Available1One-Page Site Builder
Turn your product brief into a responsive one-page website and a portable content document. An original, free Skillrove workflow with an editable fictional example.
Codex +2Conversion Experiment Labv1.0.0
Turn page observations into a conversion experiment backlog, control/variant copy, nested-cohort metrics and a tracking contract. Work from evidence, define one change and hand off a measurable experiment. Original Skillrove workflow.
Interact with the sample. Scroll inside to explore.
Made with this SkillAn evidence-led experiment plan
Open full exampleActual page observations · three untested hypotheses
What you get
An evidence-led experiment planWhat you can make
- Connect page observations to a prioritized experiment backlog.
- Compare nested-cohort counts, conditional rates and stage drop-offs.
- Hand off one-change variants, tracking contracts, guardrails and rollback decisions.
Explore delivered files7 groups
index.htmlplan.jsonexperiments.csvtracking-plan.jsoncopy-variants.mdhandoff.mddelivery-manifest.json
About this skill
Capabilities: build 2–8 experiment hypotheses from 1–24 attributed observations across a 2–8-stage journey. Compare supplied nested-cohort counts, conditional rates and drop-offs; unknown measurements stay unknown. Review evidence, assigned priority/effort, single-change proposals, control/variant copy, primary outcomes, guardrails, stopping decisions and rollback.
Deliverables: interactive four-view experiment lab, reusable plan.json, CSV backlog, copy-variants.md, launch handoff, SHA-256 manifest and draft tracking-plan.json. The contract covers assignment/exposure events, stable assignment, session attribution, deduplication and a required success-window decision.
Read the full workflow
Requirements and run: Python 3.10+ standard library, offline, no API key. python3 scripts/build-lab.py --input examples/experiment.json --output ./sample-lab. Your agent inspects the actual page/data and implements a selected experiment within your existing authorization.
Validation: actual Skillrove pricing/detail observations generated three independent hypotheses with no analytics counts invented. Independent fictional product plan, known and unknown cohorts, plan regeneration, source links, field validation, export integrity and desktop/mobile report interactions tested.
Limits: no experiment, tracker or variant is activated by exporting a plan. Rates are descriptive, not statistical significance or causality. The tool does not predict uplift, choose sample size or declare a winner. Complete design decisions and verify collected outcomes before judging performance.
Version 1.0.0: original MIT-licensed implementation; methodology attribution included. Individual purchase and active membership unlock the package.
FROM PACKAGE TO FIRST RESULT
Your first conversion lab.
Build the fictional example, then replace its observations with your own page evidence. The public result proposes three experiments from actual Skillrove product and pricing pages.
US$4.99 · MIT licensePython 3.10+ · offlineNo API key or paid provider
- 01
Choose your agent
These steps use a project folder. Open the project in your agent and run terminal commands from its root.
Package folder
.agents/skills/conversion-experiment-lab - 02
Add the package
Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.
Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.
- 03
Run the included sample
Manual sample commands and technical details
Read SKILL.md, review the generator and check its runtime requirements before running:
cd .agents/skills/conversion-experiment-lab python3 scripts/build-lab.py --input examples/experiment.json --output ./sample-labYour first resultSwitch between experiments, journey metrics, copy and source evidence. Inspect the event contract for assignment, exposure, attribution, deduplication and the required success-window decision. Missing measurements stay unknown; plan.json can be edited and used as your next input.
Python 3.10+ standard library only, offline. The generator does not connect analytics, activate variants or prove conversion uplift. Review the actual cohort, consent, design and stopping rule before implementing an experiment.
If sample-lab already exists, change the output to ./sample-lab-2. Existing files are never overwritten.
Prefer to ask your agent?
Use Conversion Experiment Lab at .agents/skills/conversion-experiment-lab. Read SKILL.md and review scripts/build-lab.py. Run examples/experiment.json into a new output folder and show me all generated files. Keep fictional sample content clearly labeled.
Reviews0
Share your first result
Tried this workflow? Help others decide with an honest review.
Before you choose this Skill
How do I get Conversion Experiment Lab?
The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.
Which agents can use this skill?
This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.
What files can this workflow generate?
The documented 1.0.0 workflow lists: index.html; plan.json; experiments.csv; tracking-plan.json; copy-variants.md; handoff.md; delivery-manifest.json. Some files or exports are optional; follow the package’s setup and inspect the delivered result.
What should I check before using the result?
Python 3.10+ standard library only, offline. The generator does not connect analytics, activate variants or prove conversion uplift. Review the actual cohort, consent, design and stopping rule before implementing an experiment.
More skills to explore
View all skillsAvailable1Codex +2
$4.99One-time purchase