amazon-ads-attribution-and-metrics-audit SKILL.md skillB
amazon-ads-attribution-and-metrics-audit from coupler-io/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add coupler-io/skills/amazon-ads-attribution-and-metrics-audit@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- coupler-io/skills
- Path
marketing-and-ads/amazon-ads/amazon-ads-attribution-and-metrics-audit/SKILL.md- Versions recorded
- 8
- Latest version
- v1.0.0, committed Oct 21, 2026
- First version recorded
- Sep 30, 2026
- Size
- 13,869 bytes
- Repository stars
- 40
- License
- MIT
Use for "can I trust my Amazon ACOS", "why don't my Amazon Ads sales match Seller Central", "which attribution window does Amazon use", "are my Amazon ad sales including halo", "why is my Amazon Sponsored Display ROAS so high", "are my Amazon numbers comparable across ad products", or "my Amazon sales keep changing" — and whenever someone doubts their Amazon Ads numbers, even without the word "audit". Run before trusting any ACOS or ROAS comparison. Amazon Ads only.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Amazon Ads Attribution and Metrics Audit Checks whether your Amazon Ads sales and ACOS can be trusted and compared before you use them to move budget. Amazon Ads Attribution and Metrics Audit is a Coupler.io AI agent skill that works with live data from Amazon Ads and Amazon Ads (Unified). **Tells you whether the Amazon Ads sales and ACOS figures can be compared and trusted before anyone moves money on them — which window, which sales, which currency — and where two numbers that look alike aren't.** Amazon doesn't have a tracking tag to break, so its numbers look solid. The problems are definitional. Sponsored Products and Sponsored Brands can report on different attribution windows, so their ACOS figures aren't comparable. Some sales columns count only the product advertised; others add halo sales from the rest of the brand; Display and DSP add sales credited to people who only saw the ad. Two marketplaces can sit in one dataset in two currencies. And recent days keep filling in. Every one of these produces a clean-looking number that's wrong to compare. **What you get back** …
Read the whole file at its exact version.
How to install
mdr add coupler-io/skills/amazon-ads-attribution-and-metrics-audit@sha256:1c6171b40da1148cThe line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_547hfrecpfbw7su5)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Sep 30, 2026 and Oct 21, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-10-21 | e36545f | 13,869 B | B | view · diff |
| v1.0.0 | 2026-10-13 | ee6a3a9 | 13,618 B | B | view · diff |
| v1.0.0 | 2026-10-12 | 3a5f5c7 | 13,612 B | B | view · diff |
| v1.0.0 | 2026-09-30 | a9cfdc6 | 13,592 B | B | view · diff |
| v1.0.0 | 2026-09-30 | 109e9cf | 13,464 B | B | view · diff |
| v1.0.0 | 2026-09-30 | d8e9ed6 | 13,129 B | B | view · diff |
| v1.0.0 | 2026-09-30 | 94d88d4 | 13,094 B | B | view · diff |
| v1.0.0 | 2026-09-30 | 6f07e3d | 12,475 B | B | view |
Audit of the latest version
- fail: No prompt-injection phrasing (matched: ignore previous instructions)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13869 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
coupler-io/skills · 40 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_547hfrecpfbw7su5 GET https://markdownregistry.com/api/v1/resolve?ref=coupler-io/skills/amazon-ads-attribution-and-metrics-audit GET https://markdownregistry.com/api/v1/blob/1c6171b40da1148c0f3dfad1fcbd657c0f609065876e9258e4c5aa5d8563cec9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.