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 product-ad-cinematicgit 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/product-ad-cinematic)<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/product-ad-cinematic"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/product-ad-cinematic/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/product-ad-cinematic"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/product-ad-cinematic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 65 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 77 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 77 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00024 | $0.00843 |
| Opus 5 | $0.00012 | $0.00421 |
| Sonnet 5 | $0.00005 | $0.00169 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade B, and why
muapi-product-ad-cinematic 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 13d 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: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic Product Ad
Cinematic 5–10s product ad from a product photo + brand brief.
Inputs
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
product_image |
image_url | yes | — | URL of the product photo (must already be uploaded). |
brand_brief |
text | yes | — | Mood / style direction (e.g. "luxury minimal", "playful"). |
duration_sec |
int | no | 6 | Final video length in seconds (5–10). |
Steps
This skill has TWO phases separated by a user pick. Submit them as two separate the plan calls — never bundle downstream steps into the first plan.
Phase A — variant exploration (cheap)
Submit ONE the plan containing only:
- Hero frame variants — 4 separate
muapi image generatenodes (model=nano-banana-2, aspect_ratio=16:9 by default).- Each prompt restyles the product against the brand brief mood. Vary lighting, palette, framing, and lens between variants. Keep product geometry intact.
- Reference the user's
product_imageif the model supports image conditioning; otherwise describe the product in detail.
After the plan executes, end your turn with a brief message listing the 4 asset_ids and asking the user which one to take forward (e.g. "Pick a hero (asset_1, asset_2, asset_3, or asset_4)?"). Wait.
Phase B — commit on the picked hero (expensive)
Once the user replies with their pick, submit a SECOND the plan:
- Upscale the picked frame —
enhance_image(operation=upscale). - Animate the upscaled frame —
muapi video from-image(model=kling-v3.0-standard-image-to-video, duration={{duration_sec}}, prompt="slow cinematic push-in, soft volumetric light, subtle product micro-rotation"). Reference the upscale's URL with$nX.url. - Background music —
muapi audio create(kind=music) — runs in parallel with the upscale/animate. Style derived frombrand_brief(luxury → "ambient cinematic, warm strings, slow tempo, instrumental"). Duration ≈ video length. - Return the upscaled hero image and the final video.
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.
- 13d ago First seen · 79 lines · 24 tokens per session scan B 9cb3fa55fa85
muapi-product-ad-cinematic is a skill published in the GitHub repository SamurAIGPT/Generative-Media-Skills (4,263 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 843 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.