Taobao Detail Long Image

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). The local stitch script scripts/stitch_long_image.py also needs Python 3 with Pillow (PIL) — Pillow is not part of the Python standard library and is not installed by this install; SKILL.md itself shows a `pip install pillow` step at stitch time, which is a use-time step for me to run myself, never part of this install. The other two scripts use the standard library only. 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. Install "taobao-detail-long-image" for me. It plans and generates a Taobao / Tmall / Pinduoduo / JD product detail page (详情页) as 750-px-wide screens stitched into one long image: first a product identity lock written from my reference photos and pasted verbatim into every prompt, then a default 8-screen plan confirmed with me (hero, pain point → solution, three selling-point screens, usage scenes, macro details, specs + after-sales), a detail-page style lock pasted into every screen prompt, one prompt per screen in portrait 3:4 (each screen about 750×1000, resized to 750 px wide), 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 local stitch of the screens into one 750-px long JPG plus upload slices of at most 1546 px high, and a 3-line QA note per asset. Repository: https://github.com/xianyu110/ecommerce-image-skills (the skill is the whole skills/taobao-detail-long-image/ folder at the pinned commit: SKILL.md plus its scripts/ folder, 4 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/taobao-detail-long-image/ 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 0fc12f3a5a67fbf136f5a6f7d012f304667967cc7cb411df4963d6db1b62d80b - scripts/generate.py: SHA-256 5339fc5c9c3fd9bb02a1f0dd8643386329ba813c7ebe958a8d28241ed343d1c5 - scripts/online_link.py: SHA-256 72a6a843157d8cfb84f809d4811edefbc1e222dd10807037f0b64524ebb43ad3 - scripts/stitch_long_image.py: SHA-256 bbb3a33e89b1a97267fe2ec24dae819e1048d274fba49eb8fb14cbd7d900a6f1 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 all three scripts in scripts/ (generate.py, online_link.py, stitch_long_image.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 4 files only: SKILL.md (5,823 bytes) and three Python scripts in scripts/ (generate.py 4,824 bytes, online_link.py 788 bytes, stitch_long_image.py 1,292 bytes). The three scripts in this folder are byte-identical copies of the same-named scripts at the repository root (scripts/): the skill is self-contained in its own folder and needs no file from elsewhere in the repository — not the other 11 skills, not the root scripts/, not the README. SKILL.md only ever calls the scripts sitting next to it (scripts/generate.py, scripts/online_link.py, scripts/stitch_long_image.py, relative to the skill folder). - 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 detail page: (a) built-in image tool: the final screen prompt (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 key) 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; the SKILL.md example uses --size 1024x1536). 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=taobao-detail-long-image, 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. - The local-only parts at use time: scripts/stitch_long_image.py never touches the network — it opens the generated screens locally with Pillow, resizes each to 750 px wide (or the --width given), stacks them vertically into one long JPG, and also writes upload slices of at most 1546 px high into a <name>-slices/ folder. The planning steps (identity lock, 8-screen plan, style lock, prompt writing, QA note) also stay local, between you and me. 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. SKILL.md also carries a Chinese advertising-law note: avoid absolute superlatives (最 / 第一 / 国家级 / 绝对 and the like) and use only provable claims. - Do not install Pillow or anything else during this install (do not run the `pip install pillow` line shown in SKILL.md), do not set or ask for GPTIMAGE_API_KEY, do not run any of the three scripts, and do not generate any image: setup of a generation route is my decision, later, when I actually ask for a detail page. 3. When I say "yes, install", install it as a skill: copy the whole taobao-detail-long-image folder into the agent's skills directory, in a folder named "taobao-detail-long-image", keeping all 4 files (SKILL.md at its root and the three scripts in its scripts/ subfolder). A manual clone followed by copying the skills/taobao-detail-long-image folder into ~/.claude/skills/ is the route described here; any other route is fine only as long as every installed file matches its fingerprint. 4. Verify with no network calls: frontmatter valid (name: taobao-detail-long-image), all 4 files in place with matching fingerprints. Do not run generate.py, online_link.py or stitch_long_image.py to verify. 5. Report what was installed, where, and what I still need to do myself (for example: provide a product photo, front view at minimum, and confirm or edit the 8-screen plan; 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; install Pillow myself if I want the local stitch into the 750-px long image; 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.