Skip to content

Aetheria-Labs1/storefront-skills / skills/optimize

optimize

Flagged

Score an existing Lexsis page against the same page-type, design, proof, offer, asset and copy rules used to build pages, propose improvements as a strict optimization plan with real replacement copy and asset decisions, wait for approval, then apply the approved changes with version protection and hosted QA.

FileKindSize
SKILL.mdskill md13.6 KB
agents/openai.yamlconfig499 B
references/ab-testing.mdmarkdown6.3 KB
references/ad-to-page.mdmarkdown1.3 KB
references/animation-system.mdmarkdown11.1 KB
references/anti-patterns/copy-anti-patterns.mdmarkdown12.2 KB
references/anti-patterns/cro-anti-patterns.mdmarkdown17.8 KB
references/anti-patterns/dark-patterns.mdmarkdown23.9 KB
references/anti-patterns/design-anti-patterns.mdmarkdown9.3 KB
references/anti-patterns/mobile-anti-patterns.mdmarkdown9.7 KB
references/asset-prep.mdmarkdown6.9 KB
references/assets/asset-sourcing-sequence.mdmarkdown12.2 KB
references/assets/generation-policy.mdmarkdown25.9 KB
references/assets/image-jobs-by-page-type.mdmarkdown31.8 KB
references/assets/imagery-by-vertical.mdmarkdown24.8 KB
references/assets/slot-spec.mdmarkdown20.2 KB
references/assets/video-rules.mdmarkdown17.6 KB
references/authoring/css-and-styling.mdmarkdown4.0 KB
references/authoring/source-authoring.mdmarkdown9.0 KB
references/blob-shapes.mdmarkdown1018 B
references/cart-composition.mdmarkdown7.2 KB
references/cart-profile-management.mdmarkdown17.1 KB
references/consumer-behavior-cro.mdmarkdown12.7 KB
references/conversion-psychology.mdmarkdown403 B
references/copy/copy-frameworks.mdmarkdown20.5 KB
references/copy/headline-and-cta-rules.mdmarkdown12.9 KB
references/copy/message-match.mdmarkdown9.2 KB
references/copy/voice-of-customer-mining.mdmarkdown10.9 KB
references/design-assets.mdmarkdown366 B
references/design-enrichment.mdmarkdown334 B
references/design-rules.mdmarkdown15.5 KB
references/evidence-led-cro.mdmarkdown1.2 KB
references/generate-bundle-page.mdmarkdown303 B
references/generate-collection.mdmarkdown555 B
references/generate-editorial.mdmarkdown366 B
references/generate-homepage.mdmarkdown280 B
references/generate-landing-page.mdmarkdown335 B
references/generate-listicle.mdmarkdown295 B
references/generate-pdp.mdmarkdown312 B
references/generation-protocol.mdmarkdown3.2 KB
references/industry-cro.mdmarkdown433 B
references/island-patterns.mdmarkdown380 B
references/islands/collection-grid/index.mdmarkdown5.4 KB
references/islands/collection-swipe/index.mdmarkdown4.1 KB
references/lexsis-design-capabilities.mdmarkdown6.2 KB
references/lexsis-mcp-contract.mdmarkdown14.2 KB
references/merchant-templates.mdmarkdown2.6 KB
references/module-authoring.mdmarkdown9.0 KB
references/offers/aov-levers.mdmarkdown17.0 KB
references/offers/campaign-calendar.mdmarkdown21.4 KB
references/offers/funnel-stages.mdmarkdown17.6 KB
references/offers/offer-ledger.mdmarkdown5.1 KB
references/offers/offer-stacking.mdmarkdown3.5 KB
references/offers/offer-strategy.mdmarkdown9.6 KB
references/offers/offer-types.mdmarkdown36.6 KB
references/offers/price-presentation.mdmarkdown18.0 KB
references/offers/urgency-scarcity.mdmarkdown17.5 KB
references/page-editing.mdmarkdown9.7 KB
references/page-files.mdmarkdown2.7 KB
references/page-types/_checklist-format.mdmarkdown11.1 KB
references/page-types/_index.mdmarkdown21.9 KB
references/page-types/ad-landing-page.mdmarkdown29.0 KB
references/page-types/advertorial.mdmarkdown28.2 KB
references/page-types/brand-story-founder.mdmarkdown20.6 KB
references/page-types/bundle-kit.mdmarkdown27.4 KB
references/page-types/collection-landing.mdmarkdown21.9 KB
references/page-types/comparison-us-vs-them.mdmarkdown24.5 KB
references/page-types/faq-support-led.mdmarkdown20.4 KB
references/page-types/gift-guide.mdmarkdown22.0 KB
references/page-types/homepage.mdmarkdown23.6 KB
references/page-types/ingredient-science.mdmarkdown28.3 KB
references/page-types/launch-waitlist-preorder.mdmarkdown28.1 KB
references/page-types/lead-capture-giveaway.mdmarkdown22.6 KB
references/page-types/listicle.mdmarkdown27.2 KB
references/page-types/lookbook-shop-the-look.mdmarkdown19.6 KB
references/page-types/offer-page.mdmarkdown25.8 KB
references/page-types/pdp-hybrid-landing.mdmarkdown31.1 KB
references/page-types/pdp.mdmarkdown32.8 KB
references/page-types/quiz-funnel.mdmarkdown26.2 KB
references/page-types/referral-loyalty-vip.mdmarkdown18.4 KB
references/page-types/restock.mdmarkdown23.3 KB
references/page-types/retargeting-warm.mdmarkdown24.9 KB
references/page-types/sale-clearance-flash.mdmarkdown25.0 KB
references/page-types/seasonal-gifting.mdmarkdown26.9 KB
references/page-types/seo-buyers-guide.mdmarkdown23.9 KB
references/page-types/subscription.mdmarkdown26.5 KB
references/page-types/thank-you-post-purchase.mdmarkdown19.7 KB
references/page-types/trial-sample.mdmarkdown24.4 KB
references/page-types/ugc-creator-collab.mdmarkdown27.5 KB
references/page-types/video-sales-page.mdmarkdown25.1 KB
references/page-types/wholesale-b2b.mdmarkdown24.2 KB
references/plan-page.mdmarkdown9.7 KB
references/product-grid.mdmarkdown2.0 KB
references/proof/before-after-and-claims.mdmarkdown19.2 KB
references/proof/numbers-and-counts.mdmarkdown16.0 KB
references/proof/press-and-media-mentions.mdmarkdown12.5 KB
references/proof/proof-ledger.mdmarkdown8.3 KB
references/proof/reviews-sourcing.mdmarkdown24.8 KB
references/proof/trust-badges-certifications.mdmarkdown21.8 KB
references/proof/ugc-rights-and-display.mdmarkdown16.0 KB
references/publishing.mdmarkdown2.4 KB
references/qa-recipe.mdmarkdown4.3 KB
references/quiz-authoring.mdmarkdown14.5 KB
references/resource-templates.mdmarkdown7.7 KB
references/scroll-patterns.mdmarkdown1.2 KB
references/source-artifact-workflow.mdmarkdown3.7 KB
references/styling-hooks.mdmarkdown7.8 KB
references/traffic-source-google.mdmarkdown1.6 KB
references/traffic-source-meta.mdmarkdown1.5 KB
references/traffic-source-tiktok.mdmarkdown1.5 KB
references/vertical-beauty.mdmarkdown1.8 KB
references/vertical-fashion.mdmarkdown1.7 KB
references/vertical-food.mdmarkdown1.6 KB
references/vertical-home.mdmarkdown1.7 KB
references/vertical-luxury.mdmarkdown1.6 KB
references/vertical-supplements.mdmarkdown1.7 KB
references/workflow-intent.mdmarkdown2.0 KB
references/workflows/_how-to-read.mdmarkdown2.7 KB
references/workflows/copy-workflow.mdmarkdown1.5 KB
references/workflows/island-selection-workflow.mdmarkdown4.8 KB
references/workflows/section-asset-workflow.mdmarkdown5.8 KB

references/ab-testing.md

View on GitHub
# URL-First A/B Testing

Build a controlled Lexsis page experiment from an existing landing-page URL.
The URL may use the Lexsis storefront domain or a connected custom domain, but
the resolved page must belong to a workspace the user can edit.

## Inspect and Resolve the Control

Open the supplied URL with the browser capability available in the host:
Codex's browser, Claude Code with Playwright, or an equivalent browser tool.
Inspect desktop and mobile before proposing a test. Capture:

- headline, offer, CTA, media, proof, section order, and visual hierarchy;
- responsive behavior and obvious usability problems;
- interactive commerce behavior relevant to the proposed change;
- the current page title and URL path.

If no browser is available, accept current screenshots from the user and state
which behavior could not be verified. Do not claim a visual review from source
alone.

Extract likely handles or short ids from the path and resolve the owned page
with `lexsis_pages` action `find`. Confirm the match with `get`,
`edit_context`, and `source`. For a custom domain or root route that does not
map cleanly to one page, compare the observed title and content with the
candidate pages and ask the user only when more than one remains plausible.
Stop if the URL is not an editable Lexsis page; for external inspiration,
inspect the URL in the host browser.

## Define One Hypothesis

After inspection, present the strongest testable opportunities and ask what
the user wants to test. Supported scope includes:

- headline, supporting copy, offer, or CTA;
- CSS, typography, spacing, color, or layout;
- hero or other media;
- adding, removing, reordering, or replacing sections;
- mobile presentation;
- an island or commerce interaction supported by the current schema.

Confirm the primary hypothesis, primary metric (`cvr`, `aov`, or `rpv`),
protected elements, audience or segment, traffic weights, and stopping rule.
Default to the control plus one challenger with equal traffic. Add more
challengers only when the user explicitly asks and approves the additional
credit cost.

One experiment should isolate one decision. A design challenger may contain
coordinated CSS changes that express one visual hypothesis, but do not bundle
an unrelated headline, offer, section order, and design rewrite into the same
challenger.

For offer, positioning, or pricing tests, use
`references/offers/offer-strategy.md` and carry the relevant Page strategy
rationale into the hypothesis. Default price/offer economics tests to `rpv`;
review `cvr` and `aov` alongside it. Record merchant-supplied contribution
margin, refund, or retention guardrails when available, with their sources
and measurement windows. Do not invent native profit metrics or call higher
AOV a profit improvement when costs are unknown.

For an actual price change, record the confirmed commerce configuration that
honors each arm's price, eligibility, and recurring terms from page through
cart and checkout. If that support is unavailable, leave the test as a proposal;
do not duplicate, build, or activate price challengers that only change the
displayed price. A presentation-only test keeps payable terms unchanged.
Preserve existing rules against preselecting multipacks, paid add-ons, or
subscriptions, and retain the existing promotional tier-badge rules.

Write `ab-test-plan.md` with:

- observed control evidence;
- hypothesis and rationale;
- control and challenger definitions;
- exact intended differences and protected elements;
- metric, audience, weights, and stopping rule;
- required browser and commerce checks.

Return `AB_TEST_PLAN_READY` and obtain approval before paid page duplication.

## Create Source-First Challengers

Check credits and state the number of paid duplicates before creating them.
For each approved challenger:

1. Prepare an isolated source value from the current persisted control.
2. Apply only its planned change.
3. Compile the complete source and fix blocking compiler errors.
4. Call `lexsis_drafts` action `page_duplicate` with a stable idempotency key.
5. Apply the challenger change to the duplicate with `lexsis_build.patch` or
   `lexsis_build.commit` (only the changed files, `base_version` from
   `lexsis_build.get` on the duplicate).
6. Record the duplicate page id, blueprint id, version and
   compile evidence.
7. Run page integrity, affected commerce checks, and browser checks at mobile
   and desktop widths.

Do not use `page_variation` for this workflow: it creates a 50/50 experiment
before the challenger has been authored and verified.

When sub-agents are available, give one isolated source challenger to each
sub-agent. The parent owns the control, shared plan, compilation review,
credit confirmation, duplicate calls, remote writes, and experiment creation.
Sub-agents never spend credits or mutate remote pages. Without sub-agents,
build challengers sequentially using the same isolation.

Before experiment creation, compare control and challenger source and confirm
that every visible difference is covered by the approved plan. Return
`AB_VARIANTS_READY` with all preview URLs.

## Create the Draft Experiment

After variant approval, call `lexsis_drafts` action `experiment_create` using
the live schema. Supply:

- the original page id;
- original blueprint as the control;
- duplicate blueprint ids as challengers;
- approved labels and weights summing to 1;
- the supported primary metric and hypothesis fields.

Experiment creation is a reversible draft operation. Return
`AB_TEST_DRAFT_CREATED` with the experiment id and variant mapping.

Starting traffic is separate. Before publishing variants or starting the
experiment, require explicit approval that names the experiment and pages.
Resolve the current start action through exact discovery if it is exposed; if
the MCP has no start action, direct the user to activate the draft in Lexsis.
Never treat experiment creation as permission to publish pages or route live
traffic.

## Evaluate

For later evaluation, read `lexsis_analytics` action `experiment` and report:

- exposure and sample size per arm;
- primary and guardrail movement;
- statistical decision returned by Lexsis;
- device, targeting, or data-quality concerns;
- recommended next action: continue, pause, stop, or promote.

Do not call a winner from directional movement alone. `scale_winner` is a live
operation and requires explicit approval for the reported winning variant.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall