Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pbc-os/smb-starter-kitnpx agentmods add skills/pbc-os/smb-starter-kit/creative-matrixWrote 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/pbc-os/smb-starter-kit/creative-matrix)<a href="https://agentmods.dev/skills/pbc-os/smb-starter-kit/creative-matrix"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/creative-matrix/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/pbc-os/smb-starter-kit/creative-matrix"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/creative-matrix.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 | $0.00064 | $0.02184 |
| Opus 5.5 | $0.00026 | $0.00874 |
| Sonnet 5.5 | $0.00013 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
creative-matrix 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Matrix
Overview
Generate a full set of ad creative concepts for any brand using the Creative Multiplication framework by Curtis Howland. The framework produces 27 unique creative concepts by combining 3 messaging angles (Pain Point, Desire, Social Proof) x 3 creative formats (Static, Video, Carousel) x 3 funnel stages (TOF, MOF, BOF). Each concept is distinct enough to avoid auction overlap in Meta's algorithm.
Attribution: The Creative Multiplication framework was created by Curtis Howland, based on $30M+ in Meta ad spend. This skill implements his methodology as published on LinkedIn.
Prerequisites — Asset Generation (Optional)
Brief/copy generation requires no additional tools. Asset generation is optional:
- Static image generation: Requires nano-banana skill (Gemini). Verify:
python3 -c "from google import genai; print('ok')"andGEMINI_API_KEYin environment. Alternatively: fal.ai MCP server (Flux, SDXL) - Transparent product cutouts (for compositing on ad backgrounds): Requires nano-banana's full 4-pass web-asset pipeline (
generate_image.py→edit_image.py→make_transparent.py→pngquant). See nano-banana skill'sreferences/web-asset-workflow.md - Video generation: Requires fal.ai MCP server (Kling, MiniMax, Wan)
- No tools available: Output briefs only — the user or their production team handles asset creation
To detect availability, check if nano-banana scripts are accessible before offering asset generation:
python3 -c "from google import genai; print('nano-banana: ok')"
Workflow
Phase 1: Gather Brand Context
Before generating concepts, collect the following from the user. Ask concisely — do not overwhelm with questions. Prioritize the first three; the rest are helpful but optional.
- Brand/Product — What is the product or service?
- Target Audience — Who is the ideal customer? Demographics, psychographics, pain points.
- Offer — What is the current offer? (discount, bundle, free trial, etc.)
- Product Category Signal — Is the value immediately visible (fashion, jewelry, food) or does the customer need to believe a transformation (skincare, supplements, coaching)? This determines the static vs video weighting.
- Existing Creative Winners — Any ads that have worked well? What angle/format were they?
- Budget Tier — Starter (5-10 concepts), Growth (15-18 concepts), or Full Matrix (all 27).
- Platform Notes — Stories-heavy? Feed-heavy? Reels? This affects format specs.
What ships with it
2 files 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 · 174 lines · 64 tokens per session scan A b9a16215fde7
creative-matrix is a skill published in the GitHub repository pbc-os/smb-starter-kit (10 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 2,184 once invoked, about $0.0003 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-matrix compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| creative-matrixpbc-os/smb-starter-kit | Skill | 10 | 5mo ago | MIT | A | 64 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 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 |