field-experiment SKILL.md skillA
field-experiment from ericluo04/claude-academic-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ericluo04/claude-academic-workflow/field-experiment@git:20261009.20e3598Pins git:20261009.20e3598 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ericluo04/claude-academic-workflow
- Path
skills/field-experiment/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261009.20e3598, committed Oct 9, 2026
- First version recorded
- Aug 1, 2026
- Size
- 27,665 bytes
- Repository stars
- 25
- License
- a license file GitHub does not identify
Design, analyze, and write up randomized experiments (field experiments, A/B tests, RCTs): stratified and clustered designs, randomization inference, covariate adjustment done right, noncompliance, attrition and gated outcomes, treatment-effect heterogeneity, and interference. TRIGGER on "A/B test", "randomized experiment", "RCT", "field experiment", "randomized holdout", "lift test", "randomization inference", "stratified randomization", "matched pairs", "rerandomization…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Field experiments An opinionated experimental workflow grounded in a read canon (references/canon.md): the Athey-Imbens handbook chapter as the spine (randomization-based inference first), Freedman's logistic-regression critique and Lin's repair for covariate adjustment, Guo-Basse's generalization to nonlinear outcomes, and Lee's bounds for attrition and gated outcomes. Deliverable: the recommendation with its citation, the R estimation and diagnostics code, and a methods paragraph. The skill stops at the four stop points in ../causal-design/references/shared-rules.md (section "Stop points") and puts each choice to the user. Before any estimation, stop and confirm three things with the user: the estimand (cluster-average or unit-average under clustering), the pre-specified covariate list, and whether outcomes have been seen. Current as of 2026-10-09; refresh per shared-rules (../causal-design/references/shared-rules.md, section "Refresh path"). Nothing enters the canon without the user's approval. The same refresh checks every pin in the package index of references/details.md against CRAN and reads the NEWS of any package with a new major version. …
Read the whole file at its exact version.
How to install
mdr add ericluo04/claude-academic-workflow/field-experiment@sha256:6f470dd8615d341dThe line at the top of this page pins the label git:20261009.20e3598, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_kkyblczgsvdghsky)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Aug 1, 2026 and Oct 9, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261009.20e3598 latest | 2026-10-09 | 20e3598 | 27,665 B | A | view · diff |
| git:20261009.2daaeb2 | 2026-10-09 | 2daaeb2 | 28,236 B | A | view · diff |
| git:20261009.712d4e9 | 2026-10-09 | 712d4e9 | 27,937 B | A | view · diff |
| git:20261009.9e467a6 | 2026-10-09 | 9e467a6 | 20,888 B | A | view · diff |
| git:20261009.ebdc946 | 2026-10-09 | ebdc946 | 18,699 B | A | view · diff |
| git:20260828.039723a | 2026-08-28 | 039723a | 18,747 B | A | view · diff |
| git:20260805.0f0e26e | 2026-08-05 | 0f0e26e | 18,132 B | A | view · diff |
| git:20260802.bfe550f | 2026-08-02 | bfe550f | 17,942 B | A | view · diff |
| git:20260801.5eed4e2 | 2026-08-01 | 5eed4e2 | 17,918 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 (27665 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
ericluo04/claude-academic-workflow · 25 stars · license a license file GitHub does not identify · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_kkyblczgsvdghsky GET https://markdownregistry.com/api/v1/resolve?ref=ericluo04/claude-academic-workflow/field-experiment GET https://markdownregistry.com/api/v1/blob/6f470dd8615d341d042f82b8f806bdcc82168795aa5b1c0c33d8295ddb9c2ab1
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.