skills-ws
Version:
87 agent skills for AI coding assistants — marketing, growth, web3, dev, design & operations. Built for OpenClaw, Claude Code, Cursor, and Codex.
15 lines (10 loc) • 1.75 kB
Markdown
## How to run a CRO engagement (don't start with the checklist)
The 100-point audit below is a **first-pass diagnostic**, not the work itself. A real CRO program is a loop:
1. **Instrument & baseline** — confirm conversion tracking is correct, get 2–4 weeks of clean data, know your current CVR, revenue-per-visitor (RPV), and bounce. Never optimize a page you can't measure.
2. **Diagnose** — combine quant (GA4 funnels, scroll/click heatmaps) with qual (session replays, 5-second tests, user interviews, on-page surveys). The checklist scores the page; diagnosis finds *why* it leaks.
3. **Hypothesize** — write each idea as: *"Because [evidence], we believe [change] will cause [metric] to move for [segment]. We'll know from [primary metric]."* No hypothesis, no test.
4. **Prioritize** — score every idea by **PIE** (Potential, Importance, Ease) or **ICE** (Impact, Confidence, Ease), 1–10 each, rank by average. See the prioritization rubric below.
5. **Experiment** — run a powered A/B test (sample size + duration computed up front; see the experimentation section). Most "wins" that aren't powered are noise.
6. **Analyze & ship** — check SRM, primary metric, and guardrails before declaring a winner. Ship winners, document losers, feed learnings back to step 2.
**Expected effect sizes (set expectations honestly):** mature pages move 2–10% relative per winning test; a brand-new page or a hero/offer rework can move 20–50%+. Anyone promising "+127% from a button color" is selling, not testing — the example testimonials in this doc are illustrative placeholders, not benchmarks.
Sibling skills: popups/exit-intent/cookie-consent UX → `popup-cro`; multi-step signup/onboarding funnels → `signup-flow-cro`.