Conversion Optimization
Leaking flow → measured, tested funnel
Takes one leaking conversion flow — a landing page, a signup, a checkout, an in-app onboarding — to a measured, tested funnel. It orchestrates six skills across seven phases, asking you the decision questions at every step and recording every result in your project’s docs/ folder so the journey resumes across sessions.
What is the Conversion Optimization journey?
One flow leaks money and nobody agrees why. Seven phases find the leak with numbers, learn the reason from customers in their own words, then fix message, offer, proof and friction in that causal order — and every fix ships as a test with a pre-committed metric, all of it recorded in docs/ so the work spans sessions.
One prompt runs it
npx skills add wondelai/skills/conversion-optimization --global This skill is compatible with Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent, and other agentskills.io-compatible agents.
Example prompts for the Conversion Optimization journey
Our checkout loses 60% at the payment step — find the leak and fix it. using conversion-optimization skill
Checkout leakRun the conversion journey on our signup flow, starting with the funnel numbers. using conversion-optimization skill
Signup funnelResume the funnel work from the tracker and design the next test. using conversion-optimization skill
Resume journeyWhen to use Conversion Optimization — and when not to
Reach for it when
- Fix checkout or signup abandonment on one specific flow
- Diagnose onboarding drop-off inside a product
- Replace guesses about why people quit with researched objections
- Strengthen the offer and place honest proof at each point of doubt
- Ship every fix as a test with a pre-committed metric
Reach for something else when
- The whole site needs a look, message and speed pass rather than one flow — that is Improve a Website.
- The flow converts fine and the problem is that too few people reach it — Grow a Website is the traffic journey.
- There is no site yet to optimize — Create a Website builds the first version.
- You want one landing-page audit this afternoon — CRO Methodology alone is the lighter tool.
Frequently asked questions
How do I install the Conversion Optimization journey?
Run npx skills add wondelai/skills/conversion-optimization --global. It takes about 30 seconds and needs no account. The Conversion Optimization skill then works in Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw and Hermes Agent — anything that reads the open agentskills.io format — and your agent loads it on its own when a task calls for it. It is free and MIT-licensed, and the source is at https://github.com/wondelai/skills.
Which skills does the Conversion Optimization journey run, and what does it produce?
It orchestrates 6 skills across 7 phases — Lean Analytics, CRO Methodology, StoryBrand Messaging, $100M Offers, Influence Psychology, Design of Everyday Things — asking you one decision question per phase. Each answer is written to your project's docs/ folder (docs/METRICS.md, docs/FUNNEL.md, docs/EXPERIMENTS.md, docs/POSITIONING.md, docs/OFFER.md, docs/DESIGN.md, docs/CONVERSION-OPTIMIZATION-PLAN.md), so the journey survives across sessions and you keep the reasoning, not just the output.
Why is the order message, then offer, then proof, then friction?
Because it is causal, not alphabetical. Cutting friction only pays once someone wants the thing: removing a form field from a page whose promise nobody understands moves nothing. So the journey raises motivation first — does the step promise the visitor’s own outcome, is the offer worth acting on now, is there proof where doubt appears — and only then makes the act of completing it effortless. Running it backwards is the most common way a redesign loses conversions.
We barely have traffic. Can we still A/B test?
Often not, and the journey asks about volume in the intake precisely so it does not pretend otherwise. Below the traffic needed for significance, phase seven stops proposing split tests and switches to pre-committed before/after windows, guardrail metrics, and qualitative evidence — session recordings and exit surveys against a stated prediction. You still commit to the metric in advance; you just stop claiming a p-value you cannot earn.
What do the two gates actually block?
Phase one will not let the journey pick a fix before a number says where the flow leaks — with no instrumentation, that phase starts by adding it. Phase two will not let a fix ship on a hunch about why people drop; the objections have to come from the customer’s own words in exit surveys, recordings, tickets or calls. Both may be deferred, never skipped: a fix with no researched reason behind it goes back to phase two.
Does this work on in-app onboarding, or only marketing pages?
Both. The unit of work is a flow with one action at the end, which describes an in-product onboarding as well as a checkout. What changes is the evidence: product analytics and session recordings instead of page-level funnels, and phase six leans harder on Design of Everyday Things because the friction is in the interface rather than the form. If the whole product’s engagement is the concern rather than one flow, Improve an App is the better fit.
Install Conversion Optimization
Free, open-source, and ready in 30 seconds.
npx skills add wondelai/skills/conversion-optimization --global MIT Licensed · Works with Claude, Claude Code, Claude Cowork, Codex, Cursor, OpenClaw, Hermes Agent & other agentskills.io agents · No account needed
Don’t guess your AI engineering level.
Measure it.
AI Developer Scorecard
How production-grade is your AI engineering?
Twenty-five questions across the practices that separate vibe-coding from production-grade engineering. Instant score, per-section breakdown, and a 30/60/90-day playbook.
Score 0–75 · 30/60/90-day playbook Score yourself For CTOs & foundersCTO Scorecard
Is your engineering team ready for AI at scale?
Twenty-five questions on how your org adopts AI — adoption, governance, automation, and ROI. See where you sit on the path from Reactive to Strategic Leader.
Score 0–75 · Reactive → Strategic Leader Score your orgWe build the skills you already use. Now we’ll build yours.
Fixed-price engagements, quoted after a 15-minute call. Shipped to production, or you don't pay the final milestone.