55-scaling-ads-global SKILL.md skillA
55-scaling-ads-global from minhnv0807/ai-business-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add minhnv0807/ai-business-skills/55-scaling-ads-global@v1.0.2Pins v1.0.2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- minhnv0807/ai-business-skills
- Path
skills/en/55-scaling-ads-global/SKILL.md- Versions recorded
- 3
- Latest version
- v1.0.2, committed Oct 28, 2026
- First version recorded
- Jul 30, 2026
- Size
- 11,392 bytes
- Repository stars
- 644
- License
- MIT
Use when a WINNING ad has to be scaled without breaking it — readiness checks, vertical scaling at plus 20 to 30 percent per step, horizontal scaling into new audiences, creatives, and channels, learning-phase reset risk, how Advantage+ and Performance Max behave when scaled, creative refresh cadence, and the signals that mean stop. Trigger on 'scale ads', 'increase the ad budget', 'scale a winner', 'CPA went up after I scaled', 'how fast can I scale', 'it worked at 50 a day and broke at 200'.…
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
# Scaling Ads (Global) Scaling means increasing spend while holding or improving efficiency. Scaling badly means CPA spikes and budget burns. **Hard rule: never increase budget while CPA is bad.** Fix the problem first (run `21-ads-audit-global`), then scale. ## Information gathering Ask up to 4 questions: 1. **Is there a proven winner?** How many consecutive days has CPA been stable? At least 7 are needed. 2. **What are the current numbers?** CPA, ROAS, frequency, spend, and reach against total audience size. 3. **Current daily budget and target daily budget?** 4. **Which platform, and how many spare creatives exist?** Never scale on a single creative. ## Principles 1. **Bad CPA means no scaling.** Adding budget to a broken campaign accelerates the loss. 2. **+20-30% per step, never double overnight.** Sudden jumps reset the learning phase and CPA spikes. The safest cadence is +20% every 72 hours. 3. **Monitor 24-48 hours after every increase** before the next one. 4. **Do not edit a winning ad set while scaling.** Any significant change — budget shock, audience edit, creative swap inside the ad set — can reset learning. …
Read the whole file at its exact version.
How to install
mdr add minhnv0807/ai-business-skills/55-scaling-ads-global@sha256:ac933761f89d0216The line at the top of this page pins the label v1.0.2, 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_jjad23bsuexz4ep5)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Jul 30, 2026 and Oct 28, 2026, about one every 45 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.2 latest | 2026-10-28 | 1bbd790 | 11,392 B | A | view · diff |
| v1.0.1 | 2026-08-10 | 764ea20 | 10,809 B | A | view · diff |
| v1.0.0 | 2026-07-30 | b16acbc | 10,562 B | A | view |
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 (11392 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
minhnv0807/ai-business-skills · 644 stars · license MIT · pushed 2026-11-05 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_jjad23bsuexz4ep5 GET https://markdownregistry.com/api/v1/resolve?ref=minhnv0807/ai-business-skills/55-scaling-ads-global GET https://markdownregistry.com/api/v1/blob/ac933761f89d02166aa770522777292f3ca6625c553ae25a6fae213f078fe9b3
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.