Install
$ agentstack add skill-kelpi-ai-meta-ads-skills-creative-director ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Creative Director
Doctrine
Design production is where most small advertisers stall: the angle exists, the image never gets made. The bar is not "polished", it is "native and specific": the feed rewards creative that looks like it belongs to a real brand talking to a real person, not a stock template. Every angle gets its own visual, because the visual is part of what the delivery system reads.
When to use
- After angles are approved, before campaign build.
- Needs an image-generation capability for the visuals and a Meta Ads MCP (Pipeboard hosted, or the official one) for the upload step. Without an MCP, stop after the design specs.
Run it
For each of these approved angles: [PASTE ANGLES]
1. Write an image brief: the single visual idea, the on-image text (8 words max, in the brand voice), and how it uses the brand colors and fonts from my kit. One idea per image; if the brief needs a second sentence to explain, it is too complicated.
2. Generate each as a 1:1 (1080x1080) ad image using my real brand colors and fonts. No fake UI, no invented review scores, no brand logos I do not own.
3. Show me all of them as a set first. I will tell you which to keep.
4. For the keepers only: upload them to my ad account image library and give me the image hashes for the campaign build.
Guardrails
- Nothing uploads until the human picks keepers. The swipe is the approval gate.
- On-image text must be a claim the brand can actually make. No invented numbers on the image, ever.
- If the generated set looks like it could belong to any company, regenerate with the brand's verbatim phrases on-image. Generic kills delivery.
Good output looks like
A set of 5-6 images where each one visibly matches a different angle, the brand is recognizable without the logo, and the approved ones are already in the account library with hashes listed.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kelpi-ai
- Source: kelpi-ai/meta-ads-skills
- License: MIT
- Homepage: https://kelpi.ai/skills
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.