Ozon listing assembly from 1688 for Codex
ozon-pilot
A Codex skill that turns a 1688 link into a local package for manual Ozon upload: retouched photos, Russian copy, a keyword plan and an Excel pricing register
Low risk
We rate an entry low when it mostly gives the agent instructions and reference material.
Why this level
- Prepares files locally and never calls the Ozon Seller API, publishing stays manual
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/ozon-pilotDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a claude-code -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a cursor -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a github-copilot -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a codex -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a gemini-cli -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a cline -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a roo -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
A fork of Roo Code, same .roo folders.
Run in a terminal in the project folder
npx skills add canfeng524-bot/ozon-pilot --skill ozon-pilot -a opencode -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Install dependencies into .deps with py -3.12 -m pip install --target .deps -r requirements.txt, then run python run.py "<1688 link>" and check review.html before manually uploading to Ozon.
Other ways from the author
py -3.12 -m pip install --target .deps -r requirements.txtInstalling dependencies locally into the project before the first run.
This is third-party code. Review the repository files before installing.
What it does
Given a 1688 product link or a userscript-exported JSON, the skill downloads the source photos, filters them by resolution and content, composes 1350x1800 upload-ready images from real photos plus programmatic layout, and flags any missing scene for separate AI generation instead of inventing one. It separately builds a keyword_plan.json with a source confidence tier (Ozon Seller data, current search-page wording, or stale guesses) and Russian copy that avoids word-for-word translation from Chinese. The output is a review.html for manual checking, an ozon_listing.xlsx with pricing, and a remastered folder with the finished images; the skill itself uploads nothing to Ozon, publishing in the seller cabinet stays with the seller.
Who it is for. For sellers who source products on 1688 and assemble Ozon listings by hand, but want photo selection, copy and pricing automated.
Good fit when
- You have a 1688 product link or a userscript export and need a ready package for Ozon upload
- You need Russian listing copy that isn't a literal Chinese translation
- You are fine manually uploading the finished package into the Ozon cabinet
Not a fit when
- You need direct Ozon publishing without a manual upload: the skill doesn't do that
- You lack Ozon Seller demand data and need an honest estimate without invented search volume
- You don't want to configure separate text, vision and image-generation models in config.yaml
Example request
Assemble an Ozon package from this 1688 link, skip AI generation, use only real photosLimitations
The README is in Chinese. Without configured models (text, vision, image generation) some steps degrade: photo selection falls back to heuristics, copy becomes a prompt file instead of a finished result, and images queue into ai_todo.json. Uploading to Ozon is done by a person manually from the finished package, the skill does not connect to the Seller API to publish.
How to disable. Remove the ozon-pilot skill from the Codex skills directory.
Security check
- Prepares files locally and never calls the Ozon Seller API, publishing stays manual
README in short
The Chinese README describes two run modes (by link or by a folder with a userscript JSON export), an output-file table, rules for clean listing images with no foreign text or watermarks, requirements for scale-reference photos, keyword rules tiered by source confidence (Ozon Seller data, current search results, stale guesses), and the principle of splitting real photos from AI generation by scene type.
FAQ
Does the skill publish the listing to Ozon itself?
No, it prepares a local package (photos, copy, xlsx), the seller uploads it into the cabinet manually.
What if no text or image model is configured?
The skill degrades gracefully: copy comes out as a prompt file for any model, images with no source material queue into ai_todo.json instead of being guessed.
Related
A skill that strips AI writing tells from text using Wikipedia's list, without adding invented facts
Marketing Skills for AI agents
Marketing Skills for AI Agents
About fifty skills for CRO, copywriting, SEO, analytics, ads and launches, built for coding agents
SendPulse MCP server
SendPulse MCP
SendPulse's official remote MCP server: statistics, campaigns and user data through an agent chat
Yandex Direct MCP generated from a machine-readable schema
yandex-direct-mcp
An MCP server and CLI covering all 113 Yandex Direct API v5 methods generated from WSDL, exposing 9 read tools by default and writes only on demand