tiktok-ads-structure-and-learning-review skillA
tiktok-ads-structure-and-learning-review is agent-read markdown (skill) from coupler-io/skills: Use for "is my TikTok account built right", "why are my ad groups stuck in learning", "do I have too many ad groups", "should I consolidate", "why won't this ad group exit learning", "I inherited this TikTok account, what's wrong with it", or "my delivery keeps restarting" — even when the user never says "structure". Covers how the account is organised and what that costs it in learning. TikTok Ads only..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# TikTok Ads Structure and Learning Review **Tells you whether the account is split into more ad groups than its budget can feed, and prices what that costs in delivery.** The most expensive mistake in a TikTok account is almost always structural and almost never visible. An account split into fourteen ad groups on a £6,000 month gives each one about £14 a day — nowhere near the conversion volume an ad group needs to exit learning, so every one of them delivers on guesswork indefinitely. Cost per result stays 30% worse than it needs to be and nothing in Ads Manager says why, because each individual ad group looks unremarkable. The second version is self-inflicted: someone edits budgets or creative weekly, delivery restarts each time, and the account never gets a settled week to be judged on. **What you get back** - **The fragmentation verdict** — ad groups against budget, and how many the account can actually feed at the volume delivery needs. - **The learning read** — which ad groups are getting enough weekly conversions to have exited, which are not, and the spend sitting in the second group. …
Read the whole file at its exact version.
How to install
mdr add coupler-io/skills/tiktok-ads-structure-and-learning-review@v1.0.0mdr add coupler-io/skills/tiktok-ads-structure-and-learning-review@sha256:1a2918101bd5c2a1Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_u43c7ydr56gjzubf)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12837 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 prompt-injection phrasing
- 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
Source
coupler-io/skills · 34 stars · license none · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_u43c7ydr56gjzubf GET https://markdownregistry.com/api/v1/resolve?ref=coupler-io/skills/tiktok-ads-structure-and-learning-review GET https://markdownregistry.com/api/v1/blob/1a2918101bd5c2a163009c2f802c99c2d30d116315d0634e61ed79dfcea46bdf
Your agent 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.