brainstorming
OBobra/superpowers298k2,631 new stars in the last 7 days
experimental-design
Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.
- Star
- 14,635
- Category
- Requirements & planning
- License
- MIT
- Last commit
- Aug 19, 2026
researchclaw/skills/builtin/experiment/experimental-design/SKILL.md
View on GitHubExperimental Design Best Practice
- ALWAYS include meaningful baselines (not just random):
- At least one classical method baseline
- At least one recent SOTA method baseline
- A simple-but-strong baseline (e.g., linear probe, k-NN)
- Use MULTIPLE random seeds (minimum 3, ideally 5)
- Report mean +/- std across seeds
- Design ablations that isolate EACH key component:
- Remove one component at a time
- Each ablation must be meaningfully different from baseline
- Control variables: change only ONE thing per comparison
- Use standard splits (train/val/test) — never test on training data
- Report wall-clock time and memory usage alongside accuracy
Similar Skills
diagnosing-superpowers
OBobra/superpowers298k2,631 new stars in the last 7 days
dispatching-parallel-agents
OBobra/superpowers298k2,631 new stars in the last 7 days
using-superpowers
OBobra/superpowers298k2,631 new stars in the last 7 days
executing-plans
OBobra/superpowers298k2,631 new stars in the last 7 days
loop-me
MAmattpocock/skills288k10,178 new stars in the last 7 days