create-experiment
Skill127 starsChanged 30 days agoApache-2.0View on GitHub
Thin compatibility entrypoint for creating a new Harness FME experiment. Invokes manage-experiments' Create experiment flow directly - same scope, parent/environment resolution, hypothesis, metrics, treatments, window, and rule - and returns the created experiment id plus verification. Use when asked to create an experiment, set up an A/B test, or design a new experiment. Do NOT use for updating, pausing, resuming, completing, archiving, or deleting an experiment (manage-experiments), or for explaining results (review-experiment-results). Trigger phrases: create experiment, set up an A/B test, design an experiment, launch a test, new experiment for X.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- kaiohenricunha/dotbabeltheir own version, first seen Oct 17, 2026
- Conzel/personal-claude-code-skillstheir own version, first seen Apr 24, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Conzel/personal-claude-code-skills★ 2same name
- kaiohenricunha/dotbabel★ 0same name
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 repository76 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/harness.mdcCursor rule
- manage-rolesSkill
- manage-usersSkill
- create-agentSkill
- create-agent-templateSkill
- dbops-changesetSkill
- choose-metricSkill
- cleanup-feature-flagsSkill
- create-feature-flagSkill
- create-metricSkill
- discover-feature-flagsSkill
- explain-flagSkill
- feature-flag-onboardingSkill
- fme-pipelineSkill
- instrument-feature-flagSkill
- instrument-metricSkill
- manage-experimentsSkill
- manage-flag-lifecycleSkill
- manage-segmentsSkill
- review-experiment-resultsSkill
- update-flag-targetingSkill
- create-connectorSkill
- create-environmentSkill
- create-infrastructureSkill
- create-secretSkill
- create-serviceSkill
- ai-operationsSkill
- analyze-costsSkill
- audit-reportSkill
- chaos-code-risk-scanSkill
- chaos-dr-testSkill
- chaos-experimentSkill
- create-policySkill
- deployment-readinessSkill
- dora-metricsSkill
- gitops-statusSkill
- incident-responseSkill
- manage-idpSkill
- manage-slosSkill
- optimize-pipelineSkill
- pr-analysisSkill
- scorecard-reviewSkill
- security-reportSkill
- sei-analyticsSkill
- template-usageSkill
- create-pipelineSkill
- create-pipeline-v1Skill
- create-templateSkill
- create-triggerSkill
- debug-pipelineSkill
- manage-freeze-windowsSkill
- migrate-pipelineSkill
- run-pipelineSkill
- create-sbomSkill
- enforce-sbomSkill
- manage-artifactsSkill
- manage-cdeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Create experiment flow, named in tool-map.md.
- Very specific: line 39
Read manage-experiments/SKILL.md and follow its Phase 1: Establish scope and Create experiment section (Steps 1-8) exactly as written, …
- Very specific: line 48
If the tool interface you're running under can't follow a markdown link to load another skill's file on demand, read …
- Distinctive: line 72
No independent tool calls: every MCP/CLI operation happens inside the delegated manage-experiments flow, so there's no duplicate scope …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create Experiment
Compatibility entrypoint kept for direct /create-experiment invocation. This
skill does not duplicate any workflow - it hands the entire creation flow to
manage-experiments's Create experiment
section and returns once that flow completes.
Tools
Performs no operations of its own; it uses the operations of manage-experiments' Create experiment flow, named in tool-map.md.
Instructions
Step 1: Delegate
Read manage-experiments/SKILL.md and follow
its Phase 1: Establish scope and Create experiment section (Steps 1-8)
exactly as written, using the current request's scope (org/project), parent
flag + environment, hypothesis, metrics, treatments, window
(startAt/endAt), and rule. Do not re-derive or re-interpret any of that
section's logic here - this skill has no independent instructions for
resolving treatments, choosing metrics, or drafting the payload; it only
exists so /create-experiment remains a valid invocation.
If the tool interface you're running under can't follow a markdown link to
load another skill's file on demand, read
skills/fme/manage-experiments/SKILL.md directly (same repo, relative path) and
proceed the same way.
Step 2: Return the result
Once manage-experiments' Step 8 (Verify) completes, report the created
experiment's id, status, and the verified fields (baseline/comparison
treatments, key/supporting metrics, rule) back to the user. Don't add a
second verification pass - manage-experiments' Step 8 is authoritative.
Examples
- "Create an experiment on the new-checkout flag" → delegate to manage-experiments Create flow, return created id
- "Set up an A/B test for the pricing page" → same delegation
- "Pause experiment pricing_test_2" → not this skill; route to manage-experiments (Update)
- "Did the checkout experiment win?" → not this skill; route to review-experiment-results
Performance Notes
- No independent tool calls: every MCP/CLI operation happens inside the delegated manage-experiments flow, so there's no duplicate scope resolution or double-verification to optimize away here.
Troubleshooting
| Issue | Resolution |
| User asks to update/pause/resume/complete/archive/delete an existing experiment | Route to manage-experiments (Update/Delete), not this skill |
| User asks about results, winner, or significance | Route to review-experiment-results |
| manage-experiments' Create flow stops on a missing decision (hypothesis, treatments, metrics) | Surface that stop to the user here too - don't guess on its behalf |
| Delegated flow fails partway (e.g. 404 on parent, 409 duplicate name) | Report the error as manage-experiments' Troubleshooting table describes; don't retry with invented values |
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.