experimentation skillA
experimentation is agent-read markdown (skill) from nahid-sparktales/agent-dispatcher: Design an A/B test that can answer its question — hypothesis, randomization unit, power, duration, pre-registered analysis — and read the result honestly, including a null. Use when someone proposes testing a change, asks how long a test must run or whether a result is real, when a test is about to be stopped early, or when a flat result is being read as "no difference". Not for defining the metric itself (product-analytics), not for a change too small or too rare to power, and not for authorizi.
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
# Experimentation Most experiments fail before they launch: an unmeasurable hypothesis, a unit that leaks between arms, or a sample that was never going to detect the effect anyone cared about. Reading results is the short part. The design is where the answer is won or lost. ## When this fires A change is about to be tested, a running test is about to be read or stopped, or a result is being turned into a decision. It also fires as a refusal: when the traffic cannot support a test worth running, saying that early is the valuable output. ## Five states, not one - **Designed** — hypothesis, unit, primary metric, power and duration written down. - **Launched** — assignment is live and exposures are being logged. - **Read** — analysed at the pre-registered time, after sanity checks pass. - **Conclusive** — the result distinguishes the hypothesis from its absence at the stated power. - **Shipped** — a human decided to roll it out. Never a consequence of the other four. ## Procedure 1. **Write a falsifiable hypothesis with a direction and a size.** "Moving the plan selector above the fold will increase trial starts by at least 5% relative, because users currently scroll past …
Read the whole file at its exact version.
How to install
mdr add nahid-sparktales/agent-dispatcher/experimentation@git:20260919.a0d4f55mdr add nahid-sparktales/agent-dispatcher/experimentation@sha256:e116b7f5fe59e4c6Pin 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_pcyxnjywnmyigoq5)
1 badge views in 30 days
Versions
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 (8042 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
nahid-sparktales/agent-dispatcher · 49 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pcyxnjywnmyigoq5 GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/experimentation GET https://markdownregistry.com/api/v1/blob/e116b7f5fe59e4c6e6a3506fa55bd8976e068a214714a8fef06b6c963e491b00
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 nahid-sparktales/agent-dispatcher
Every file in nahid-sparktales/agent-dispatcher