Analysis updated 2026-06-24
Rewrite English product titles in bulk with DeepSeek or Kimi
Normalize duplicate SKU spec names like two yellow variants into numbered entries
Strip disclaimer and factory shots out of detail image sets
Sync edited products from a Philippines store to Malaysia and Thailand
| xmanner/miaoshou-auto-edit | deanwhitex/aiw2.0stack | emirsametguzel/escape-from-mz | |
|---|---|---|---|
| Stars | 28 | 28 | 27 |
| Language | JavaScript | JavaScript | JavaScript |
| Setup difficulty | moderate | moderate | easy |
| Complexity | 3/5 | 3/5 | 2/5 |
| Audience | ops devops | vibe coder | general |
Figures from each repo's GitHub metadata at analysis time.
Needs Node 18+, a Miaoshou open-platform App ID and Secret, and a DeepSeek or Kimi API key, always run with --publish false first because --publish true pushes live.
This is a Node.js script for sellers who use the Miaoshou platform to manage products on TikTok Shop. The README is written in Chinese. The script automates the boring, repetitive cleanup work on items pulled into Miaoshou's collection box, so the seller can batch-process many products at once instead of editing them one by one. The main jobs it does are: rewriting English product titles using either DeepSeek or Kimi as the AI provider, stripping sensitive words from titles and detail text, normalising SKU spec names into English and handling duplicates (the README gives the example of turning two yellow variants into #1 Yellow and #2 Yellow), and adding 30 grams to each product's weight by default while making sure repeated runs do not keep stacking the weight up. It also cleans irrelevant images out of the main and detail picture sets, things like disclaimers, factory shots, store recommendations, and bundle promotions. Cross-site sync from the Philippines store to Malaysia and Thailand is supported by default. To run it you need Node.js 18 or newer, a working Miaoshou open-platform App ID and App Secret, and an API key for either DeepSeek or Kimi. You copy .env.example to .env and fill in the keys, then either run a web console at http://127.0.0.1:3000 by typing npm run web, or call the script from the command line with flags like --count and --publish false to do a dry run. The README warns that --publish true actually pushes changes live, so the author recommends always running with --publish false first to inspect the result before doing a batch publish.
A Node.js script for TikTok Shop sellers using the Miaoshou platform that batch-cleans product titles, SKU names, weights, and detail images via DeepSeek or Kimi, with an optional web console and a dry-run mode.
Mainly JavaScript. The stack also includes Node.js, JavaScript, DeepSeek.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly ops devops.
This repo across BitVibe Labs
Verify against the repo before relying on details.