experiment-results-interpreter SKILL.md skillA
experiment-results-interpreter from testland/qa is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add testland/qa/experiment-results-interpreter@v1.1.18Pins v1.1.18 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- testland/qa
- Path
plugins/qa-feature-flags/skills/experiment-results-interpreter/SKILL.md- Versions recorded
- 2
- Latest version
- v1.1.18, committed Oct 11, 2026
- First version recorded
- Aug 13, 2026
- Size
- 14,557 bytes
- Repository stars
- 11
- License
- MIT
Interprets the results of a valid online controlled experiment, one whose harness, SRM, and telemetry have already been confirmed. Covers the distinction between practical and statistical significance, reading confidence intervals instead of binary p-values, novelty and primacy week-over-week decay that causes post-ship reversion, interaction effects from concurrent experiments, Simpson's paradox in segmented results, and the ordered guardrail-check sequence required before a ship decision -…
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
# experiment-results-interpreter ## Overview The `ab-test-validity-checklist` skill confirms that an experiment was run correctly - clean SRM, honest peeking discipline, pre-declared OEC. This skill covers the **next question**: given a valid experiment, what does the result actually mean, and is it safe to ship? The two most common failure modes at this stage, per Kohavi, Tang, Xu *Trustworthy Online Controlled Experiments* (Cambridge Univ. Press, 2020, ISBN 9781108724265), are: 1. Shipping a result that is statistically significant but not practically meaningful. 2. Shipping a result that will not persist because it reflects novelty, primacy, or interaction artefacts rather than genuine long-term user value. This skill is a **pure reference** for data scientists and PMs reading final experiment dashboards. ## When to use - Reading the results of an experiment that has reached its pre-declared sample size or end date. - Preparing the ship/no-ship decision document. - Auditing a past ship decision that produced unexpected post-launch outcomes. - Coaching a PM or analyst who is over-indexing on p-values or under-checking guardrails. ## How to use …
Read the whole file at its exact version.
How to install
mdr add testland/qa/experiment-results-interpreter@sha256:f5371c76bd5b8460The line at the top of this page pins the label v1.1.18, 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_oq36lph4ccztpmsd)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 13, 2026 and Oct 11, 2026, about one every 58 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.18 latest | 2026-10-11 | a1bd3f7 | 14,557 B | A | view · diff |
| git:20260813.7f38a7f | 2026-08-13 | 7f38a7f | 14,537 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 (14557 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
testland/qa · 11 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_oq36lph4ccztpmsd GET https://markdownregistry.com/api/v1/resolve?ref=testland/qa/experiment-results-interpreter GET https://markdownregistry.com/api/v1/blob/f5371c76bd5b84603924a6b2acba00998f8fcc6b3ef5acdfde4c7f50b036c3b8
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.