agentleFS
Aetheria-Labs1Aetheria-Labs1/storefront-skills/skills/quiz/SKILL.md

quiz

Skill8 starsChanged 3 months agoMITView on GitHub

Create, update, validate, or preview a Lexsis Quiz island with real product recommendations, branching, variant matching, optional response saving, and consent-aware analytics.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use progress and learn.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • remenoscodesSkill

    progress

    Longitudinal language learning progress report with metrics, trends, and insights

    Also in 4 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the live Quiz island for the journey.

    line 8
  2. Distinctive:

    Remove questions that serve no recommendation or stated capture purpose.

    line 20
  3. Very specific:

    If saving is requested, inspect the immutable page-version UUID using lexsis_capture.quiz_inspect and prepare its inactive policy with …

    line 31
  4. Very specific:

    Test reachable branches/results, ties/fallbacks, required/optional inputs, back/review/restart, unavailable variants, Cart V2 outcomes, …

    line 34
  5. Very specific:

    When explicitly authorized, activate the reviewed policy with lexsis_live_ops.quiz_activate and publish the reviewed page through /publish.

    line 40
  6. Very specific:

    After publication, verify saving allowed/declined and analytics allowed/denied, edit/reload/retry, one completed Forms response, and …

    line 44
  7. Distinctive:

    Use the returned published URL.

    line 46
  8. Distinctive:

    Only use registered islands and host capabilities present in the live schema.

    line 58
  9. Distinctive:

    If supported hooks cannot express the design, identify the reusable host change needed.

    line 59
  10. Distinctive:

    Do not promise automatic result email, marketing sync, a dedicated quiz funnel dashboard, paid-order attribution, preview capture, or …

    line 61

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create a Quiz

Use the live Quiz island for the journey. Read references/quiz-authoring.md and the current vibe://schema/island/Quiz before authoring. Resolve unfamiliar MCP arguments through lexsis_discover.

Workflow

  1. Resolve the exact workspace, store, page, and theme. Load brand context and inspect available desktop/mobile references. Keep the same theme throughout.
  2. Refresh real candidate products and variants with lexsis_catalog; never invent Shopify IDs, prices, availability, option values, or result imagery.
  3. Plan stable keys, questions, branches, scoring, deterministic fallback, result explanations, product/variant mapping, and entry and exit actions. Remove questions that serve no recommendation or stated capture purpose.
  4. Decide whether responses should be saved. For saving, define the purpose, disclosure, question classifications, merchant visibility, retention, resume window, and optional contact purpose. Saving and analytics are independent; collecting contact details does not subscribe the visitor to marketing.
  5. Author one complete Quiz definition in normal page source. Use scoped CSS, supported hooks, and managed motion for transitions. Preserve focus and reduced-motion behavior; do not invent runtime presets or custom state machines.
  6. Compile, repair blockers, then create or update the requested unpublished draft with version protection. Keep source and QA in MCP; do not save local JSON dumps, screenshot reports, or ad hoc page artifacts.
  7. If saving is requested, inspect the immutable page-version UUID using lexsis_capture.quiz_inspect and prepare its inactive policy with lexsis_drafts.quiz_prepare. Reinspect after any source edit.
  8. Test reachable branches/results, ties/fallbacks, required/optional inputs, back/review/restart, unavailable variants, Cart V2 outcomes, focus, transitions, and reduced motion at 390, 768, and 1280. Record supported hosted QA via MCP.
  9. Return DRAFT_CREATED while QA or approval is pending. Record DESIGN_APPROVED only after hosted QA and explicit approval of that same version. This is a valid handoff to /publish.
  10. When explicitly authorized, activate the reviewed policy with lexsis_live_ops.quiz_activate and publish the reviewed page through /publish. These are separate decisions; reuse approval already given for the exact scope. Preview does not prove production capture.
  11. After publication, verify saving allowed/declined and analytics allowed/denied, edit/reload/retry, one completed Forms response, and redacted MCP reads. Use the returned published URL. Report any untested path or live limitation.

Boundaries

  • Definitions live in page source. Saved responses use the managed capture policy and Forms response viewer; do not edit generic Forms schemas to bypass it.
  • Personal and sensitive answers are protected; MCP exposes only permitted categorical values. analytics.answerAllowlist does not allow raw analytics.
  • Result commerce uses Quiz add_items. Do not add hidden BuyBoxes, direct Shopify requests, authored cart shells, or programmatic clicks.
  • reward and offer actions are unavailable. Verify existing cart promotions separately before claiming a discount or gift.
  • Only use registered islands and host capabilities present in the live schema. If supported hooks cannot express the design, identify the reusable host change needed; do not fabricate an island or inject arbitrary JavaScript.
  • Do not promise automatic result email, marketing sync, a dedicated quiz funnel dashboard, paid-order attribution, preview capture, or historical-version resume.

Return

Report page/version and hosted URL; product sources and tested paths; responsive, cart, and motion QA; saving policy state; activation/publication state; and live capture/analytics evidence or pending checks. Keep design approval, policy activation, publication, confirmed saving, and purchase as separate outcomes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.