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 chibi-collage-effectgit 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/chibi-collage-effect)<a href="https://agentmods.dev/skills/samuraigpt/generative-media-skills/chibi-collage-effect"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/chibi-collage-effect/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/chibi-collage-effect"><img src="https://agentmods.dev/badge/skills/samuraigpt/generative-media-skills/chibi-collage-effect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Data Exfiltration · line 60 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 60 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 | $0.00062 | $0.01189 |
| Opus 5.5 | $0.00025 | $0.00476 |
| Sonnet 5.5 | $0.00012 | $0.00238 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade B, and why
muapi-chibi-collage-effect 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 How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chibi Collage Effect
Turn a real lifestyle photo into a polished "chibi clone sticker diary" image — the original person stays photorealistic, surrounded by 5–8 kawaii chibi mini-clones, scrapbook doodles, and handwritten-style captions that match the scene.
Inputs
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
person_image |
image_url | yes | — | A clear lifestyle photo of the person. Setting, outfit, mood, and activity are read from this image and drive the chibi poses and captions. |
Steps
Phase A — Chibi Collage Generation
If {{person_image}} is not provided, ask the user to upload a lifestyle photo (café, outdoor, cozy at home, travel, etc.). The scene context is what makes the chibi clones feel native to the moment, so a generic studio headshot will give weaker results than a real lifestyle shot.
Once the photo is available, submit the plan with ONE step to generate the chibi collage:
- Chibi Collage Generation —
muapi image edit(model=gpt-image-2-image-to-image):- Reference Image:
{{person_image}} - Image size:
2160x3840(9:16 portrait) — high-resolution social-media-ready output - Background:
auto - Output format:
png - Quality:
auto - Moderation:
low - Prompt:
Create a high-quality "chibi clone sticker diary photo" based on the uploaded real-life image. Preserve the original person's identity, face, hairstyle, hair color, outfit, body proportions, pose, lighting, and background. Do not alter facial features or turn the subject into a full illustration—maintain a realistic photo look. Analyze the uploaded image carefully: identify the setting, mood, activity, clothing style, and overall vibe of the scene. Use this analysis to determine the theme of the chibi stickers, poses, emotions, and text phrases — everything should feel native to the actual moment captured in the photo. Add 5–8 chibi mini clones of the same person around the subject, designed in a consistent kawaii sticker style (big head, small body, large expressive eyes, clean digital finish). Each clone must clearly resemble the real person (same hair, outfit, colors). Design each chibi with different actions and emotions that are directly relevant to what the person is doing or feeling in the photo — inferred naturally from the scene (e.g. if they're at a café: sipping coffee, reading, daydreaming, chatting; if outdoors: exploring, laughing, taking photos; if cozy at home: cuddling, reading, relaxing). Ensure all poses are unique and contextually matched to the image. Render each chibi as a sticker with white outlines, soft shadows, and a slightly floating effect. Arrange them around the subject and edges without covering the face or main body. Add light hand-drawn doodles (hearts, sparkles, arrows, motion lines, circles, stars) in white with subtle pink accents, keeping a clean scrapbook diary feel. Doodle style should complement the mood of the scene. Include 5–8 short handwritten-style phrases that match the mood and context of the uploaded photo — cute, expressive, and scene-appropriate. Use mostly white text with slight pink highlights and small decorative marks. Composition: keep the real person as the central focus, surrounded by chibi stickers and doodles. The result should feel like a polished, playful, high-resolution social media lifestyle diary image — clean, balanced, and visually rich without clutter.
- Reference Image:
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 · 64 lines · 62 tokens per session scan B da36d4ec0280
muapi-chibi-collage-effect is a skill published in the GitHub repository SamurAIGPT/Generative-Media-Skills (25 stars, last pushed 28d ago), licensed MIT. It adds 62 tokens to every session and 1,189 once invoked, about $0.0002 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). 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.