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 workflowgit 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/workflow)<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/workflow"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/workflow/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/workflow"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01548 |
| Opus 5.5 | $0.00018 | $0.00619 |
| Sonnet 5.5 | $0.00009 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
muapi-workflow 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 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.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Workflow Builder
Chain any combination of muapi.ai generation steps into automated pipelines. The AI architect converts your plain-language description into a runnable node graph.
Prerequisites
Always ensure the muapi CLI is up-to-date before running any commands. Reinstall from source at the start of every session:
pip install --upgrade /path/to/muapi-cli
Replace /path/to/muapi-cli with the actual path to the muapi-cli directory in the workspace (the directory containing pyproject.toml).
Core Operations
- Generate (
generate-workflow.sh) — AI architect creates a workflow from a description - Discover (
discover-workflow.sh) — Find a relevant existing workflow by natural language - Edit (
generate-workflow.sh --workflow-id) — Modify an existing workflow with a prompt - Interactive Run (
interactive-run.sh) — Prompt for inputs and execute a workflow - Run (
run-workflow.sh) — Execute a workflow, poll node-by-node, collect outputs - CLI (
muapi workflow) — Full CRUD + visualization directly from the terminal
Agent Guided Discovery & Selection
As an AI agent, you have the ability to read and understand the purpose of available workflows to select the best one for the user's task (e.g., "create a UGC video").
- Discover: Fetch the catalog of available workflows and their descriptions in JSON format.
muapi workflow discover --output-json - Match (Internal Reasoning): Use your LLM capabilities to analyze the
name,category, anddescriptionfields of the returned workflows. Find the best match for the user's intent. - Analyze: If you find a promising candidate, inspect its structure to ensure it has the necessary nodes and parameters.
CRITICAL RULE: The output ofmuapi workflow get <workflow_id>muapi workflow getwill include an "API Inputs" table. You MUST read this table to understand what inputs are required. - Choose & Confirm & Prompt User:
- If one workflow is a perfect match, you MUST ask the user to provide the exact values for the required API inputs before executing it. Never invent or guess input values (like prompts, URLs, etc.) on your own.
- If multiple workflows are highly relevant, present the options to the user with their descriptions and ask them to confirm which one to use, and also ask for the required inputs.
- If no workflow matches the user's complex request, offer to architect a new one using
muapi workflow create.
What ships with it
5 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.
- 1mo ago First seen · 198 lines · 44 tokens per session scan A 8a0802d97828
muapi-workflow is a skill published in the GitHub repository SamurAIGPT/Generative-Media-Skills (25 stars, last pushed 28d ago), licensed MIT. It adds 44 tokens to every session and 1,548 once invoked, about $0.0002 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 2026-09-03.
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.