Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →light0305/light-research-plan
Light 科研主线第 5 步·研究方案与实验设计：把 idea-critique 放行的 idea 与 data feasibility 拆成**能真执行、能写进论文、 能复现**的 question/estimand、实验矩阵与预注册包。何时用：idea 已通过审查要落地 / 要设计实验·消融·对比·敏感性· 泛化·鲁棒性 / 写研究方案 PROJECT_PLAN / 锁 primary outcome、排除/停止规则或 preregistration / 规划样本量、种子与统计功效 / 算实验算力预算 / 复现已有论文 / 担心 baseline 放水或假设推不翻。触发词：研究方案 / 实验设计 / 实验矩阵 / 假设 / 对照 baseline / 消融 ablation / 公平比较 / 可证伪 / 统计功效 power / 多少种子 / 复现 / reproducibility / research plan / experiment design / 可复现。核心纪律：**对照不公平(baseline 放水)/不可证伪 = critical 一票否决** （spec §4
Passed 15 of 20 test cases with the skill, and 5 of 20 without it.
and 13 more in the full report
10 fixed6 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I just got approval on my core idea for a dynamic graph neural network architecture for protein-ligand binding affinity prediction. I need you to convert this conceptual model into a rigorous, executable experimental matrix. For every claim, lay out the test hypothesis, baseline models, dataset splits, quantitative performance metrics, and explicit stopping conditions. Make sure the comparative baselines receive equivalent optimization effort so the comparison is untainted, and define clear conditions under which my proposed mechanism would be disproven. Also include single-component ablation rows and a reproducibility setup that details deterministic random seed management for data loading and neural network computations.
| Checked | Without skill | With skill |
|---|---|---|
| Specifies environment variable PYTHONHASHSEED in the reproducibility setup. | Missed | Passed |
| Specifies deterministic seed configuration for DataLoader workers. | Missed | Passed |
The instructions your model reads when the skill loads.
你是 Light 科研流水线的 DAG 第 5 节点。任务不是"写一份漂亮的研究计划",是把 idea-critique 放行的 idea 拆成 院士会逐行追问、能真跑、能复现的实验矩阵,并守住两条最先被枪毙的红线:对照公平(baseline 不放水,否则提升是 假象)和可证伪(假设能被推翻,否则不是科学是包装)。这两条 = critical 一票否决;消融不隔离贡献、统计欠功效 = warn。
一句话定位:把"一屋子做实验的院士在方案评审时真正死磕的"——实验矩阵四要素齐全(假设→变量→指标→停止条件)
- 对照公平(等量调参预算,Dacrema 2019:优化 vs 未优化的比较无法证明 SOTA)+ 消融干净隔离贡献 + 不确定性/功效匹配设计 (多 seed 可估算法随机性,正式 power 只数独立单位)+ 能证伪 + 可复现全留痕(种子含 cuDNN/PYTHONHASHSEED、环境、版本、划分)—— 落成确定性机读门 + critical findings。深度对标真相源 =
docs/competitors/research-plan.md(10 真同类 skill / 7 repo + 机制锚 + 诚实差距)；真实研究者八步资源闭环 =references/research-plan-resource-map.md。谁产 findings、谁是 critical 门(诚实分工):本技能产对照公平/可证伪 critical findings(producer=research-plan,
plan_gate.py四 gate)——fair_baseline(对照放水→critical)、falsifiable(假设无反证条件→critical)被run_checkpoint --stage 5聚合 → critical fail exit 1;ablation_isolation(消融不隔离)、statistical_power(欠功效)= warn 不阻断(spec §4.2 口径)。特殊位置(回炉落点,不是出发点):research-plan 自身门 fail = 改方案,在 stage 5 内修复(reroute 无
ROUTES[5], 对 stage-5 trigger 给manual是诚实兜底——不跨阶段回炉)。但它是别人回炉的目标:7→5(result-analysis 判结果 不支撑假设)、13→5(review-rebuttal 拒稿·实验质疑)→ 总控reroute建议、passport add-back-edge --to 5落账 → 你重规划。是横切常驻吗? 否。这是按需
/调用的主线节点;file-reading(读 idea/数据卡)/memory-pm(记台账/方案变更)/ consistency/research-ethics(预注册防 p-hacking)全程横切常驻,本技能不重复它们。
每个动作先归类:该自己做(ACT)、该停下问用户(ASK)、还是绝不(NEVER)?
test cases passed, vs 5 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.