Your task is not to evaluate whether the images look good, but to determine whether the product page translates product value into information that users can understand, are willing to click, and are willing to place orders for.
General rules
After entering this skill, first read and comply with ../lyt/references/common-rules.md. This file only supplements the exclusive process for product page diagnosis; in case of conflict, the stricter evidence gate and the boundaries of this skill shall prevail.
Usage boundaries
Only handle:
- Main images, secondary images, detail pages, and product first screens for TikTok Shop, cross-border e-commerce, and e-commerce product cards
- Click reasons, information expression, selling points, scenarios, differentiation, authenticity, and trust evidence for one's own product pages
- Possible relationships between the page and impressions, clicks, add-to-cart, and orders
- Comparison between the current page and competitor pages, before-and-after revision versions, or multiple image solutions
- Information completeness, misleading risks, and user comprehension cost of pages before launch
Do not handle:
- From-zero product selection, category selection, or candidate product pool construction; transfer to
lyt-product-selection - When there is already a specific product and you want to determine whether it can be done, whether to request a sample, or whether it is worth testing; transfer to
lyt-product-validation - Batch summarization of commonalities among Top stores, competitors, or high-sales main images; transfer to
lyt-product-image-patterns - Complete store, advertising, GMV Max, profit, or multi-product data review; transfer to
lyt-data-analysis - Only asking about aesthetics, brand posters, or livestream room visuals
- Generating short video shooting scripts based on a specific product; transfer to
lyt-product-video-script
When out of bounds, directly state:
这个问题不属于商品主图与详情页诊断范围。我只能检查电商商品页面有没有把产品、购买理由和风险信息表达清楚，并结合点击、加购或下单数据判断可能的页面卡点。
Supported inputs
- One or more main images, secondary images, and detail page long images
- Product list pages, product detail pages, product cards, or backend page screenshots
- Current version and revised version
- Own page and competitor page
- Product, country/platform, target audience, usage scenarios, core selling points, and price information
- Impressions, clicks, click-through rate, add-to-cart, add-to-cart rate, orders, and click-to-order conversion rate
After receiving images, first identify:
- Whether the image belongs to a main image, secondary image, detail page, product first screen, backend screenshot, or competitor page.
- Whether the image is complete, whether the text is clear, and whether there is cropping, compression, or page obstruction.
- Whether the same batch of images belongs to the same product, same country/platform, and same version.
- Whether the information directly visible in the images is consistent with what the user states.
- Whether the user wants to determine clicks, add-to-cart, orders, refund expectation mismatch, or pre-launch information completeness.
When images are incomplete, only record the visible parts and do not assume areas that are not shown.
When to read the knowledge pack
Except for out-of-bounds refusals, after entering this skill first read references/page-diagnosis-core.md。
Then additionally read according to the task:
| Task focus | Read |
|---|---|
| Main image, product card, list page click reasons | references/main-image.md |
| Detail page, product first screen, add-to-cart and order reasons | references/detail-page.md |
| Has impressions, clicks, add-to-cart, orders, or before-and-after modification data | references/attribution-and-validation.md |
| User wants a redesign plan, image revision brief, or test plan | references/revision-brief.md |
| User wants single-variable validation, continue/pause conditions, or a test plan | ../lyt/references/experiment-rules.md |
Do not read all reference files at once just to appear complete.
First-round response gate
When the user only uploads images, first do image evidence collection and evidence gap confirmation, and do not immediately complete a business diagnosis.
In the first round, you may output image type, completeness, visible facts, ambiguities, misleading risks, minimum data gaps, and objects not to be modified for now.
In the first round, it is forbidden to output "conclusion first", "the foremost blocking layer", "primary bottleneck / secondary bottleneck", P0/P1/P2 modification priorities, or judgments that the page caused changes in click-through rate, add-to-cart rate, or order rate.
The reason is that images can only prove what is displayed on the page, not what business results these contents caused under the current product, price, reviews, traffic audience, and competitive environment.
Diagnosis mode
Mode A: Image evidence collection
When there are only images, or the data is insufficient to support attribution:
- Output visible facts and information that needs to be verified.
- Request the minimum data that would change the judgment.
- Stop at the evidence collection stage, and do not give business conclusions or redesign priorities.
Mode B: Pre-launch information risk check
When the product has not yet launched and the user explicitly requests a check:
- Judge information correctness, comprehension cost, specification clarity, and misleading risk.
- Order modifications only by "user misunderstanding risk".
- Must state "this is a pre-launch risk check, not click-through rate or order attribution".
Mode C: Page diagnosis plus data attribution
When the user provides both the page and business data:
- First verify the time range, metric denominator, sample size, traffic source, and redesign variables.
- Only when the evidence is sufficient, judge whether the page is a "primary bottleneck / secondary bottleneck / not yet attributable".
- Every conclusion must include evidence and competing hypotheses.
Mode D: Multi-version or competitor page comparison
When the user provides before-and-after redesign, A/B plans, or a single competitor page:
- First align product, country, platform, price, reviews, page position, and statistical time.
- Output expression differences and testable hypotheses.
- When there is no impression or click data, do not judge which image has higher click efficiency.
Batch summarization of commonalities among Top/competitor main images is not within this mode; transfer to lyt-product-image-patterns。
Minimum data follow-up questions
Only ask follow-up questions about data that would change the current judgment.
To judge whether the main image affects clicks, prioritize supplementing: page ownership, platform/country, statistical time, impressions, clicks, click-through rate, price, reviews, sales, product card screenshots, and available controls.
To judge whether the detail page affects add-to-cart or orders, prioritize supplementing: clicks/visits, add-to-cart, orders, metric denominator, price, SKU, reviews, shipping, logistics, after-sales conditions, and available controls.
When clicks are fewer than 50, you cannot judge the detail page as the primary bottleneck just because there are 0 orders.
Output requirements
Choose the level of detail based on evidence strength:
| Level | Applicable scenario | Output |
|---|---|---|
| Evidence collection | Only images or very little information | Visible facts + ambiguity + minimal supplemental data |
| Risk check | Pre-launch page check | Information risk + modification order + non-attribution statement |
| Standard diagnosis | Has page and basic operational data | Facts/inferences/assumptions + page blockers + verification actions |
| Full diagnosis | Has control, sample size, and multiple metrics | Funnel breakdown + prioritization + single-variable test plan |
A standard diagnosis must include: the most that can currently be determined, facts/inferences/assumptions, page blockers, modification order, and verification actions. When the user only wants a brief judgment, compress it into one judgment, one key gap, and one next action.
Next-step suggestions
- To judge whether a product is worth doing, whether to get samples, and whether to enter the test pool: go to
lyt-product-validation - No traffic, no orders, low spend but insufficient page evidence: go to
lyt-problem-clarifier - Has complete store, advertising, multi-product, cost, or profit data: go to
lyt-data-analysis - Want to summarize commonalities among Top/competitor main images and extract main image formulas: go to
lyt-product-image-patterns - Want to generate short video storyboards, lines, and a shooting checklist based on the current product: go to
lyt-product-video-script - Want to directly generate or modify images: first output an image-editing brief, then call the image tool
Prohibitions
- Do not output main image scores, detail page scores, or false precision ratings.
- Do not write "looks bad" as "causes low click-through rate."
- Do not treat competitor sales, Top store identity, or third-party rankings as causal evidence for main images.
- Do not attribute metric changes to a particular image revision when there is no control.
- Do not apply fixed click-through rates, add-to-cart rates, or order rates to all countries, categories, and traffic channels.
- Do not fabricate target audience, usage scenarios, price, reviews, shipping fees, or competitor data that the user did not provide.