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 kgelster/awesome-ecom-skills --skill shopify-matrixifygit clone --depth 1 https://github.com/kgelster/awesome-ecom-skillsWrote 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/kgelster/awesome-ecom-skills/shopify-matrixify)<a href="https://agentmods.dev/skills/kgelster/awesome-ecom-skills/shopify-matrixify"><img src="https://agentmods.dev/badge/skills/kgelster/awesome-ecom-skills/shopify-matrixify/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/kgelster/awesome-ecom-skills/shopify-matrixify"><img src="https://agentmods.dev/badge/skills/kgelster/awesome-ecom-skills/shopify-matrixify.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 | $0.00163 | $0.02380 |
| Opus 5 | $0.00081 | $0.01190 |
| Sonnet 5 | $0.00033 | $0.00476 |
| Haiku 4.5 | $0.00016 | $0.00238 |
Grade A, and why
shopify-matrixify 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shopify Matrixify
The bulk-data workhorse of the catalog-cleanup suite. Matrixify moves store data in and out as spreadsheets, so it is how you touch thousands of records at once instead of one at a time in the admin. Almost every destructive mistake here comes from one of two misunderstandings: what a blank cell means, and what omitting a row means. Internalize the safety doctrine below before you touch a production catalog.
Canonical docs: matrixify.app/documentation. This skill is the operational playbook the docs don't spell out.
Store access
Matrixify runs inside the store, not through the Admin API. You do the work in two places:
- The Matrixify app (Shopify admin → Apps → Matrixify): run Export to pull a sheet, run Import to push one. Every import shows an Analyze preview and, after it runs, an Import Results file.
- A spreadsheet you edit locally (Excel or any CSV editor) or generate with throwaway code.
No token lives in this skill. To verify a write landed, re-export the affected records and inspect the cells, or read them back through the Admin API: the storefront is CDN-cached and lies about freshness.
Safety doctrine
Read this section twice. Every rule here was learned by someone breaking a live store.
- Back up first: the export IS the backup. Before any bulk write, run a full export of the entity you're about to touch (Products, Collections, etc.) and save the file. If the import goes wrong, that export is your restore path. There is no "undo import" button.
- MERGE is the default and it is safe. An empty Command cell defaults to MERGE (except Orders/Draft Orders, which default to NEW). MERGE updates rows that exist, creates rows that don't, and leaves untouched anything you didn't put in the file. Stay on MERGE unless you have a specific reason not to.
- A blank cell in an import DELETES that value: it does not skip it. This
is the single most expensive trap in Matrixify. If your sheet has a
Metafield: custom.care [multi_line_text_field]column and a product's cell is empty, the import writes empty, wiping the existing metafield. Same for any field: blank Body HTML clears the description, blank Vendor errors out. Only include columns you intend to change. The fix is column omission, not blank cells. Absent column = untouched; present-but-blank column = deleted. - REPLACE is destructive by definition. REPLACE deletes the existing record (or nested set: variants, images, tags) and recreates it from only what's in the file. Anything not in the file is gone. Reach for REPLACE only when you truly want the file to be the complete new truth, and back up first.
- Omitting a row does NOT revert a prior import. Dropping a handle from your next file doesn't undo what a previous import did to it. Matrixify only acts on rows present in the current file; it has no memory of the last run. To reverse a change you must import a new file that explicitly sets the old values back.
- Sub-command MERGE ≠ entity MERGE. Setting the entity
Commandto MERGE does not by itself govern tags, images, or variants. Those have their own command columns (Tags Command,Image Command,Variant Command), each of which defaults to MERGE when absent (per the matrixify.app docs). MERGE is the safe default, but state it anyway: always pair aTagscolumn with an explicitTags Commandso the intent (add vs. REPLACE the exact list vs. DELETE listed) is unambiguous on the sheet rather than relying on the default.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 204 lines · 163 tokens per session scan A 05f05f09fed7
shopify-matrixify is a skill published in the GitHub repository kgelster/awesome-ecom-skills (46 stars, last pushed 19d ago), licensed MIT. It adds 163 tokens to every session and 2,380 once invoked, about $0.0008 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
paid-ads-amazon
Plan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon advertising, Sponsored Products, Sponsored Brands, Sponsored Display, ASIN targeting, Amazon ACoS, or Amazon Ads performance exports.
beat-sync-reel
Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.
ebay-search
Search eBay listings - find items, auctions, deals, and compare prices.
einbeziehung-online-clickwrap-browsewrap
Für Einbeziehung Online Clickwrap Browsewrap: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
kurzfristige-preiserhoehung-lieferfrist
Für Kurzfristige Preiserhöhung 309: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel. Fachgebiet: AGB-Recht-Prüfer. Route: kurzfristige-preiserhoehung-lieferfrist.
plattform-online-gate-rollout-rangfolge
Für Plattform und Online Checkout: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: plattform-online-gate-rollout-rangfolge.