experiment
Skill4 starsChanged 6 days agoMITView on GitHub
Design or read out a controlled experiment (A/B test) — hypothesis, power analysis, pre-registered primary metric, guardrails, randomisation unit, then sample-ratio and effect-size analysis with a clear ship/no-ship decision. Use to plan a test before launch or to analyse one after it ends.
29 other projects use a version of this.
Adopted by
Most recently taken up by
- adithyanraj03/dsh-skills-packtheir own version, first seen Nov 15, 2026
- HiteSit/real-scientist-skillstheir own version, first seen Nov 15, 2026
- SethGammon/Citadeltheir own version, first seen Nov 4, 2026
- DaeSeokSong/oh-my-ouroborostheir own version, first seen Nov 1, 2026
- Anglesite/anglesite-skillstheir own version, first seen Oct 27, 2026
- simota/agent-skillstheir own version, first seen Oct 23, 2026
Used with
Projects with it also use cost, decide and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
maxvaegaSkillcost
Estimate what Claude Cowork / Claude Code conversations would cost if run on the pay-per-token Claude API instead of the subscription. Reports token counts and cache-aware API cost in USD and EUR, for the current conversation or for the whole history (cost per conversation). Trigger when the user asks things like "how much would this conversation cost on the API", "API cost of my Cowork conversations", "token usage / token count", "cost per conversation", "/cost", or wants to compare subscription vs API pricing.
Also in 3 projects that use this
dirienSkilldecide
Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.
Also in 3 projects that use this
javatarzSkillwiki
Access and manage the local GitHub Wiki clone. Use this skill when you need to read wiki content (architecture, design docs, guides), update wiki documentation, check wiki status, or push wiki changes. The wiki contains high-level system design and architectural documentation.
Also in 3 projects that use this
HeshamFSSkillloop
Run a command or check on a recurring interval
Also in 3 projects that use this
VercelSkillworkflow
Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of "workflow", "durable functions", "resumable", "workflow sdk", "queue", "event", "push", "subscribe", or step-based orchestration.
Also in 3 projects that use this
ibahgatSkillautopilot
Run autonomous multi-stage execution loops until acceptance criteria pass or blockers are reached.
Also in 3 projects that use this
Other versions29 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 29
- rohanpsingh/LearningHumanoidWalking★ 1.2ksame name
- SethGammon/Citadel★ 927same name
- menkesu/awesome-pm-skills★ 441same name
- ai-analyst-lab/ai-analyst★ 304same name
- simota/agent-skills★ 99same name
- sunnnybala/Rstack★ 69same name
- Kastalien-Research/thoughtbox★ 64same name
- logly/mureo★ 64same name
- alirezarezvani/gaios★ 50same name
- skyf0xx/gambit★ 29same name
19 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- build-dashboardSkill
- build-modelSkill
- build-pipelineSkill
- causal-analysisSkill
- connect-dataSkill
- define-kpisSkill
- evalSkill
- forecastSkill
- health-checkSkill
- investigate-metricSkill
- make-deliverableSkill
- powerbiSkill
- privacy-reviewSkill
- research-domainSkill
- scorecardSkill
- setup-teamSkill
- tableauSkill
- triageSkill
- upgradeSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 27 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Default to design if no results exist yet.
- Distinctive: line 26
Add 1–3 guardrail metrics (things that must not get worse: latency, refunds, churn).
- Distinctive: line 38
Variance reduction (CUPED): If the metric has a pre-experiment history per unit, plan to adjust for it.
- Distinctive: line 50
Check for interference: If one unit's treatment can change another's outcome — marketplaces, shared inventory, pricing, social features — …
- Distinctive: line 63
Check sample ratio mismatch (SRM) first: If the actual split deviates from the intended allocation beyond chance, the assignment is broken …
- Very specific: line 100
Close the loop: Update experiments/README.md with the decision, log the ruling in knowledge/decision-log.md, and if the test changed a …
“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Experiment — A/B Test Design & Readout
Owner: data-scientist, with metrics-steward on metric definitions and analytics-engineer
for the analysis dataset. Args name the test and mode, e.g. /experiment design new checkout flow
or /experiment readout pricing-page test.
This skill has two modes. Design runs before launch; Readout runs after the test ends. Default to design if no results exist yet.
Mode A — Design (before launch)
- Frame the decision. What ships if it wins? What's the cost of a false positive? If the answer doesn't change a decision, an experiment may be overkill — say so.
- State the hypothesis as a directional, testable claim: "Changing X will increase [primary metric] by at least [MDE] for [population]." The minimum detectable effect (MDE) is the smallest change worth shipping, set with the business — not whatever turns out significant.
- Pick the primary metric — one — from
knowledge/metrics-catalog.md. Pre-register it. Add 1–3 guardrail metrics (things that must not get worse: latency, refunds, churn). Picking the winner after the fact from many metrics is how teams ship noise. - Choose the unit of randomisation (user, account, session, cluster) and confirm the analysis unit matches it. Mismatch (e.g. randomise by user, analyse by session) breaks the statistics. Watch for cross-unit contamination/network effects.
- Power analysis. Compute required sample size and run duration from: baseline rate (from
the catalog/marts), MDE, significance level (default α=0.05), and power (default 80%). State
the assumptions. If the required duration is implausible, the MDE is too small — renegotiate,
don't peek early. Two ways to need less traffic, both decided now, not after the result
(
analytics.mdPart 5):- Variance reduction (CUPED). If the metric has a pre-experiment history per unit, plan to adjust for it; the sample needed falls by the squared correlation between the pre-period and in-experiment values. Record the covariate and its window in the design.
- A capped metric for heavy-tailed outcomes (revenue per user): pre-register the winsorisation percentile.
- Decide how the test will be monitored. People will look at the dashboard before the end. Pick one and write it down: fixed horizon (interim looks are for guardrails and broken assignment only — no decisions), group-sequential (a stated number of looks with an alpha-spending rule), or always-valid intervals (safe to check any time, at the cost of width). An unplanned early stop on a significant-looking interim result is not a result.
- Check for interference. If one unit's treatment can change another's outcome — marketplaces, shared inventory, pricing, social features — randomise clusters or use a switchback, and size the test for the number of clusters, not the number of users.
- Write
experiments/YYYY-MM-DD-<slug>/DESIGN.md: hypothesis, primary + guardrail metrics (with catalog links), randomisation unit, MDE, sample size, planned duration, the monitoring method and stop rules, any variance-reduction covariate, how secondary metrics and segments will be corrected for multiple comparisons, and what decision each outcome triggers. If the test collects or uses personal data in a new way, run/privacy-reviewfirst. For high-stakes or customer-affecting tests, confirm the design with the user before launch. Add a row toexperiments/README.md.
Mode B — Readout (after the test ends)
- Check sample ratio mismatch (SRM) first. If the actual split deviates from the intended allocation beyond chance, the assignment is broken — stop and diagnose; do not interpret the result.
- Profile the data per
standards/sql-and-data-standards.md: exposure counts per arm, date coverage, dedup at the randomisation unit, exclusions (and why). - Estimate the effect on the pre-registered primary metric: point estimate with a confidence interval, at the randomisation unit. Report effect size in business terms, not just a p-value. Check every guardrail metric. Use exactly the analysis the design registered: the CUPED adjustment if one was planned (and say how much it narrowed the interval), the sequential boundary if looks were planned. If the metric is a ratio whose unit differs from the randomisation unit (clicks per session, revenue per order), get the variance from the delta method or a bootstrap over randomisation units — a row-level test understates it.
- Pressure-test (run the
analytics.mdPart 1 traps and Part 5): Twyman's law first — a surprisingly large effect is a bug until shown otherwise, so check logging, assignment, and the join before believing it; no peeking-based early calls; secondary metrics and segment cuts corrected for multiple comparisons (Holm for a confirmatory family, Benjamini–Hochberg for exploration) and labelled as hypotheses, not results; segment heterogeneity (does one segment drive it — Simpson's paradox?); novelty/primacy effects; outlier sensitivity on skewed metrics (report robust/median where the metric is heavy-tailed). Distinguish "no effect" from "underpowered."- Incremental effect, not just averages. The treated-vs-control gap is the causal lift — the raw treated rate is not. When the effect varies across segments, that heterogeneity is the seed of uplift modelling: the clean control group lets
data-scientistmodel who is persuadable (largest incremental effect) so future targeting spends only where the treatment actually moves the needle.
- Incremental effect, not just averages. The treated-vs-control gap is the causal lift — the raw treated rate is not. When the effect varies across segments, that heterogeneity is the seed of uplift modelling: the clean control group lets
- Decide and write
experiments/YYYY-MM-DD-<slug>/RESULTS.md:- Verdict: ship / don't ship / inconclusive — with the effect estimate + CI and a confidence level.
- Guardrail check, segment notes, and any caveats that change the conclusion.
- Impact if shipped (quantified) and what to monitor post-launch (hand to
performance-monitor). - For customer-affecting decisions, note the fairness trade-off explicitly (
analytics.mdPart 1) — equal error rates and equal predictive value can't both hold when base rates differ. - The provenance footer (
standards/reporting-standards.md). A ship decision goes toanalysis-reviewerbefore it is announced.
- Close the loop. Update
experiments/README.mdwith the decision, log the ruling inknowledge/decision-log.md, and if the test changed a metric's interpretation, route it tometrics-steward.
Created by Colin Beck — https://www.linkedin.com/in/beckcolin/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

