Ecommerce Listing Suite

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites: none for the install itself: no account, no API key, no paid service, and nothing else to install first. For using the skill afterwards, read this first: generation goes through one of three routes, and only one of them is free of keys — (a) your agent's own built-in image tool, if it has one (no key from me); (b) an API key route that needs Python 3 and my own API key in the environment variable GPTIMAGE_API_KEY, billed by the provider I choose (see the sends disclosed in point 2: the default endpoint in the bundled script is https://api.openai.com, and SKILL.md recommends the third-party OpenAI-compatible gateway https://tryallapi.com/v1 — if I set that base URL, my key and my images go to that gateway, not to OpenAI); or (c) a no-key online link route, where the final prompt leaves this machine in a link to a third-party site (also disclosed in point 2). Both bundled scripts use the Python standard library only; there is no Pillow or other extra dependency in this skill folder. I also provide the product photo myself: the skill asks for at least a front view, and text-only generation is only a concept, not the real product. Important scope note, disclosed up front: this skill is an orchestrator — at use time its workflow plans a full set and then calls the 11 specialised sibling skills of the same repository (or, if a sibling is not installed, reads that sibling's SKILL.md template directly from the repository); this listing installs this orchestrator folder only, not the 11 siblings (see point 2). Install "ecommerce-listing-suite" for me. It orchestrates a complete, platform-ready ecommerce image set for one product: first a product identity lock written from my reference photos and pasted verbatim into every prompt, then a campaign style lock, then a confirmed plan table per platform (Amazon 7-image set: white-background main, key-benefit infographic, lifestyle, second benefit/comparison, size chart, detail macro/multi-angle, in-use or what's in the box, plus A+ modules; Taobao/Tmall 5 main images 800x800 plus a 750-wide detail long image; Shopee/Lazada/TikTok Shop 1 main 1:1 plus 4-8 benefit/scene images plus a campaign banner; Xiaohongshu 3 cover variants 3:4 plus 3-6 inner images), generation through one of the three routes above (default model GPT Image 2.5 Flare, gpt-image-2.5-flare, for new scenes; Sunburst, gpt-image-2.5-sunburst, when a logo, label or small text must survive exactly), then a QA check of every image and a hand-off (file list named 01-main.jpg and so on, prompts in prompts.md, QA table, and a 3-line QA note per asset). Repository: https://github.com/xianyu110/ecommerce-image-skills (the skill is the whole skills/ecommerce-listing-suite/ folder at the pinned commit: SKILL.md plus its scripts/ folder, 3 files) Pinned version: install the code at commit f4566fdc812584425728862ad8e08c90883d81ee exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/xianyu110/ecommerce-image-skills into a temporary folder, check out commit f4566fdc812584425728862ad8e08c90883d81ee, and copy the skills/ecommerce-listing-suite/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-19: [FINGERPRINTS] - SKILL.md: SHA-256 2e921a6674ccaf57a7db25c854e6a4f988179d8991addb3415d8785f9fa7cf97 - scripts/generate.py: SHA-256 5339fc5c9c3fd9bb02a1f0dd8643386329ba813c7ebe958a8d28241ed343d1c5 - scripts/online_link.py: SHA-256 72a6a843157d8cfb84f809d4811edefbc1e222dd10807037f0b64524ebb43ad3 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full and read both scripts in scripts/ (generate.py, online_link.py), and tell me in plain words: what the skill does when used, which services it connects to, whether it reads or sends any personal information or keys, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 3 files only: SKILL.md (6,530 bytes) and two Python scripts in scripts/ (generate.py 4,824 bytes, online_link.py 788 bytes). The two scripts in this folder are byte-identical copies of the same-named scripts at the repository root (scripts/): as far as its own files go, the folder is self-contained. Unlike the specialised sibling listings of this repository, however, this skill is NOT functionally self-contained at use time: SKILL.md's workflow step 5 delegates each planned asset to a named sibling skill — white-background main to amazon-white-background (then run its check script), scenes to lifestyle-scene, apparel on model to model-try-on, benefits/comparison to selling-point-infographic, A+ to amazon-a-plus, dimensions to size-chart, angles to multi-angle-set, banners to sale-banner, bulk backgrounds/colourways to batch-background-swap, RED covers to xiaohongshu-cover, detail pages to taobao-detail-long-image — and SKILL.md says verbatim: "If a sibling skill isn't installed, use the templates in this repo's skills/<name>/SKILL.md directly." Those 11 sibling folders, their SKILL.md templates and their own extra scripts (for example check, crop, grid or stitch scripts) are outside this listing's install scope and are not installed by this install; at use time the agent will either call siblings I have installed separately or read a sibling template from the repository, which is a separate download at use time, not during this installation. SKILL.md only ever calls its own two scripts (scripts/generate.py, scripts/online_link.py, relative to the skill folder) for its own generation routes. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. No script is run during installation, no key is asked for, and there is no telemetry in the folder. - What leaves this machine at use time, disclosed here before it ever happens, by route — the skill picks the first route that works, and using the skill is a separate step that only starts when I ask for a full listing image set: (a) built-in image tool: the final prompt for each asset (with the identity lock and style lock pasted in) and my product photo(s) go to whatever image generation tool my agent already has (for example Codex imagegen or ChatGPT images), under that tool's own account and terms. (b) API key route: scripts/generate.py reads GPTIMAGE_API_KEY from the environment (never from a file, never printed), plus the optional GPTIMAGE_BASE_URL (default https://api.openai.com; SKILL.md recommends https://tryallapi.com/v1) and GPTIMAGE_MODEL, and sends an authenticated (Bearer) request to that base URL — a JSON POST to /v1/images/generations carrying the prompt, model, size and count for text-to-image, or a multipart POST to /v1/images/edits carrying the same fields plus the product reference photo(s) I pass with --image (front, side, logo close-up). If the API answers with an image URL instead of base64 data, the script downloads that URL. Whichever base URL I set receives my key, my prompt and my product photos: if I set the recommended tryallapi.com gateway, that third-party gateway is the recipient, not OpenAI. (c) Online link route: scripts/online_link.py itself makes no network call — it only prints a link — but the link it builds is https://gptimage2.asia/generate?prompt=<my final prompt, URL-encoded>&utm_source=github&utm_medium=skill&utm_campaign=ecommerce-image-skills&utm_content=ecommerce-listing-suite, so opening it sends my final prompt to gptimage2.asia, and SKILL.md tells me to upload my product photo on that site; SKILL.md also names an alternative site for users in mainland China, https://chatgpt-plus.top/list/#/home, where I would paste the prompt myself. Show that link once only, and never open it for me during installation. If a sibling skill is called at use time, that sibling's own disclosed sends apply on its own route, under its own listing. - The local-only parts at use time: both bundled scripts' non-network parts and the planning steps (intake, identity lock, campaign style lock, plan table confirmed with me, prompt writing, QA of every image, hand-off file list and prompts.md) stay local, between you and me; online_link.py is local-only (it only prints the link). The identity lock rule from SKILL.md: only facts visible in my photos or confirmed by me — never invent specs, sizes or certifications, and if I gave no photo, ask for one before generating. - Do not install anything else during this install, do not set or ask for GPTIMAGE_API_KEY, do not run either of the two scripts, do not read or copy any sibling skill folder, and do not generate any image: setup of a generation route, and any separate install of a sibling skill, are my decisions, later, when I actually ask for a listing set. 3. When I say "yes, install", install it as a skill: copy the whole ecommerce-listing-suite folder into the agent's skills directory, in a folder named "ecommerce-listing-suite", keeping all 3 files (SKILL.md at its root and the two scripts in its scripts/ subfolder). A manual clone followed by copying the skills/ecommerce-listing-suite folder into ~/.claude/skills/ is the route described here; any other route is fine only as long as every installed file matches its fingerprint. Do not use the repository's plugin-marketplace route for this listing: it installs all 12 skills of the repository, which is outside this listing's scope. 4. Verify with no network calls: frontmatter valid (name: ecommerce-listing-suite), all 3 files in place with matching fingerprints. Do not run generate.py or online_link.py to verify. 5. Report what was installed, where, and what I still need to do myself (for example: provide product photos, front view at minimum plus other angles and a logo close-up, and the verified facts, target platform(s) and market/language, and confirm the identity lock, style lock and plan table; choose a generation route myself — my agent's built-in image tool if it has one, or set GPTIMAGE_API_KEY and, if I want it, GPTIMAGE_BASE_URL in my environment for the API route, knowing the key, prompt and product photos go to the base URL I set, or use the one-click online link knowing the prompt goes to gptimage2.asia; decide myself, separately, whether to install any of the 11 sibling skills this orchestrator calls, knowing that without them it will read their SKILL.md templates from the repository at use time; using the skill is a separate step that only starts when I ask for it, and the use-time sends disclosed above happen only then, on the route that runs). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.