Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Autonomous BigCommerce product content optimizer. Bulk-update, rewrite, optimize, or generate product titles and descriptions on a BigCommerce store. Trigger...
Autonomous BigCommerce product content optimizer. Bulk-update, rewrite, optimize, or generate product titles and descriptions on a BigCommerce store. Trigger...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Autonomous skill that fetches products from a BigCommerce store, generates optimized titles and descriptions, and updates them back β one page at a time with full progress tracking.
The user must provide: Store Hash β the BigCommerce store identifier (e.g., abc123def) API Token β a BigCommerce API v3 token with Products read+write scope
Before first use, install the requests library: pip install requests --break-system-packages The helper script is at: ~/.openclaw/workspace/skills/bigcommerce-content-optimizer/scripts/bc_optimizer.py Set SCRIPT as the full path to bc_optimizer.py for all commands below.
CRITICAL: Do NOT stop between pages. Process ALL pages continuously until done.
python3 $SCRIPT init --store-hash "STORE_HASH" --token "API_TOKEN" --limit 10 This creates progress.json in the current working directory and returns total product/page counts. If progress.json already exists with status: in_progress, it resumes from the last unprocessed page.
2a. Fetch the page python3 $SCRIPT fetch --store-hash "STORE_HASH" --token "API_TOKEN" --page PAGE_NUMBER --limit 10 Outputs page_N_products.json with product data. 2b. Read products and generate content Read the fetched JSON. For EACH product, generate: New Title: SEO-friendly, concise, under 70 characters. Capture the product essence. New Description: Compelling HTML description, 100-300 words. Use <p>, <ul>, <li> tags. Focus on benefits, use cases, value proposition. No inline styles, no scripts. Consider: existing name/description, SKU, price, categories, brand, images. Apply SEO best practices (natural keywords, not stuffing) and persuasive copywriting. If the user gave brand voice guidelines, follow them. Write the output as page_N_updates.json: [ { "id": 123, "name": "New Product Title", "description": "<p>New compelling description...</p>" } ] 2c. Push updates python3 $SCRIPT update --store-hash "STORE_HASH" --token "API_TOKEN" --updates-file page_N_updates.json Updates each product and logs success/failure to progress.json. 2d. Report and continue After each page, briefly state: Page X of Y complete N products updated, N failed Then IMMEDIATELY proceed to the next page. Do NOT wait for user input.
When all pages are done: python3 $SCRIPT report Print the final summary: total processed, successes, failures, time taken.
Never stop mid-run β process all pages continuously unless an unrecoverable error occurs Always use progress.json β if re-invoked, resume from where you left off Rate limiting β the script handles BigCommerce rate limits with automatic retry Error handling β if one product fails, log it and continue to the next Content quality β every title and description must be meaningfully improved, not just rephrased HTML safety β descriptions use clean simple HTML only (<p>, <ul>, <li>, <strong>, <em>) One page at a time β fetch, generate, update, then move to next page
progress.json tracks everything: { "store_hash": "abc123", "total_products": 150, "total_pages": 15, "products_per_page": 10, "started_at": "2025-01-01T00:00:00Z", "pages_completed": [1, 2, 3], "products_updated": [], "products_failed": [], "current_page": 4, "status": "in_progress" }
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.