amazon-review-workbook
Collect all customer reviews from an Amazon product URL or product-reviews URL through a logged-in Chrome session on port 9222, export a 14-column factual workbook, optionally fill translations through DeepLX, and then help the model tag the rows into a final delivery-ready spreadsheet. Use when the user sends an Amazon link and wants review scraping, competitor review analysis, review export, or a delivery-ready spreadsheet with usernames, review links, review time, helpful votes, translation, summary, sentiment, categories, and tags.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aduo6668/amazon-review-workbookAmazon Review Workbook
Turn an Amazon product or review link into a two-phase delivery workbook.
This skill is designed to be portable: the scripts live inside the skill folder and do not depend on dashcamauto or any other local repo.
Quick Path
- If this is the first run on a machine, read references/setup.md.
- Run a quick health check:
python scripts/amazon_review_workbook.py doctor --url "<amazon-url>"
- Run factual collection:
python scripts/amazon_review_workbook.py intake --url "<amazon-url>" --output-dir "<workspace>/amazon-review-output"
- If DeepLX is configured and reachable, fill
评论中文版:
python scripts/amazon_review_workbook.py translate --input-json "<workspace>/amazon-review-output/amazon_<asin>_review_rows_factual.json" --output-dir "<workspace>/amazon-review-output"
- Check coverage before deciding whether keyword expansion is worth the extra requests:
python scripts/amazon_review_workbook.py coverage-check --url "<amazon-url>" --db-path "<workspace>/amazon-review-output/amazon_review_cache.sqlite3"
- Build canonical tags and a lightweight tagging payload:
python scripts/amazon_review_workbook.py taxonomy-bootstrap --input-json "<workspace>/amazon-review-output/amazon_<asin>_review_rows_translated.json" --output-dir "<workspace>/amazon-review-output"
python scripts/amazon_review_workbook.py prepare-tagging --input-json "<workspace>/amazon-review-output/amazon_<asin>_review_rows_translated.json" --output-dir "<workspace>/amazon-review-output" --canonical-tags-json "<workspace>/amazon-review-output/canonical_tags.json"
taxonomy-bootstrap is only for building a stable canonical vocabulary for the batch. prepare-tagging consumes the full factual or translated JSON and emits a trimmed *_tagging_input.json that contains pending rows only plus cache metadata. Do not use that trimmed file as the merge source.
- Read references/tagging-guidelines.md, let the model fill only the pending rows in a separate labels JSON, then merge the labels back into the full base JSON and build the final workbook:
python scripts/amazon_review_workbook.py merge-build --base-json "<workspace>/amazon-review-output/amazon_<asin>_review_rows_translated.json" --labels-json "<workspace>/amazon-review-output/amazon_<asin>_labels.json" --output-dir "<workspace>/amazon-review-output" --taxonomy-version "v1" --strict
Workflow
1. Verify prerequisites
- Confirm
doctorreports a validasin. - Confirm
chrome_debug_readyistrue. - If you plan to use
translate, confirmdeeplx_env_readyistrue. - If
deeplx_reachableisfalse, do not block the workflow; let the model fill评论中文版during tagging.
If any of these fail, read references/setup.md before continuing.
2. Use the smallest command that fits
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aduo6668-amazon-review-workbook": {
"enabled": true,
"auto_update": true
}
}
}