Agent skill

Muapi Media

by davepoon in davepoon/buildwithclaude

Discover current MuAPI image models and run one explicitly confirmed asynchronous image generation request with bounded polling.

MITAuto-check passedMedia & Creative

Install Muapi Media

skills CLI
$ npx skills add davepoon/buildwithclaude --skill muapi-media -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davepoon/buildwithclaude muapi-media --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davepoon/buildwithclaude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/all-skills/skills/muapi-media .claude/skills/muapi-media && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
muapi-media
GitHub stars
3.6k
Token cost
~975 tokens
SKILL.md length
422 words
Files
3 (incl. scripts)
Skills in repo
245
Repo updated
First seen
Licence
MIT

At a glance

Discover current MuAPI image models and run one explicitly confirmed asynchronous image generation request with bounded polling.

  • Works in 3 steps: Discover current image models → Prepare and review parameters → Confirm cost and generate once
  • An agent needs hosted image generation without hard-coding stale model endpoints
  • SKILL.md covers When to use this skill, Setup, Workflow and Safety rules, plus 2 more sections
  • Runs Python scripts from its folder; calls python3; reaches api.muapi.ai; needs MUAPI_API_KEY

What it does

Muapi Media is an agent skill from davepoon/buildwithclaude. Discover current MuAPI image models and run one explicitly confirmed asynchronous image generation request with bounded polling. Use when an agent needs hosted image generation without hard-coding stale model endpoints or request IDs.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/muapi_media.py` and `tests/test_muapi_media.py`).

It sits in Media & Creative, covering Image generation and Async programming. The repository describes itself as: A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw. The licence is MIT.

When your agent uses it

  • An agent needs hosted image generation without hard-coding stale model endpoints
  • Tasks that involve Image generation
  • Tasks that involve Async programming

Example prompts

  • “/muapi-media”

Requirements

  • Python 3
  • A credential in MUAPI_API_KEY
  • Pre-approved tools (allowed-tools): Bash(python3 *)

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Discover current image models
  2. Prepare and review parameters
  3. Confirm cost and generate once

What it can do on your machine

Read from SKILL.md and the folder at commit 10bfc43. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(python3 *)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.muapi.ai

    Also links to:

    • muapi.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MUAPI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Muapi Media loads about 975 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 422 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~975

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from davepoon/buildwithclaude at commit 10bfc43, republished under its MIT licence (© davepoon). 422 words, ~975 tokens.

Download SKILL.mdSave it as .claude/skills/muapi-media/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
muapi-media
description
Discover current MuAPI image models and run one explicitly confirmed asynchronous image generation request with bounded polling. Use when an agent needs hosted image generation without hard-coding stale model endpoints or request IDs.
allowed-tools
Bash(python3 *)
category
media-content

MuAPI Media

Use the bundled scripts/muapi_media.py CLI to discover current MuAPI image models and submit one explicitly confirmed image-generation request. The CLI uses the live catalog's name, category, and already-versioned endpoint fields, then polls the standard prediction result endpoint. It does not assume that the catalog contains an inline request schema; add model-specific fields only from the current model contract.

When to use this skill

  • The user wants to find a current MuAPI image model.
  • An image workflow needs MuAPI's exact model endpoint rather than a remembered alias.
  • The user has explicitly approved a potentially billable image-generation request.
  • An asynchronous MuAPI prediction needs bounded status polling.

This skill covers text-to-image and image-to-image workflows. Do not use it for MuAPI video, audio, 3D, chat, or model-training requests.

Setup

Set the API key in the environment. Never pass it as a CLI argument or commit it:

bash
export MUAPI_API_KEY="your-api-key"

MUAPI_BASE_URL is optional and defaults to https://api.muapi.ai. Use it only for an approved compatible deployment.

Workflow

1. Discover current image models
bash
python3 scripts/muapi_media.py models --category image --query flux

The public catalog currently returns a top-level models array. Image-generation entries use categories such as Text to Image and Image to Image; their endpoint values already include the /api/v1/ prefix. Choose an exact model from this output immediately before generation.

2. Prepare and review parameters
json
{
  "prompt": "A clean product photograph on a neutral background",
  "aspect_ratio": "1:1"
}

Keep only fields supported by the selected model's current request contract. The catalog is a model directory, not a guarantee that every model accepts the same parameters. A prompt is required for this skill.

Show full SKILL.md (178 more words)Show less
3. Confirm cost and generate once
bash
python3 scripts/muapi_media.py generate \
  flux-dev \
  --params-file request.json \
  --confirm-paid

--confirm-paid is mandatory. The CLI sends exactly one generation POST, never retries an ambiguous POST, and polls only GET requests with a finite budget. The model argument may be the catalog model name or its exact /api/v1/... endpoint path.

Use --output to download the first completed artifact without sending the API key to the output host:

bash
python3 scripts/muapi_media.py generate \
  flux-dev \
  --params-file request.json \
  --confirm-paid \
  --output ./muapi-output.png

Safety rules

  • Keep MUAPI_API_KEY server-side and out of logs, prompts, screenshots, and committed files.
  • Never retry a generation POST automatically. Require fresh user confirmation before another paid request.
  • Poll only with GET and stop at --max-polls.
  • Preserve the catalog endpoint path; do not prepend /api/v1/ to an endpoint that already has it.
  • Download only HTTPS output URLs and do not forward the API key to the output host.
  • Require human review for sensitive, regulated, or high-impact content.

Output

Commands write structured JSON to stdout. A successful generation includes the selected model, request ID, terminal status, output URLs, and—when requested—the local artifact path.

Official references

© davepoon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in plugins/all-skills/skills/muapi-media of davepoon/buildwithclaude.

  • SKILL.md
  • scripts/muapi_media.py
  • tests/test_muapi_media.py

Open the folder on GitHubat commit 10bfc43

Compare with similar skills

Muapi Media next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Muapi Media compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Muapi Media this skilldavepoon/buildwithclaude3.6k—~975Automated safety check: PassMIT
Muapi Mediasickn33/agentic-awesome-skills47k1 repos~2.8kAutomated safety check: PassMIT
Routerbase Media Generationaiskillstore/marketplace430—~972Automated safety check: PassNone
Image Generation Gatewayscalesthio/generative-media-skills191—~20kAutomated safety check: PassMIT
Structured Image Generationbytedance/deer-flow83k5 repos~2.9kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT

Similar skills

  • Muapi Media

    sickn33/agentic-awesome-skills

    Generate images and videos with MuAPI's schema-driven asynchronous media API while protecting keys, polling, and output downloads.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    Media & CreativeAuto-check passed
  • Routerbase Media Generation

    aiskillstore/marketplace

    Build image, video, and audio generation workflows on RouterBase.

    430 GitHub stars~972 tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Image Generation Gateways

    calesthio/generative-media-skills

    Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts…

    191 GitHub stars~20k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    83k GitHub starsUsed in 5 repos~2.9k tokens
    Media & CreativeAuto-check passed
  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Canghe Comic

    freestylefly/canghe-skills

    Knowledge comic creator supporting multiple art styles and tones.

    461 GitHub starsUsed in 8 repos~3.2k tokens
    Media & CreativeAuto-check passed

More from davepoon/buildwithclaude

All 245 skills in this repo
  • Qwen Vision

    davepoon/buildwithclaude

    A skill your agent uses when the user asks to "analyze video", "watch this video", "what happens in this video", "describe this clip", "review this footage", "classify these videos", "compare…

    3.6k GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Hard Predict Future

    davepoon/buildwithclaude

    Activate this agent for any future-oriented question that requires deep quantitative analysis, historical precedents, and structured scenario planning.

    3.6k GitHub starsUsed in 1 repo~4.2k tokens
    Auto-check passed
  • iOS Hig Design Guide

    davepoon/buildwithclaude

    Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data.

    3.6k GitHub stars~735 tokensUpdated 2 days ago
    Auto-check passed
  • Video Downloader

    davepoon/buildwithclaude

    Download YouTube videos with customizable quality and format options.

    3.6k GitHub starsUsed in 1 repo~871 tokens
    Auto-check passed
  • Atlas Cloud Media

    davepoon/buildwithclaude

    Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling.

    3.6k GitHub stars~852 tokensUpdated 2 days ago
    Auto-check passed
  • Slack Gif Creator

    davepoon/buildwithclaude

    Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives.

    3.6k GitHub starsUsed in 12 repos~4.3k tokens
    Auto-check passed

Questions about Muapi Media

What does Muapi Media do?

Discover current MuAPI image models and run one explicitly confirmed asynchronous image generation request with bounded polling. Muapi Media is an agent skill from davepoon/buildwithclaude. Discover current MuAPI image models and run one explicitly confirmed asynchronous image generation request with bounded polling.

When should I use Muapi Media?

Muapi Media fits situations like: an agent needs hosted image generation without hard-coding stale model endpoints; tasks that involve Image generation; tasks that involve Async programming.

How do I install Muapi Media in Claude Code?

Run `npx skills add davepoon/buildwithclaude --skill muapi-media -a claude-code`. Or copy the skill folder (plugins/all-skills/skills/muapi-media in davepoon/buildwithclaude) into .claude/skills/muapi-media in your project. Claude Code loads it when a task matches its description.

How do I install Muapi Media in Codex?

Run `npx skills add davepoon/buildwithclaude --skill muapi-media -a codex`. Or copy the skill folder (plugins/all-skills/skills/muapi-media in davepoon/buildwithclaude) into .agents/skills/muapi-media in your project. Codex loads it when a task matches its description.

Can I use Muapi Media in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davepoon/buildwithclaude --skill muapi-media -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/muapi-media, .gemini/skills/muapi-media, .github/skills/muapi-media and .opencode/skills/muapi-media in your project.

What does Muapi Media need to run?

Going by SKILL.md and its folder, Muapi Media needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named MUAPI_API_KEY. Our summary lists: Python 3; A credential in MUAPI_API_KEY. Its frontmatter pre-approves these tools: Bash(python3 *).

Does Muapi Media access the network?

SKILL.md names 2 domains. In commands or code: api.muapi.ai; the agent is likely to contact it when it follows the instructions. As links in the text: muapi.ai. This is read from the text; nothing was executed.

Is Muapi Media safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Muapi Media use?

Muapi Media is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Muapi Media use?

About 975 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Muapi Media?

Skills that share tags, products or a category with Muapi Media: Muapi Media (sickn33/agentic-awesome-skills, 47k stars), Routerbase Media Generation (aiskillstore/marketplace, 430 stars), Image Generation Gateways (calesthio/generative-media-skills, 191 stars) and Structured Image Generation (bytedance/deer-flow, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Muapi Media?

davepoon (a GitHub user) maintains it in davepoon/buildwithclaude, which has 3,604 GitHub stars. The repository holds 245 skills in this directory. The repository was last updated on October 6, 2026.

Source: davepoon/buildwithclaude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.