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 kelpi-ai/meta-ads-skills --skill creative-directorgit clone --depth 1 https://github.com/kelpi-ai/meta-ads-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/kelpi-ai/meta-ads-skills/creative-director)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/creative-director"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/creative-director/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/kelpi-ai/meta-ads-skills/creative-director"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/creative-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.00467 |
| Opus 5.5 | $0.00014 | $0.00187 |
| Sonnet 5.5 | $0.00007 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
creative-director 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 2mo 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.
What it actually says
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.
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.
- 2mo ago First seen · 33 lines · 34 tokens per session scan A 11eabf9f7ef3
creative-director is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 467 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
creative-director compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| creative-directorkelpi-ai/meta-ads-skills | Skill | 5 | 4mo ago | MIT | A | 34 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |