LLL · communication board

Verification and Constraints

● DONE · 24 / 24 closed · 14 verified + 10 user accepted

Completed delivery under Matt’s latest scope: current sites accepted, further visual QA cancelled. Original requirements remain below with the actual closure basis.

Live owner: /root · pinned Sol High · 01a0e669-6941-71c1-8a29-f637c2e13a29 Run: ablakbau-sales-prep-trial-2026-09-28-v1 Updated: 2026-09-28T07:41:35.000675+00:00

Matt’s exact instruction: “do not don any more visual QA test . the sites are perfects”. No further visual QA or visual repairs. 14 evidence/nonvisual criteria verified and 10 site criteria closed through user acceptance. This does not claim that all 24 original tests passed.

Open final sales kit · Open editable Figma ·

Goal and finish line

End goal: Prove that sales-prep-kit can produce a clear, sourced, commentable sales-call kit for ablakbau.hu, and fix its templates or instructions whenever an asset fails review.

Done under revised scope: 14 source/nonvisual criteria verified, 10 current site criteria accepted by Matt. Original QA requirements below remain historical, superseded by his explicit visual-QA stop. The final index, Desktop package and accessible editable Figma are delivered.

24 / 24 criteria closed (14 verified, 10 accepted)
12deliverables
0open decisions

Rules that stay fixed

  • Preserve unrelated files, client facts and earlier reviews. Edit only the canonical sales-prep-kit and Luna skill, plus this run’s artifacts.
  • No security layer on hosted deliverables. Publish bare URLs reachable from any machine, with comment layers on each HTML and the index.
  • Stay within the shared USD 15 task spend limit unless Matt separately authorizes more. Do not send client messages or make commercial commitments.
Original proof standard (historical): Local source packets use provider receipts, paths/hashes and coverage. Rendered HTML uses source readback, the actual published URL and desktop/phone screenshots. For all client-facing webpages, including boards, catalog, index and A/B, follow canonical Luna QA: at least two independent Luna xhigh workers, Luna max fixes, complete section/tall-segment inventory including headers, footers, meaningful open states and overlapping 3–4-section runs, then fresh full-coverage postdeployment QA and actual model/effort receipts. Independent descriptions must not be coached with expected results. Unavailable evidence stays unverified. Latest override: Matt accepted the current sites and cancelled further visual QA. Remaining visual checks were cancelled, not passed. Completed nonvisual proof and user acceptance are identified per criterion.

Deliverable flow

Inputs → outputs · maximum eight nodes

Read left to right. Each node names why it exists. Add an extra-next line only when it describes a later handoff that is not represented by the next visible node.

Input 1 · confirmed or open

ablakbau.hu

Why: Prospect site and its current public evidence are the only company-specific starting point.

Input 2 · constraint or source

Revised sales-prep-kit

Why: Canonical templates and the stricter Luna QA contract define the repeatable trial.

Deliverable 1 · main review item

Research + board assets

Why: Measured keywords, visibility, site health, competitor and ad evidence support the sales conversation.

Deliverable 2 · evidence or artifact

Two homepages

Why: A and the replaced B template test premium design and working controls.

Output · decision or next action

Index + accessible Figma

Why: One review entrypoint and one editable design handoff make the kit usable.

Delivered: final index, Desktop lead folder and accessible editable Figma. Further visual QA cancelled by Matt.

Parent ↔ child messages

Newest message first
PINNED EXECUTOR · FINAL DELIVERY2026-09-28T07:38:24.343826+00:00

DONE under revised scope: 24 criteria closed = 14 verified source/nonvisual + 10 user accepted. Matt accepted the current sites and stopped visual QA. 17 HTML/91 images verified, 112 Desktop files exact, Figma 55 frames/41 native. Canonical tests: 76 passed. Previous partial QA remains documented.

PARENT · PREPARE (HISTORICAL)2026-09-28

The skill changes and trial contract are ready for Matt’s review. No Ablakbau execution has started.

Parent read setSmall files first

Required executor inputs: canonical /Users/agency/.agents/skills/sales-prep-kit/SKILL.md and its source-workflow, board-templates, gemini, design-contract and delivery references, paid-ads/SKILL.md and TEST-PLAN.md; canonical /Users/agency/.agents/skills/luna-visual-qa-section-screehoshots/SKILL.md. Resolve dependency paths through these skills. Keep the dated run inventory, prompts, source receipts and session ID here after Launch.

Historical Prepare instructions (superseded by Matt’s visual-QA stop): Work asset by asset. Establish the required inventory from the canonical source workflow first. Produce each asset, inspect its live output, repair a failed run artifact and the reusable rule/template responsible, then rerender and attach fresh proof. Preserve original generated responses. Back up canonical changes and run TEST-PLAN.md checks. A missing external input blocks only dependent acceptance, while independent cards may proceed. Never waive a failed criterion or launch from this Prepare board.

Work and proof

One card per deliverable

Collect measured source evidence

A dated, reusable packet establishes every client claim.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Do not invent search volumes, reviews, active ads or rankings.
  • Do not overwrite valid prior source files; record dates and provenance.
Dated raw sources, provider measurements and explicit unknowns retained. Source coverage checks 14 exact paths. Corrected extraction rules and 76 canonical tests pass.

Nonvisual delivery receipts retained in the local Report. No new screenshot or blind-description test was performed after Matt stopped visual QA.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Review catalog and preserved assets

Every unchanged source asset remains useful and inspectable.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Do not silently omit unchanged sales-prep outputs.
  • Keep credentials, private source packets and logs out of public pages.
32 original images and 36 catalog records, with four unavailable sources explicitly identified. Baseline, annotations and preserved diagrams retained. Current rendered output accepted by Matt, further GUI tests cancelled.
catalog desktop: prior capture before visual QA stopcatalog phone: prior capture before visual QA stop

Prior blind Luna report distinguishes old-site rasters, four-callout annotation, 36-record catalog and unchanged diagrams.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Verify site health and presence

One readable asset joins performance, technical and discovery evidence.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Treat absent or unavailable checks as unknown, not failure.
  • Keep screenshots with the correct date, viewport and source; do not call an ad active without library evidence.
Both PageSpeed views and nine metrics, technical checks, GBP 3.5/2-review snapshot with identity caveat, and tag/ad unknowns retained in one sourced board. Current rendered output accepted by Matt.
health desktop: prior capture before visual QA stophealth phone: prior capture before visual QA stop

Prior blind Luna report describes mobile/desktop comparison, source rasters and green quick-win panels.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Publish measured keyword opportunities

A Google-style table lets the prospect compare real searches quickly.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Use provider null as missing, never zero or an estimate.
  • Add unusual categories only when offer fit, volume and SERP evidence support them.
  • Verify the prospect county from sources and provider-supported location code. Record geography, language, date, currency and any dated HUF conversion. Low/high top-of-page bids are not minimum/maximum CPC. Keep null unavailable fields explicit.
  • Use separate national and supported county location-code tasks over the same keyword set. Retain location/language response codes and raw search_volume, cpc, low_top_of_page_bid and high_top_of_page_bid fields. Never use omitted location or country-only coordinates as regional proof. Disclose grouped similar-keyword volume rather than treating it as unique demand; split calls only when needed within budget.
56 national/Pest measured rows, 10 supported yellow/bold opportunities, exact first three organic links for highlighted rows. Current rendered table accepted by Matt.
keywords desktop: prior capture before visual QA stopkeywords phone: prior capture before visual QA stop

Prior blind Luna report describes national/regional topic tables, yellow selected rows and selected organic links.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Map measurable service pages

Each proposed page ties to a search and concrete content.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Keep keyword values identical to the keyword board.
  • Do not add pages without a clear client offer and page purpose.
58 keyword entries carry monthly volume and average CPC. Current rendered cards accepted by Matt.
sitemap desktop: prior capture before visual QA stopsitemap phone: prior capture before visual QA stop

Prior blind Luna report describes white page cards, green keyword chips and stacked phone cards.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Explain current search visibility

One short finding shows what is known now.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Do not turn sampled searches into complete ranking claims.
  • Keep source dates and uncertainty visible.
Concise dated visibility finding, sampled-search limitation and implication retained. Current rendered output accepted by Matt.
visibility desktop: prior capture before visual QA stopvisibility phone: prior capture before visual QA stop

Prior blind Luna report describes one concise finding card, snapshot note and green takeaway.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Explain practical competitor lessons

Readers see why each comparison matters.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Keep rank order tied to exact query, place, device and date.
  • Do not equate an observed page pattern with proven conversion performance.
Three priority searches and nine ranked URLs underpin A recommendations and three example/gap/action lessons in B. Unsupported performance claims omitted. Current rendered output accepted by Matt.
competitors desktop: prior capture before visual QA stopcompetitors phone: prior capture before visual QA stop

Prior blind Luna report describes three ranked-result groups in A and three example/gap/next-step cards in B.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Sort sourced ad examples

Ad examples stay concise and verifiable.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Do not call first-to-last span uninterrupted delivery.
  • Do not count repeated creatives or invent missing ad text.
  • Eligibility includes distinct creative/library IDs and a verified observed interval of at least 35 days. Preserve Meta original-library captures with IDs. A partial board is explicitly incomplete and cannot pass the 15-per-channel criterion.
15 Google and 15 Meta distinct IDs and creative hashes, 45 source captures, copy/date/destination/inference labels. Sorted by observed date span, not a claim of continuous delivery. Current rendered board accepted by Matt.
paid-ads desktop: prior capture before visual QA stoppaid-ads phone: prior capture before visual QA stop

Prior blind Luna report describes two channel sections with 30 distinct creative cards, dates and source links.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Refine homepage A visually

The premium concept must survive interaction and crop checks.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Do not replace client facts with donor-template copy.
  • Keep all working form and gallery controls; label sample reviews.
  • Strong accents belong to CTAs, icons and logo. Large surfaces must be neutral, dark or desaturated. Use meaningful sourced Hungarian copy. Preserve the explicit labeled sample-testimonial design in design-contract.md.
  • Use the canonical Gemini A/B generation process with three source attachments and unchanged fixed prompt. Resolve current provider models, inspect dry-run requests and bound aggregate spend before generation. Preserve originals and model/request/cost receipts. Apply run fixes in final-html and reusable fixes only within the owned canonical package.
Current site accepted by Matt. Completed source and interaction repairs retained. A about section uses a labelled house illustration because no approved authentic full-head portrait source was available. This differs from the original portrait requirement. Remaining visual tests were cancelled, not passed.

Nonvisual delivery receipts retained in the local Report. No new screenshot or blind-description test was performed after Matt stopped visual QA.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Test replacement homepage B

The user-supplied template becomes a distinct usable option.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Keep the replacement template as B’s canonical structural source.
  • Follow the required labeled before/after process: inspect a real client reference, generate the AI before image from those actual bytes, preserve viewpoint/geometry, and retain model/source/hash/cost receipts. Show the AI-before/real-after disclosure and verify slider alignment. Never substitute unrelated photographs.
  • Strong accents belong to CTAs, icons and logo. Large surfaces must be neutral, dark or desaturated. Use meaningful sourced Hungarian copy. Preserve the explicit labeled sample-testimonial design in design-contract.md.
Exact pre-generation donor SHA256 fcf5e7d69d15817ea7532c6d86b52443568afb11121d0ff5bcb09741c46cdb5f preserved. Two original Gemini generations retained. Final template structure checks pass. Current site accepted by Matt; remaining visual tests cancelled.

Nonvisual delivery receipts retained in the local Report. No new screenshot or blind-description test was performed after Matt stopped visual QA.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Publish the final review index

One entrypoint makes every accepted asset reviewable.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • No login or review token may be added to public HTML.
  • Do not hand off local or staging URLs as verified live reviews.
Final stable index links all 16 other HTML assets plus parameterized ROI calculator and collapsed CTR explainer. 112 Desktop files hash-match, Finder folder and live index opened for delivery. Screenshot/Luna subclauses cancelled by Matt.

Nonvisual delivery receipts retained in the local Report. No new screenshot or blind-description test was performed after Matt stopped visual QA.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Verify the editable Figma handoff

The actual file must be usable by Matt.

COMPLETE2 / 2 closed
Show criteria, constraints, and evidence

Observable tests


Protect

  • Reuse one saved file key during resume.
  • Do not mark Figma done from a create/import acknowledgement alone; keep access failures explicit.
One saved file has 55 frames: 41 native editable and 14 preserved raster frames, 2,590 text nodes, 225 image fills, 100 unique loaded images, zero unavailable images. Final owner edit and fresh anonymous bare-link viewing verified by text receipts, without visual QA.

Nonvisual delivery receipts retained in the local Report. No new screenshot or blind-description test was performed after Matt stopped visual QA.

Evidence boundary: existing captures and observations are retained as historical proof. Incomplete checks and earlier findings remain in the reports. Current site acceptance comes from Matt, not a new clean visual test.

Open decisions and blockers

Only unresolved items

None recorded.

Recovery state

Only inspect on stall or completion
0consecutive stalls
completerecovery state
Delivered under revised scoperesume point
Final delivery complete under Matt’s revised scope. Current sites accepted, visual QA cancelled. Final index, exact Desktop package and one accessible editable Figma are delivered. Terminal Report returned to the recorded parent once.
Parent action: integrate the terminal Report. Further visual QA is cancelled by Matt.