research-experiment
Design experiments that decide something, and diagnose failing ones by driving from surface symptom to root technical cause before changing anything. Treats improving a method as SGD on the idea, where the root-cause analysis IS the gradient — so it outputs a ranked candidate-cause table with a falsifying experiment for each, never a list of things to try, and ships a fully worked example diagnosis to show the granularity. Also covers minimum-viable exploratory design (binary feasibility criterion, one-day version), what comparison/ablation/demo experiments a paper needs, and which harder data to push to. Use whenever the user reports bad results, a method that doesn't work, metrics dropping after a change, asks what to run next, or asks which ablations a paper needs — and use it BEFORE proposing hyperparameter tweaks, because an unverified guess about the cause is a random gradient that burns a whole cycle. 中文触发:实验不work、效果不好、掉点了、做什么实验、实验设计、消融、ablation、baseline、调不出来、为什么不收敛、要不要试试调参、做什么demo。
Informations de source
- Dépôt
- HughYau/pengsida-learning-research-skills
- Dernière activité de la source
- 9 août 2026 à 08:48
- Langue détectée de SKILL.md
- chinois
- Étoiles
- 8
- Forks
- 1
Options d'installation
Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.
Vérifiez les fichiers source
Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.
Affichage de SKILL.md
- name
- research-experiment
- description
- Design experiments that decide something, and diagnose failing ones by driving from surface symptom to root technical cause before changing anything. Treats improving a method as SGD on the idea, where the root-cause analysis IS the gradient — so it outputs a ranked candidate-cause table with a falsifying experiment for each, never a list of things to try, and ships a fully worked example diagnosis to show the granularity. Also covers minimum-viable exploratory design (binary feasibility criterion, one-day version), what comparison/ablation/demo experiments a paper needs, and which harder data to push to. Use whenever the user reports bad results, a method that doesn't work, metrics dropping after a change, asks what to run next, or asks which ablations a paper needs — and use it BEFORE proposing hyperparameter tweaks, because an unverified guess about the cause is a random gradient that burns a whole cycle. 中文触发:实验不work、效果不好、掉点了、做什么实验、实验设计、消融、ablation、baseline、调不出来、为什么不收敛、要不要试试调参、做什么demo。