others. Includes define goal, generate hypotheses, design experiment, measure results, analyze results, iterate, full cycle, quick diagnosis, and structured investigation. USE WHEN think about, figure out, try approaches, experiment with, iterate on, improve, optimize, define goal, generate hypotheses, design experiment, measure results, analyze results, full cycle, quick diagnosis, structured investigation, science, hypothesis.

科学方法
假设检验
系统思维
迭代改进
平台收录更新
2026/08/31
GitHub 源库更新
未同步源库时间
详情

/实验设计

experiment-audit

技能
GitHub 收录 · 作者未认领

Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.5) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says \"审计实验\", \"check experiment integrity\", \"audit results\", \"实验诚实度\", or after experiments complete before writing claims.

实验审计
诚信验证
跨模型审查
平台收录更新
2026/08/31
GitHub 源库更新
未同步源库时间

/实验设计

dataset-manager

技能
GitHub 收录 · 作者未认领

Use this skill to generate benchmark datasets (TPC-H, TPC-DS, etc.). Trigger when the user needs test data at a specific scale factor for benchmarking or testing. Supports parquet and duckdb output formats.

基准数据集
TPC-H
TPC-DS
数据生成
平台收录更新
2026/08/31
GitHub 源库更新
未同步源库时间