Menu

Individual skill

exp-design

0upvotes

Idea-driven experiment design with iterative ablation — method candidate generation (direct / hybrid / cross-idea combination) → benchmark selection → iterative ablation (non-linear: ablation can trigger method simplification and re-planning) → sensitivity analysis → main experiment → optional generalization → deep analysis of intermediate quantities. Use when designing a full experiment suite for an idea after pilot evaluation.

i18n/en/skills/exp-design/SKILL.md

Read pinned source

Source commit 3c3922f02a97c347f66b91e1ded2371c963da538

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.

Repository context

Repository stars (not skill ratings)
1,730
Repository last updated
Oct 30, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# /exp-design

> Design a complete, non-linear experiment suite for an idea.
> This skill supports method candidate generation, iterative ablation with method simplification, sensitivity analysis, and deep analysis of intermediate quantities.
> The ablation loop is the core non-linear feature: ablation results classify factors as essential/contributing/marginal/harmful, and marginal/harmful factors trigger method simplification and re-planning (capped at 2 iterations).

## Inputs

- `idea-slug`: the idea to design experiments for (reads from `wiki/ideas/{slug}.md`)

## Outputs

- Experiment wiki pages: `wiki/experiments/{exp-slug}.md` — one per experiment block (ablation, sensitivity, main, generalization, analysis), each with `status: planned` and `linked_idea` set
- Master design document: `experiments/designs/{slug}-master.md` — detailed specs for all experiment blocks
Back to top