agentleFS
Sign inStart free
Aetheria-Labs1Aetheria-Labs1/storefront-skills/skills/audit/SKILL.md

audit

Skill8 starsChanged 3 months agoMITView on GitHub

Read-only conversion audit of a whole storefront page. Scores above-the-fold, offer strength, proof, copy, design, mobile and funnel data against the build rules and returns ranked fixes. Never edits; hand approved fixes to /optimize.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delight, teach-impeccable and 10 more.

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.
  • HK-hubSkill

    delight

    Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

    Also in 32 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • SkillPilotCHSkill

    level-up

    Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.

    Also in 12 projects that use this

  • ww-w-aiSkill

    pm-discovery

    PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.

    Also in 3 projects that use this

  • +7 more from HK-hub

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If work/storefront/setup.md exists, read it for rules and personas.

    line 38
  2. Very specific:

    Write the report to work/storefront/audits/<page-id>-v<version>.md.

    line 104

“Common” is measured: kept by at least 6 in 10 of the 175 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

Audit a Page

Produce an evidence-based CRO report for one live or draft page. This skill changes nothing: no page writes, no generation, no publishing.

References

ReferenceRead when
references/page-types/_index.md, then the type filealways
references/evidence-led-cro.md, references/consumer-behavior-cro.mdalways
references/design-rules.mdalways
references/offers/offer-strategy.md, references/offers/offer-stacking.md, references/offers/offer-ledger.mdalways
references/proof/proof-ledger.mdalways
references/copy/headline-and-cta-rules.md, references/anti-patterns/cro-anti-patterns.md, references/anti-patterns/mobile-anti-patterns.mdalways
the matching section of references/industry-cro.mdwhen the vertical is known

Gather

  1. Resolve the page: lexsis_pages.find, lexsis_pages.get, lexsis_pages.inspect, lexsis_pages.source.
  2. Read lexsis_analytics.page, lexsis_analytics.page_funnel, lexsis_analytics.page_attribution and lexsis_analytics.timeseries. If data is missing or thin, say so; do not invent findings from it. For product and collection templates, also read lexsis_analytics.resource_funnel, lexsis_analytics.resource_attribution, lexsis_analytics.resource_orders, lexsis_analytics.resource_views and lexsis_analytics.resource_vitals.
  3. Open the page in the host browser at 390 and 1280. Screenshot the first screen before any scroll.
  4. lexsis_assets.view on hero and offer images; lexsis_catalog.get and lexsis_catalog.reviews for claimed products and proof.
  5. If work/storefront/setup.md exists, read it for rules and personas. Its absence limits the report but does not stop it.

Score

Above the fold, at 390 and 1280

Pass or fail each, with the screenshot as evidence:

#Check
F1What it is and who it is for is clear within five seconds
F2The headline states the outcome and matches the ad or link that sent traffic
F3The hero image shows the product or its result
F4Price, or the offer, is visible on a PDP or offer page
F5The primary CTA is visible, high contrast, and states the action
F6Rating and review count sit near the title, when real reviews exist
F7One risk reducer is visible: returns, guarantee, or delivery date
F8Shipping cost or threshold is stated or one tap away
F9Nothing competes with the CTA: pop-ups, stacked bars, a second offer
F10Largest image is not lazy-loaded and appears quickly

Whole page

AreaRule source
Page type contract<type>.md checklist
Offervalue score and OS rules in offer-stacking.md, offer-ledger
Proofproof-ledger
Copyheadline and CTA rules
Designdesign-rules N1-N14, A1-A12
Mobilemobile-anti-patterns
CRO tellscro-anti-patterns
Funnelbiggest drop-off, device and source split

Give each area 0 to 100 and one overall score. Unverified claims and compliance problems are blocking, whatever the score.

Report

# Audit: <page> (version <n>, <date>)

## Summary
Overall: <score> | Blocking: <n> | Biggest opportunity: <one line>

## Above the fold
| Check | 390 | 1280 | Evidence |

## Scorecard
| Area | Score | Key finding | Rule |

## Offer
Value score, current stack, missing stack items, margin unknowns.

## Ranked fixes
| # | Fix | Evidence | Impact H/M/L | Effort H/M/L | Test or ship |

## Not assessed
<missing data>

Rank by evidence, impact, and effort. Do not promise a lift percentage. Mark ideas without page evidence as hypotheses, and send uncertain ones to /ab-test.

Write the report to work/storefront/audits/<page-id>-v<version>.md.

Return

Return the report path, overall score, blocking count, the top three fixes, and the state AUDIT_READY. To apply fixes, the user runs /optimize.

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.

Check your setup, free