Skip to content

JasonColapietro/suede-creator-skills / skills/suede-site-alchemy

suede-site-alchemy

Verified

Turn landing, launch, campaign, and product pages into measured conversion paths: funnel stage, friction, hero, proof, CTAs, pricing, mobile QA, and pre-registered experiments. Use when asked to "fix this page that gets no signups" or improve demos and sales from existing traffic. Implements and verifies changes within scope. NOT FOR: SEO scores (use suede-seo-audit), AI citations (use suede-ai-seo), promotion grades (use suede-visibility-grader), or copy alone (use suede-copy).

references/hypothesis-recipes.md

View on GitHub
# Suede Site Alchemy Skills: Hypothesis Recipes

## A/B Test Hypothesis Generator

For any CTA, headline, or section that needs improvement, generate a testable
hypothesis before rewriting. Read `references/experiment-design.md` and copy a
row into `assets/cro-hypothesis-ledger.csv` before launch.

Format:
```
For [eligible population], if we change [specific element] from [control] to
[treatment], we hypothesize [primary metric] will change because [mechanism].
Randomization unit: [visitor, account, session, or other justified unit].
Guardrails: [harm metrics]. Data quality: [SRM, exposure, event health].
MDE: [smallest business-useful effect, not expected uplift].
Decision rule: [pre-registered rule using estimate, uncertainty, guardrails,
and operational constraints].
```

Examples:

```
For eligible new visitors, if we change the hero CTA from "Learn more" to the
verified action-and-outcome label, we hypothesize qualified CTA starts will
change because the treatment reduces ambiguity.
Randomization unit: visitor ID. Guardrails: completion rate, error rate, and
support contacts. Data quality: allocation, SRM, exposure, and event parity.
MDE/sample/duration: calculate from the observed baseline, business threshold,
alpha, power, traffic, and the chosen analysis plan before launch.
```

After the Friction Audit, generate at most three hypotheses. Rank them by the
quality of the underlying evidence, size of the affected population, decision
value, effort, and risk. Do not rank by invented projected lift. A directional
result is inconclusive until assignment, exposure, SRM, metric health,
uncertainty, and guardrails have been checked.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall