[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73VC3HWA7V1N50DVDKWEH2D":3,"skill-same:01M73VC3HWA7V1N50DVDKWEH2D":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M73VC3HWA7V1N50DVDKWEH2D","generating-product-photos",null,"ALWAYS read this skill before generating a product photography — before writing any prompt or calling image_generate. Turns a product photo or URL into commercial photography - packshots, lifestyle and campaign frames, on-model, macro detail, flat lays, seasonal staging, infographics, concepts and floating shots. Reads the real product first and holds it identical across every frame. Triggers: \"product photo\", \"packshot\", \"shoot my product\", \"studio shot\", \"lifestyle shot\", \"hero image\", \"on a model\", \"flat lay\", \"product infographic\", \"floating product\", \"product ad\".","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fgenerating-product-photos__skills-supercmohq-generating-product-photos\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: generating-product-photos\ndescription: |\n  ALWAYS read this skill before generating a product photography — before writing any prompt or calling image_generate. Turns a product photo or URL into commercial photography - packshots, lifestyle and campaign frames, on-model, macro detail, flat lays, seasonal staging, infographics, concepts and floating shots. Reads the real product first and holds it identical across every frame. Triggers: \"product photo\", \"packshot\", \"shoot my product\", \"studio shot\", \"lifestyle shot\", \"hero image\", \"on a model\", \"flat lay\", \"product infographic\", \"floating product\", \"product ad\".\nlicense: Apache-2.0\nmetadata:\n  version: \"0.2.0\"\n  category: creative\n  summary: \"Directs a commercial photoshoot around your product, automatically applying the correct lighting, framing, camera angles and props to deliver studio-quality product shots across 10+ formats.\"\n---\n\n# Product Photography\n\nTurn a product into commercial imagery via the `image_generate` tool.\nMarketplace listing galleries are out of scope. Anything whose subject isn't a product should not be created with this skill.\n\n## Workflow\n\n### Step 1: Read what you have\n\n- **A product image or URL is available** → hand it to `analyzing-products`, and take four things\n  back: what the product is; **how a person physically uses it** — sprayed, pumped,\n  worn, etc.; which parts open or move, and in what order; and the details that have to stay identical wherever it appears. \n- **Look at the image before you describe it.** Take the product only from what the image shows —\n  not the brief, not the filename, not the product name. Run `image_analysis` and ask it for\n  everything this shoot needs that the product facts leave out — how the surfaces take light, and\n  whatever else the frame you end up building will have to describe.\n- **Product not supplied** → don't guess at the product. It becomes the first thing Step 2 asks for.\n\n### Step 2: Interview\n\n**Skip this entirely when the brief already makes the shot obvious** — a clear subject, a clear use,\nand nothing load-bearing missing. The interview exists to close real gaps, not to confirm what you\nwere already told.\n\nOtherwise ask once, bundled into a single message, **at most four questions**. Always leave a free-text way out so the user can answer off-menu. Anything this skill already settles is not a question.\n\n**Do ask, when the answer is genuinely missing:**\n\n| Ask | When |\n| --- | --- |\n| **The product** — what it is, and whatever else identifies it: packaging, colour, distinguishing features | No image and no URL. Offer to wait for an upload first; a photographed product beats a described one. |\n| **Brand guidelines, if they have any** — the color palette, the art direction they shoot to, anything they never put in frame, the typeface where text is drawn, and the register they want the frame to read at | The brief mentions none and the packaging doesn't imply them. Treat as optional: plenty of brands have none, so take what they give and move on. |\n| **Who the buyer is** | The frame has to speak to a particular buyer — like which features an infographic calls out, whose home a lifestyle scene is set in, who gets cast on-model, etc. |\n| **How many frames**, and where they run | The brief doesn't say, and the destination changes the crop. |\n\n**When the user waives questions** and the product is already in hand, go straight to generating.\nTake **studio**, since that is where an unrouted request lands anyway; take the tool's default ratio. Say in a sentence which settings you took, then keep going. It is a statement, not a checkpoint.\n\nA missing product image is the one thing still worth raising.\n\n### Step 3: Select the mode and read the corresponding reference file\n\n| The ask is about… | Mode | Reference |\n| --- | --- | --- |\n| The product on its own against a clean, controlled background | **studio** | `references\u002Fmode-studio.md` |\n| The product somewhere real, being used or lived with | **lifestyle** | `references\u002Fmode-lifestyle.md` |\n| One polished frame leading a campaign — the product made to look desirable | **hero** | `references\u002Fmode-hero.md` |\n| Worn, held, or applied to skin | **on-model** | `references\u002Fmode-on-model.md` |\n| Texture, material, craft, a tight crop on the thing itself | **close-up** | `references\u002Fmode-close-up.md` |\n| Arranged on a surface, shot from directly above | **flat-lay** | `references\u002Fmode-flat-lay.md` |\n| Tied to a holiday, season or buying moment | **seasonal** | `references\u002Fmode-seasonal.md` |\n| Feature labels, callouts, specs or ad copy drawn onto the image — including an ad, a before-and-after or a comparison | **infographic** | `references\u002Fmode-infographic.md` |\n| Breaking the pattern to stop a scroll — unexpected, impossible, or unlike how this product is normally shown | **creative** | `references\u002Fmode-creative.md` |\n| Suspended mid-air, defying gravity | **floating** | `references\u002Fmode-floating.md` |\n\nRoute on what the image is *for*, not on a matched word.\n\n**Where two rows both fit, these win:**\n\n- **A person in frame** → **on-model**, whatever the setting or the crop would otherwise say.\n- **Text drawn onto the image** → **infographic**, whatever else is in frame.\n- **One plane, shot from overhead** → **flat-lay**\n- **One property at close range** → **close-up**, even inside a setting.\n- **The occasion is the sell** → **seasonal**\n- **The brief asks for something unexpected, surprising or scroll-stopping** → **creative**, even when\n  it also names a placement.\n\n### Step 4: Write the product description\n\nYou read the mode guide in Step 3, so you know what this shot has to show. Write one description of\nthe product, and reuse it unchanged in every prompt you send.\n\n**How much to write depends on whether a photo is going with the call.** With a reference attached,\nthe photo carries identity and the description covers only what it cannot: the angle you want, the\nstate the moving parts are in, the action being performed. With no reference, the description is all\nthe model has, so it carries the product in full from the list below.\n\n- **Form** — shape, proportion, how it sits or stands, or whatever else pins the silhouette down.\n- **Closure and moving parts** — a cap, a hinge, a zip, whatever this product has, and whether the\n  shot wants it open or shut.\n- **Materials and finish, surface by surface** — matte or gloss, brushed, woven, translucent or\n  something else.\n- **The action, wherever the frame has one** — the specific thing being done to the product, taken\n  from the mechanic Step 1 established rather than invented to suit the composition. Write it as the\n  physical movement it is, and say what the product is doing at that instant: what has left it, what\n  is about to, which part has moved, etc.\n\nThe mode guide decides how much of this the prompt carries — the whole product for some, a single\nproperty for a close crop, one description per item where several share the frame.\n\n**Don't transcribe what the label says.** Spelling out the printing invites the model to redraw it,\nand redrawn text comes back warped.\n\n### Step 5: Select the model\n\n| Model | Use it when | How it wants the prompt written |\n| --- | --- | --- |\n| `nano-banana-pro` | everything, by default | connected sentences in one narrative paragraph, never a string of keywords |\n| `gpt-image-2` | words or graphics are drawn onto the image, or the layout is a designed one. Not for the product's own printed label — that comes from the reference | short labelled segments on separate lines, not a paragraph |\n| `seedream-5` | another model refused, or keeps failing | a description rather than keywords, leading with whatever matters most |\n\nIf the user has explicitly named a model, then use that first.\n\n### Step 6: Write the prompt\n\n- Follow the mode guide from Step 3 to write the prompts, carrying the product description from\n  Step 4 into each one. \n- Read `references\u002Fphotographic-craft.md` before writing. It carries the language for light, shadow,\n  colour, material and optics; the style anchor to pick before the first sentence; and the two fixed\n  blocks that close every prompt.\n- **Every prompt is assembled in this order:** the mode's fixed preservation block, then the scene\n  you write from the mode's fields, then the quality-marker line, then the Avoid block — the last\n  two exactly as `references\u002Fphotographic-craft.md` gives them.\n- **Every prompt sent with a reference photo states the fidelity requirement.** The attached photo\n  does not enforce itself: say outright that the product in frame is the one in the reference and\n  reaches the image unchanged. Anything the photo already settles and does not need to change must not be written\n  out again: a detail spelled out reads as an instruction to draw it, and what gets drawn drifts from\n  the photo. Those words go to what the reference cannot show — the setting, the light, the framing, etc.\n- **Where a call carries more than one reference image, label them.** Refer to them as Image 1, Image 2\nand so on, in the order they are passed. Say what each one is, then use those numbers in the\ninstruction rather than describing the pictures again. Left unlabelled, the model picks its own\nsubject from the set.\n- **Scene-specific exclusions go inline**, phrased as the thing you want instead — there is no\n  negative-prompt parameter. The closing Avoid block is the one exception, and it is fixed: do not\n  add this frame's own exclusions to it.\n- **Don't reserve empty space for text nobody asked for.** A region requested as emptiness comes back\n  as an untextured block.\n- **A name is not a description.** Borrowing someone's name — whoever or whatever it belongs to —\n  buys a vague imitation at best, and some models simply decline the request. Say what you were\n  reaching for instead: the geometry, the palette, how the light behaves. A rival's name has no place\n  in the frame at all, not even as the thing you are steering away from. The only brand name that\n  belongs in a prompt is one for the product you are photographing.\n- **No internal name goes in the prompt** — not a mode, not a file.\n\n### Step 7: Generate\n\nCall `image_generate` with a `requests` list (one object per image):\n\n- Per object: `prompt`; `model`; `aspect_ratio`; `resolution`; `reference_images`.\n- **The product photo goes in `reference_images` every time.** It holds identity; the prompt alone\n  will not.\n- **Take the ratio from the user.** If they haven't named one, derive it from where the image runs —\n  the destination decides the crop, not the mode. If neither is known, ask in Step 2 or take the\n  tool's default and say which you took.\n- **One image per request.** Generate a single frame unless the brief asked for more than one.\n  Never generate a second to compare models, to try a different look, or to correct an output you\n  judged poor — every one of those bills again. Where the brief does ask for several, send them as\n  several request objects in the one call.\n- **Don't run a vision or analysis call on the image you just generated.** Judging your own output\n  is not part of this workflow: it costs another call, and anything it finds you are not permitted to\n  act on. Hand the result to the user and let them decide.\n- **An unanswered question is not a yes.** If you ask whether to regenerate and no answer comes back,\n  the answer is no — deliver what you have and say what you would have changed. A run with nobody\n  watching cannot consent to being billed twice.\n- Call `list_image_models` for accepted `aspect_ratio` values, `resolution` tiers and per-model\n  `reference_images` limits rather than guessing — a wrong enum fails a billed call.\n\nImages are polled for you, but a heavy one can come back as `{status: \"pending\", …}`. That is a job handle, not a failure. Pass that exact handle to `job_status` to retrieve the finished image, and if it comes back pending again, call `job_status` again with the same handle. **Never re-run a pending image** through `image_generate`: that abandons the job you are already paying for and starts a second, separately billed one.\n\n### Step 8: Return\n\n- Share the image URLs and local file paths, once every frame has finished — never a partial set.\n- For a set, present them in the order you outlined.\n\n## Producing a set of images\n\nRequests generate independently, so build the continuity in:\n\n1. **Draft the frame list and get it agreed before generating anything.** Every frame is billed\n   separately, so misreading the brief means paying to generate the entire set a second time.\n2. **Fix one look and write it into every prompt unchanged** — the palette, the surface, the light,\n   the camera height and angle, whatever else the look is made of. Rephrasing it between frames reads\n   as a new instruction.\n3. **Send the same reference image and the same model on every frame.** Those two carry the product\n   and hold the set together; wording alone will not.\n4. **Vary only what each frame shows.** A frame that needs a different setting is a second set, not a\n   member of this one.\n5. **Make them genuinely different** — near-duplicates test nothing. Give each frame its own argument\n   first and let that pick the staging; frames differing only in camera angle ask the same question\n   twice.\n6. **Where the set is a sequence rather than a spread**, decide the order first and write each frame\n   to its position: what has to stop someone, what carries the middle, what the last frame leaves\n   them holding. A sequence assembled from interchangeable frames reads as a spread that lost its\n   order.\n\n## Common mistakes\n\n- Writing a freeform prompt instead of what the mode says it must carry.\n- Skipping the interview when something load-bearing is missing.\n- Showing an interaction the product doesn't support, when Step 1 already established what it does.\n- Naming a brand, a photographer or a publication in the prompt in place of describing the look.\n- Re-running a rejected frame without first finding out what was wrong with it.\n\n## Edge cases\n\n- **The image came back not as intended** — wrong angle, warped label, a look you didn't ask for →\n  deliver it anyway and say what you think is off. Do not regenerate on your own judgement: a second\n  generation bills again, and the user may be happy with the first.\n- **A rejection that names no reason** → ask what missed before re-running, with options drawn from\n  the mode you just shot, plus free text. A blind re-run bills again and lands elsewhere at random.\n- **Safety or policy rejection** → name a workable stand-in and resubmit; on a second, try\n  `seedream-5`; on a third, say which element is blocked rather than retrying blind.\n- **Generic failure** → read the error. If it names a parameter or limit, fix that and resubmit;\n  otherwise resubmit once, then hand the user the error text.\n- **`reference_images` rejected on count** → the error states the limit; drop to it.\n- **`error: \"no_provider_configured\"`** → relay the tool's `hint` (the user must set their key).\n\n## Reference\n\n**Mode guides** — read the one you routed to; each ends with a checklist to read your prompt against:\n\n- `references\u002Fmode-studio.md` — the background and its brightness, true colour, sharpness, shadow.\n- `references\u002Fmode-lifestyle.md` — place, hour, motivated light, and what keeps the product the subject.\n- `references\u002Fmode-hero.md` — the open side for copy, the graded key, surviving every delivery crop.\n- `references\u002Fmode-on-model.md` — casting, styling condition, hands, where the crop cuts the body.\n- `references\u002Fmode-close-up.md` — the one property, raking light, apparent source size, the scale cue.\n- `references\u002Fmode-flat-lay.md` — camera plane, arrangement register, the open surface.\n- `references\u002Fmode-seasonal.md` — the single carrier, whose palette it is, props that read as included.\n- `references\u002Fmode-infographic.md` — callout copy, anchors, leader lines, the exposing angle.\n- `references\u002Fmode-creative.md` — the concept, the one departure, coloured sources, what is held dark.\n- `references\u002Fmode-floating.md` — the underside, the displaced shadow, the gap that reads as height.\n\n**Shared craft** — read on every job:\n\n- `references\u002Fphotographic-craft.md` — the two fixed blocks that close every prompt; the style\n  anchor; light, shadow, colour, material, optics and on-image text; what changes for paid media.\n","# Product Photography\n\nTurn a product into commercial imagery via the `image_generate` tool.\nMarketplace listing galleries are out of scope. Anything whose subject isn't a product should not be created with this skill.\n\n## Workflow\n\n### Step 1: Read what you have\n\n- **A product image or URL is available** → hand it to `analyzing-products`, and take four things\n  back: what the product is; **how a person physically uses it** — sprayed, pumped,\n  worn, etc.; which parts open or move, and in what order; and the details that have to stay identical wherever it appears. \n- **Look at the image before you describe it.** Take the product only from what the image shows —\n  not the brief, not the filename, not the product name. Run `image_analysis` and ask it for\n  everything this shoot needs that the product facts leave out — how the surfaces take light, and\n  whatever else the frame you end up building will have to describe.\n- **Product not supplied** → don't guess at the product. It becomes the first thing Step 2 asks for.\n\n### Step 2: Interview\n\n**Skip this entirely when the brief already makes the shot obvious** — a clear subject, a clear use,\nand nothing load-bearing missing. The interview exists to close real gaps, not to confirm what you\nwere already told.\n\nOtherwise ask once, bundled into a single message, **at most four questions**. Always leave a free-text way out so the user can answer off-menu. Anything this skill already settles is not a question.\n\n**Do ask, when the answer is genuinely missing:**\n\n| Ask | When |\n| --- | --- |\n| **The product** — what it is, and whatever else identifies it: packaging, colour, distinguishing features | No image and no URL. Offer to wait for an upload first; a photographed product beats a described one. |\n| **Brand guidelines, if they have any** — the color palette, the art direction they shoot to, anything they never put in frame, the typeface where text is drawn, and the register they want the frame to read at | The brief mentions none and the packaging doesn't imply them. Treat as optional: plenty of brands have none, so take what they give and move on. |\n| **Who the buyer is** | The frame has to speak to a particular buyer — like which features an infographic calls out, whose home a lifestyle scene is set in, who gets cast on-model, etc. |\n| **How many frames**, and where they run | The brief doesn't say, and the destination changes the crop. |\n\n**When the user waives questions** and the product is already in hand, go straight to generating.\nTake **studio**, since that is where an unrouted request lands anyway; take the tool's default ratio. Say in a sentence which settings you took, then keep going. It is a statement, not a checkpoint.\n\nA missing product image is the one thing still worth raising.\n\n### Step 3: Select the mode and read the corresponding reference file\n\n| The ask is about… | Mode | Reference |\n| --- | --- | --- |\n| The product on its own against a clean, controlled background | **studio** | `references\u002Fmode-studio.md` |\n| The product somewhere real, being used or lived with | **lifestyle** | `references\u002Fmode-lifestyle.md` |\n| One polished frame leading a campaign — the product made to look desirable | **hero** | `references\u002Fmode-hero.md` |\n| Worn, held, or applied to skin | **on-model** | `references\u002Fmode-on-model.md` |\n| Texture, material, craft, a tight crop on the thing itself | **close-up** | `references\u002Fmode-close-up.md` |\n| Arranged on a surface, shot from directly above | **flat-lay** | `references\u002Fmode-flat-lay.md` |\n| Tied to a holiday, season or buying moment | **seasonal** | `references\u002Fmode-seasonal.md` |\n| Feature labels, callouts, specs or ad copy drawn onto the image — including an ad, a before-and-after or a comparison | **infographic** | `references\u002Fmode-infographic.md` |\n| Breaking the pattern to stop a scroll — unexpected, impossible, or unlike how this product is normally shown | **creative** | `references\u002Fmode-creative.md` |\n| Suspended mid-air, defying gravity | **floating** | `references\u002Fmode-floating.md` |\n\nRoute on what the image is *for*, not on a matched word.\n\n**Where two rows both fit, these win:**\n\n- **A person in frame** → **on-model**, whatever the setting or the crop would otherwise say.\n- **Text drawn onto the image** → **infographic**, whatever else is in frame.\n- **One plane, shot from overhead** → **flat-lay**\n- **One property at close range** → **close-up**, even inside a setting.\n- **The occasion is the sell** → **seasonal**\n- **The brief asks for something unexpected, surprising or scroll-stopping** → **creative**, even when\n  it also names a placement.\n\n### Step 4: Write the product description\n\nYou read the mode guide in Step 3, so you know what this shot has to show. Write one description of\nthe product, and reuse it unchanged in every prompt you send.\n\n**How much to write depends on whether a photo is going with the call.** With a reference attached,\nthe photo carries identity and the description covers only what it cannot: the angle you want, the\nstate the moving parts are in, the action being performed. With no reference, the description is all\nthe model has, so it carries the product in full from the list below.\n\n- **Form** — shape, proportion, how it sits or stands, or whatever else pins the silhouette down.\n- **Closure and moving parts** — a cap, a hinge, a zip, whatever this product has, and whether the\n  shot wants it open or shut.\n- **Materials and finish, surface by surface** — matte or gloss, brushed, woven, translucent or\n  something else.\n- **The action, wherever the frame has one** — the specific thing being done to the product, taken\n  from the mechanic Step 1 established rather than invented to suit the composition. Write it as the\n  physical movement it is, and say what the product is doing at that instant: what has left it, what\n  is about to, which part has moved, etc.\n\nThe mode guide decides how much of this the prompt carries — the whole product for some, a single\nproperty for a close crop, one description per item where several share the frame.\n\n**Don't transcribe what the label says.** Spelling out the printing invites the model to redraw it,\nand redrawn text comes back warped.\n\n### Step 5: Select the model\n\n| Model | Use it when | How it wants the prompt written |\n| --- | --- | --- |\n| `nano-banana-pro` | everything, by default | connected sentences in one narrative paragraph, never a string of keywords |\n| `gpt-image-2` | words or graphics are drawn onto the image, or the layout is a designed one. Not for the product's own printed label — that comes from the reference | short labelled segments on separate lines, not a paragraph |\n| `seedream-5` | another model refused, or keeps failing | a description rather than keywords, leading with whatever matters most |\n\nIf the user has explicitly named a model, then use that first.\n\n### Step 6: Write the prompt\n\n- Follow the mode guide from Step 3 to write the prompts, carrying the product description from\n  Step 4 into each one. \n- Read `references\u002Fphotographic-craft.md` before writing. It carries the language for light, shadow,\n  colour, material and optics; the style anchor to pick before the first sentence; and the two fixed\n  blocks that close every prompt.\n- **Every prompt is assembled in this order:** the mode's fixed preservation block, then the scene\n  you write from the mode's fields, then the quality-marker line, then the Avoid block — the last\n  two exactly as `references\u002Fphotographic-craft.md` gives them.\n- **Every prompt sent with a reference photo states the fidelity requirement.** The attached photo\n  does not enforce itself: say outright that the product in frame is the one in the reference and\n  reaches the image unchanged. Anything the photo already settles and does not need to change must not be written\n  out again: a detail spelled out reads as an instruction to draw it, and what gets drawn drifts from\n  the photo. Those words go to what the reference cannot show — the setting, the light, the framing, etc.\n- **Where a call carries more than one reference image, label them.** Refer to them as Image 1, Image 2\nand so on, in the order they are passed. Say what each one is, then use those numbers in the\ninstruction rather than describing the pictures again. Left unlabelled, the model picks its own\nsubject from the set.\n- **Scene-specific exclusions go inline**, phrased as the thing you want instead — there is no\n  negative-prompt parameter. The closing Avoid block is the one exception, and it is fixed: do not\n  add this frame's own exclusions to it.\n- **Don't reserve empty space for text nobody asked for.** A region requested as emptiness comes back\n  as an untextured block.\n- **A name is not a description.** Borrowing someone's name — whoever or whatever it belongs to —\n  buys a vague imitation at best, and some models simply decline the request. Say what you were\n  reaching for instead: the geometry, the palette, how the light behaves. A rival's name has no place\n  in the frame at all, not even as the thing you are steering away from. The only brand name that\n  belongs in a prompt is one for the product you are photographing.\n- **No internal name goes in the prompt** — not a mode, not a file.\n\n### Step 7: Generate\n\nCall `image_generate` with a `requests` list (one object per image):\n\n- Per object: `prompt`; `model`; `aspect_ratio`; `resolution`; `reference_images`.\n- **The product photo goes in `reference_images` every time.** It holds identity; the prompt alone\n  will not.\n- **Take the ratio from the user.** If they haven't named one, derive it from where the image runs —\n  the destination decides the crop, not the mode. If neither is known, ask in Step 2 or take the\n  tool's default and say which you took.\n- **One image per request.** Generate a single frame unless the brief asked for more than one.\n  Never generate a second to compare models, to try a different look, or to correct an output you\n  judged poor — every one of those bills again. Where the brief does ask for several, send them as\n  several request objects in the one call.\n- **Don't run a vision or analysis call on the image you just generated.** Judging your own output\n  is not part of this workflow: it costs another call, and anything it finds you are not permitted to\n  act on. Hand the result to the user and let them decide.\n- **An unanswered question is not a yes.** If you ask whether to regenerate and no answer comes back,\n  the answer is no — deliver what you have and say what you would have changed. A run with nobody\n  watching cannot consent to being billed twice.\n- Call `list_image_models` for accepted `aspect_ratio` values, `resolution` tiers and per-model\n  `reference_images` limits rather than guessing — a wrong enum fails a billed call.\n\nImages are polled for you, but a heavy one can come back as `{status: \"pending\", …}`. That is a job handle, not a failure. Pass that exact handle to `job_status` to retrieve the finished image, and if it comes back pending again, call `job_status` again with the same handle. **Never re-run a pending image** through `image_generate`: that abandons the job you are already paying for and starts a second, separately billed one.\n\n### Step 8: Return\n\n- Share the image URLs and local file paths, once every frame has finished — never a partial set.\n- For a set, present them in the order you outlined.\n\n## Producing a set of images\n\nRequests generate independently, so build the continuity in:\n\n1. **Draft the frame list and get it agreed before generating anything.** Every frame is billed\n   separately, so misreading the brief means paying to generate the entire set a second time.\n2. **Fix one look and write it into every prompt unchanged** — the palette, the surface, the light,\n   the camera height and angle, whatever else the look is made of. Rephrasing it between frames reads\n   as a new instruction.\n3. **Send the same reference image and the same model on every frame.** Those two carry the product\n   and hold the set together; wording alone will not.\n4. **Vary only what each frame shows.** A frame that needs a different setting is a second set, not a\n   member of this one.\n5. **Make them genuinely different** — near-duplicates test nothing. Give each frame its own argument\n   first and let that pick the staging; frames differing only in camera angle ask the same question\n   twice.\n6. **Where the set is a sequence rather than a spread**, decide the order first and write each frame\n   to its position: what has to stop someone, what carries the middle, what the last frame leaves\n   them holding. A sequence assembled from interchangeable frames reads as a spread that lost its\n   order.\n\n## Common mistakes\n\n- Writing a freeform prompt instead of what the mode says it must carry.\n- Skipping the interview when something load-bearing is missing.\n- Showing an interaction the product doesn't support, when Step 1 already established what it does.\n- Naming a brand, a photographer or a publication in the prompt in place of describing the look.\n- Re-running a rejected frame without first finding out what was wrong with it.\n\n## Edge cases\n\n- **The image came back not as intended** — wrong angle, warped label, a look you didn't ask for →\n  deliver it anyway and say what you think is off. Do not regenerate on your own judgement: a second\n  generation bills again, and the user may be happy with the first.\n- **A rejection that names no reason** → ask what missed before re-running, with options drawn from\n  the mode you just shot, plus free text. A blind re-run bills again and lands elsewhere at random.\n- **Safety or policy rejection** → name a workable stand-in and resubmit; on a second, try\n  `seedream-5`; on a third, say which element is blocked rather than retrying blind.\n- **Generic failure** → read the error. If it names a parameter or limit, fix that and resubmit;\n  otherwise resubmit once, then hand the user the error text.\n- **`reference_images` rejected on count** → the error states the limit; drop to it.\n- **`error: \"no_provider_configured\"`** → relay the tool's `hint` (the user must set their key).\n\n## Reference\n\n**Mode guides** — read the one you routed to; each ends with a checklist to read your prompt against:\n\n- `references\u002Fmode-studio.md` — the background and its brightness, true colour, sharpness, shadow.\n- `references\u002Fmode-lifestyle.md` — place, hour, motivated light, and what keeps the product the subject.\n- `references\u002Fmode-hero.md` — the open side for copy, the graded key, surviving every delivery crop.\n- `references\u002Fmode-on-model.md` — casting, styling condition, hands, where the crop cuts the body.\n- `references\u002Fmode-close-up.md` — the one property, raking light, apparent source size, the scale cue.\n- `references\u002Fmode-flat-lay.md` — camera plane, arrangement register, the open surface.\n- `references\u002Fmode-seasonal.md` — the single carrier, whose palette it is, props that read as included.\n- `references\u002Fmode-infographic.md` — callout copy, anchors, leader lines, the exposing angle.\n- `references\u002Fmode-creative.md` — the concept, the one departure, coloured sources, what is held dark.\n- `references\u002Fmode-floating.md` — the underside, the displaced shadow, the gap that reads as height.\n\n**Shared craft** — read on every job:\n\n- `references\u002Fphotographic-craft.md` — the two fixed blocks that close every prompt; the style\n  anchor; light, shadow, colour, material, optics and on-image text; what changes for paid media.\n",{"name":5,"license":15,"metadata":24,"description":28},{"summary":25,"version":26,"category":27},"Directs a commercial photoshoot around your product, automatically applying the correct lighting, framing, camera angles and props to deliver studio-quality product shots across 10+ formats.","0.2.0","creative","ALWAYS read this skill before generating a product photography — before writing any prompt or calling image_generate. Turns a product photo or URL into commercial photography - packshots, lifestyle and campaign frames, on-model, macro detail, flat lays, seasonal staging, infographics, concepts and floating shots. Reads the real product first and holds it identical across every frame. Triggers: \"product photo\", \"packshot\", \"shoot my product\", \"studio shot\", \"lifestyle shot\", \"hero image\", \"on a model\", \"flat lay\", \"product infographic\", \"floating product\", \"product ad\".\n","master","63f17866001c5ca854bf2fa0b678ce277133de5b","skills\u002Fmarketplace\u002Fgenerating-product-photos__skills-supercmohq-generating-product-photos",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill generating-product-photos",{"tool":45,"command":46},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill generating-product-photos",{"tool":48,"command":49},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill generating-product-photos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fgenerating-product-photos__skills-supercmohq-generating-product-photos\u002FSKILL.md",true,[53],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"skill-report.json","REFERENCE","参考文档",52811,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fgenerating-product-photos__skills-supercmohq-generating-product-photos\u002Fskill-report.json",[60,69,76,83,90,97],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":68},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":68},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":68},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":68},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":68},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":68},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]