Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/ablation-planner
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.
Passed 17 of 20 test cases with the skill, and 10 of 20 without it.
and 6 more in the full report
9 fixed10 passed either way2 still failing1 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.
What information must be captured for each entry in a hyperparameter sensitivity sweep table?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies that hyperparameter entries must include the target parameter, test range, hypothesis, and priority. | Missed | Passed |
The instructions your model reads when the skill loads.
Systematically design ablation studies that answer the questions reviewers will ask. The reviewer agent leads the design; the local executor reviews feasibility and implements.
gpt-5.4 - Used via a secondary Codex agent for reviewer-style ablation design./result-to-claim with claim_supported = yes or partial/auto-review-loop identifies missing ablationsRead available project files to build the full picture:
docs/research_contract.md, project notes, or method docs)EXPERIMENT_LOG.md, EXPERIMENT_TRACKER.md, or W&B)/result-to-claim output or project notes)spawn_agent:
model: REVIEWER_MODEL
reasoning_effort: xhigh
message: |
You are a rigorous ML reviewer planning ablation studies.
Given this method and results, design ablations that:
1. Isolate the contribution of each novel component
2. Answer questions reviewers will definitely ask
3. Test sensitivity to key hyperparameters
test cases passed, vs 10 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.