Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add respira-press/agent-skills-wordpress --skill woo-catalog-perfectiongit clone --depth 1 https://github.com/respira-press/agent-skills-wordpressWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/respira-press/agent-skills-wordpress/woo-catalog-perfection)<a href="https://agentmods.dev/skills/respira-press/agent-skills-wordpress/woo-catalog-perfection"><img src="https://agentmods.dev/badge/skills/respira-press/agent-skills-wordpress/woo-catalog-perfection/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/respira-press/agent-skills-wordpress/woo-catalog-perfection"><img src="https://agentmods.dev/badge/skills/respira-press/agent-skills-wordpress/woo-catalog-perfection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01029 |
| Opus 5 | $0.00037 | $0.00515 |
| Sonnet 5 | $0.00015 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
woo-catalog-perfection scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Woo Catalog Perfection
Description
Close the loop from "your catalog scores 43" to "your catalog scores 90+", product by product, with every change snapshotted.
AI shopping surfaces reject rows that are missing images, descriptions, brands or identifiers, and rank thin content last. This skill runs the Respira readiness fixlist as a work queue: score the catalog, fetch the ordered list of failing products with the exact tool that fixes each gap, apply the fixes in safe batches, and re-score until the target is reached. It writes real content, not filler: descriptions are drafted from the product's own attributes, categories and existing copy, and anything uncertain is queued for the merchant instead of invented.
Requires the Respira WooCommerce Add-on v3.1+.
Trigger Phrases
This skill activates when the user says any of the following:
- "fix my catalog for ai"
- "improve my ai readiness score"
- "fix products failing the feed checks"
- "my products keep getting rejected by google"
- "catalog perfection"
- "fix missing gtins" / "fix missing brands" / "fix product descriptions"
- "get my catalog to 90"
- "clean up my product data"
- "feed disapprovals woocommerce"
Do NOT trigger for: feed setup and platform registration (that is woo-agent-storefront), pricing changes, or content work outside the catalog.
Execution Workflow
Step 1: Score and scope
respira_get_site_context, then woocommerce_catalog_ai_readiness for the baseline score and woocommerce_readiness_fixlist for the ordered work queue. Report: current score, how many products fail which checks, and the estimated pass count. Agree the target (default 90) and the batch size (default 10 products per pass, so every batch is reviewable).
Step 2: Fix in priority order
The fixlist orders work by impact. Per product, apply only what the fixlist maps, using the tool it names:
- Missing GTIN →
woocommerce_update_productwithglobal_unique_idwhen the user can supply real GTINs (ask; never fabricate a GTIN. If none exist, assign brand + SKU so identifier rules pass via brand+MPN). - Missing brand →
woocommerce_create_brand/woocommerce_update_productbrand assignment. Derive the brand from the product name or ask once for the house brand; apply consistently. - Missing or thin description →
woocommerce_update_product. Draft 40-80 words from the product's own attributes, category and existing short description. No invented specs, no superlatives. - Missing image alt text →
woocommerce_set_image_alt, descriptive and under 125 characters. - Missing gallery →
woocommerce_update_productwithgallery_image_idsonly from existing media (respira_list_media); never hotlink. - Unmapped categories →
woocommerce_set_feed_category_mappingto the closest Google taxonomy node.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 79 lines · 74 tokens per session scan A 01221af55aca
woo-catalog-perfection is a skill published in the GitHub repository respira-press/agent-skills-wordpress (43 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,029 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
refund-processor
Process a refund request by gathering context and preparing the refund workflow.
seo-ecommerce
E-commerce SEO analysis: Google Shopping visibility, Amazon marketplace intelligence, product schema validation, competitor pricing analysis, and marketplace keyword gaps. Combines on-page product SEO with marketplace data from DataForSEO Merchant API. Use when user says "ecommerce SEO", "product SEO", "Google…
kelly-inquiry
Personal App-in-Skill inbound-inquiry reception desk (Busabase App-in-Skill) for cross-border/foreign-trade sellers, aggregating WhatsApp, Instagram, Messenger, and email inquiries into a pipeline with a product knowledge base, quote worksheet, approval queue, and follow-up reminders. Use when the user invokes…
kelly-listing
A product-listing workspace for cross-border e-commerce sellers. It turns product information into drafts for Amazon, Shopify, TikTok Shop and eBay, including versions for different countries.
kelly-picks
Product-research (选品) desk (Busabase App-in-Skill) for a cross-border e-commerce seller. The agent sweeps trend sources — Amazon BSR movers, TikTok viral product videos, Temu/AliExpress rising items, Google Trends terms, competitor new launches — and files product candidates with margin cards (landed cost, fees…
kelly-products
An e-commerce product-management workspace for product records, SKUs, prices, inventory, sales-channel status, assets, compliance notes, and product lifecycle stages.