experiment-design skillA
experiment-design is agent-read markdown (skill) from uchicago-dsi/ai-sci-skills: Design the smallest useful experiment matrix that separates important hypotheses and changes a decision. Use when the agent is proposing runs, ablations, sweeps, benchmarks, or debugging experiments across research or engineering projects..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Experiment Design ## Design For Decisions - The purpose of an experiment is to change a decision, not to accumulate runs. - Start from the decision that needs to be made. - Work backward to the smallest experiment that can separate the live hypotheses. ## Use This Output Contract When proposing an experiment, report: 1. Decision to make. 2. Live hypotheses. 3. Nearest control or baseline. 4. Minimal experiment matrix. 5. Predicted outcomes by hypothesis. 6. Readouts that will decide the result. 7. Stop rule and follow-up rule. 8. Baseline inheritance: what remains active if the candidate fails, and what evidence would be required to supersede it. ## Apply These Rules - Every arm should exist for a reason. - If two arms would not change the decision differently, remove one. - Prefer one-variable changes over broad combinatorial sweeps. - Freeze everything not under test. - Use the nearest baseline, not a weak or outdated one. - If the baseline is unfair, stale, or confounded, fix that before treating the experiment as decision-worthy. - Prefer cheap discriminative checks before expensive cluster-scale runs. …
Read the whole file at its exact version.
How to install
mdr add uchicago-dsi/ai-sci-skills/experiment-design@git:20260921.9b3de7cmdr add uchicago-dsi/ai-sci-skills/experiment-design@sha256:b92481b7c284685dPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_q3lstdwuuukg6xsv)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260921.9b3de7c latest | 2026-09-21 | 9b3de7c | 5,645 B | A | view · diff |
| git:20260716.0e01ec7 | 2026-07-16 | 0e01ec7 | 3,071 B | A | view · diff |
| git:20260320.999ac68 | 2026-03-20 | 999ac68 | 2,426 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5645 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
uchicago-dsi/ai-sci-skills · 20 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q3lstdwuuukg6xsv GET https://markdownregistry.com/api/v1/resolve?ref=uchicago-dsi/ai-sci-skills/experiment-design GET https://markdownregistry.com/api/v1/blob/b92481b7c284685d43307b1e3f7fce44e920eefa7d309ba34a7a49bd3bb778d9
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from uchicago-dsi/ai-sci-skills
Every file in uchicago-dsi/ai-sci-skills