メニュー
Drive a WooCommerce catalog to an AI-readiness score of 90+ — an ordered fixlist loop that writes the missing images alt text, descriptions, brands, GTINs and category mappings, with a snapshot before every change.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Make a WooCommerce store discoverable and shoppable for AI assistants — set up product feeds in six formats, serve a store llms.txt, register with Google Merchant Center / OpenAI / Meta / Pinterest / TikTok, and hand out attributed cart links.
Fast 30-second session-starter. Loads the active site, identifies the page builder, loads inline schemas, and primes the agent on the do-not-write-raw-HTML rule before any work begins. v1.1 adds per-site memory: it reads a stored brief at the start and appends what it learned at the end, so context carries across sessions, teammates, and AI clients.
Turn the audit log of work done on a WordPress site into a polished written report. Wraps the v7.1 respira_generate_activity_report MCP tool with six framings: agency client report, case study, internal recap, testimonial draft, build-in-public, personal recap.
Read 5-10 published posts and extract the brand voice — tone, lexicon, sentence patterns, person used, formality, signature phrases, phrases the site never uses. Persist it so every future content-writing skill produces copy that sounds like the brand, not like generic AI.
Audit a WordPress site for conversion-rate friction across six dimensions: above-the-fold clarity, CTA hierarchy, form length, social proof placement, page speed, and trust signals. Prioritized fixes with expected impact — recommendations, not redesigns.
Design and create WordPress custom post types end to end — CPT + supporting taxonomies + ACF field group + sample entries + builder-specific single template suggestion. Uses new v7.1 MCP tools: respira_create_post_type, respira_create_taxonomy, respira_create_acf_field_group.
| name | woo-catalog-perfection |
| description | Drive a WooCommerce catalog to an AI-readiness score of 90+ — an ordered fixlist loop that writes the missing images alt text, descriptions, brands, GTINs and category mappings, with a snapshot before every change. |
| license | MIT |
| metadata | {"author":"Respira for WordPress","author_url":"https://respira.press","version":"1.0.0","mcp-server":"respira-wordpress","category":"commerce"} |
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+.
This skill activates when the user says any of the following:
Do NOT trigger for: feed setup and platform registration (that is woo-agent-storefront), pricing changes, or content work outside the catalog.
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).
The fixlist orders work by impact. Per product, apply only what the fixlist maps, using the tool it names:
woocommerce_update_product with global_unique_id when the user can supply real GTINs (ask; never fabricate a GTIN. If none exist, assign brand + SKU so identifier rules pass via brand+MPN).woocommerce_create_brand / woocommerce_update_product brand assignment. Derive the brand from the product name or ask once for the house brand; apply consistently.woocommerce_update_product. Draft 40-80 words from the product's own attributes, category and existing short description. No invented specs, no superlatives.woocommerce_set_image_alt, descriptive and under 125 characters.woocommerce_update_product with gallery_image_ids only from existing media (respira_list_media); never hotlink.woocommerce_set_feed_category_mapping to the closest Google taxonomy node.Batch writes 10 at a time. Every write is snapshotted by the add-on automatically; state the snapshot coverage in the report.
After each batch, woocommerce_validate_feed (google) for the score delta. Continue until the target is hit, the fixlist is empty, or the remaining items need merchant input (real GTINs, product photos). Queue those explicitly instead of guessing.
Close with: score before → after, products fixed per check type, what was written (with snapshot note: "every change is reversible for 90 days"), and the merchant-input queue (missing photos, GTINs to source). If feeds are enabled, remind that they rebuild automatically within minutes, so the fixes reach Google/ChatGPT on the next platform fetch.