Generative-Media-Skills is a toolkit that lets AI agents generate, edit, and display images, videos, and audio through the muapi command-line interface. It is for users of Claude Code, Cursor, Gemini CLI, and OpenCode who need multimodal media-generation workflows. The catalogue entries are the skills that expose these media capabilities to coding agents.
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 SamurAIGPT/Generative-Media-Skills --skill ad-creativegit clone --depth 1 https://github.com/SamurAIGPT/Generative-Media-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/samuraigpt/generative-media-skills/ad-creative)<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/ad-creative"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/ad-creative/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/samuraigpt/generative-media-skills/ad-creative"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/ad-creative.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 | $0.00037 | $0.01018 |
| Opus 5.5 | $0.00015 | $0.00407 |
| Sonnet 5.5 | $0.00007 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade B, and why
muapi-ad-creative scanned grade B with 2 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 1mo 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with This is a copy
100% identical to muapi-ad-creative — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Creative Set
Generate a high-converting ad creative set — hero image, ad copy variations, and platform-optimized crops for Meta, Google Display, and LinkedIn.
Inputs
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
product_or_service |
text | yes | — | What is being advertised (e.g. "SaaS project management tool for remote teams"). |
target_audience |
text | yes | — | Who the ad is for (e.g. "startup founders aged 25–40, tech-savvy"). |
campaign_goal |
text | no | awareness | Campaign objective — "awareness", "consideration", or "conversion". |
tone |
text | no | professional, clean, modern | Creative tone and visual style (e.g. "bold and disruptive", "luxury minimal", "friendly and approachable"). |
product_image |
image_url | no | — | Optional product or brand image URL already in the session. |
Steps
This skill has TWO phases. Phase A creates the hero concept for approval; Phase B fans out to platform formats.
Phase A — Hero image + Ad copy
Submit ONE the plan with:
- Hero image —
muapi image generate(model=nano-banana-pro) ormuapi image edit(model=nano-banana-pro-edit) if{{product_image}}is provided:- Aspect ratio: 1:1 (universal starting point).
- Prompt must capture: product/service benefit, target audience lifestyle cue, campaign tone.
- Style:
{{tone}}, advertising photography, clean background, product focus, ultra detailed, commercial quality. - Tier: quality.
After the plan executes, present the hero asset and 3 ad copy variations:
- Variation A — Problem-aware hook: "Tired of X? [Product] fixes that."
- Variation B — Benefit-led: "[Feature] → [Outcome] for [Audience]."
- Variation C — Social proof / urgency: "X teams already use [Product]." Each variation includes: Headline (6 words max), Body (20–30 words), CTA button text.
Ask which copy variation to use for Phase B. Wait for user confirmation.
Phase B — Platform crops
Once the user picks a copy direction, submit a SECOND the plan with parallel crops:
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.
- 1mo ago First seen · 80 lines · 37 tokens per session scan B c2310ee46ac3
muapi-ad-creative is a skill published in the GitHub repository SamurAIGPT/Generative-Media-Skills (25 stars, last pushed 28d ago), licensed MIT. It adds 37 tokens to every session and 1,018 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 100% identical to muapi-ad-creative, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
mlops-automation
Automate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking on a SQL backend. Use when adding a task runner, git hooks, CI/CD, or experiment tracking to a working package.
mlops-validation
Add the validation layers that gate a merge — ty typing, Ruff linting, pytest coverage, structured logging, and the trivy, pip-audit, and gitleaks scans. Use when hardening code quality or wiring the mise run check task.
mlops-prototyping
Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.
mlops-collaboration
Prepare a project for public collaboration — license, code of conduct, docs, branch rulesets, templates, and git-cliff releases. Use when open-sourcing a repository, onboarding contributors, or cutting a tagged release.
mlops-observability
Make an ML system a glass box with reproducible runs, MLflow dataset lineage, drift monitoring, alerting, and SHAP explanations. Use when a deployed model needs traceability, monitoring, alerting, or explanation.
mlops-industrialization
Convert notebook prototypes into a distributable Python package with a src layout, a domain/io/application split, and validated OmegaConf plus Pydantic configuration. Use when moving code out of notebooks or designing entrypoints.