An image- and video-generation skill that uses Krea AI from slash commands such as /krea.

Use it to generate images or short videos, search available visual styles, or check an existing generation job.

It gives coding agents a defined way to request visual content and check the status of longer-running generations.

How keugenek/krea-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to keugenek/krea-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/keugenek/krea-mcp/main/.claude/skills/krea/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/keugenek/krea-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/keugenek/krea-mcp/krea/github.svg)](https://agentmods.dev/skills/keugenek/krea-mcp/krea)

Your own site

<a href="https://agentmods.dev/skills/keugenek/krea-mcp/krea"><img src="https://agentmods.dev/badge/skills/keugenek/krea-mcp/krea/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/keugenek/krea-mcp/krea"><img src="https://agentmods.dev/badge/skills/keugenek/krea-mcp/krea.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00035	$0.00590
Opus 5	$0.00017	$0.00295
Sonnet 5	$0.00007	$0.00118
Haiku 4.5	$0.00003	$0.00059

Measured 11d ago against content hash 84e3451fdf32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

krea 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 11d 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.

.claude/skills/krea/SKILL.md · 84 lines

What it actually says

Krea AI Generation

Generate images and videos using the Krea MCP server.

Usage

/krea [prompt] - Generate an image with the given prompt /krea video [prompt] - Generate a video with the given prompt /krea status [job_id] - Check generation status /krea styles [query] - Search for styles

Commands

Based on $ARGUMENTS, perform the appropriate action:

Image Generation (default)

If no specific command prefix, generate an image:

Use the generate_image tool with:
- prompt: the user's description
- model: "flux-dev" (or user-specified)
- width/height: 1024x1024 (or user-specified)

Video Generation

If arguments start with "video":

Use the generate_video tool with:
- prompt: the description after "video"
- model: "hailuo" (or user-specified)
- duration: 5 seconds (or user-specified)

Job Status

If arguments start with "status":

Use the get_job tool with the job_id

Style Search

If arguments start with "styles" or "style":

Use the search_styles tool with the query

Response Format

After calling the Krea tool:

For generations: Report the job ID and explain that generations are async. Offer to check status.
For job status: Show the status and include result URLs if completed.
For style search: List available styles with their IDs.

Available Models

Image Models

flux-dev (default) - High quality, balanced
flux-pro - Highest quality
flux-schnell - Fast generation
ideogram-v2 - Great for text in images
imagen-4 - Google's latest
krea-1 - Krea's custom model

Video Models

hailuo (default) - High quality video
kling-1.6 - Detailed motion
runway-gen4 - Cinematic quality
pika-2 - Creative styles
veo-3 - Google's video model

Examples

/krea a cyberpunk cityscape at night with neon lights
/krea video a cat playing with yarn in slow motion
/krea status job_abc123
/krea styles anime

Files

What ships with it

1 file 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.

reference.md 2.0 KB

Changes

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.

11d ago First seen · 84 lines · 35 tokens per session scan A 84e3451fdf32

Subscribe to this mod's changes

krea is a skill published in the GitHub repository keugenek/krea-mcp (9 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 590 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Creative and media ai ai-tools anthropic claude flux generative-ai

image-generate

Transform descriptions into ultra-detailed prompts, then generate real images via the image generation server. Supports custom types, styles, moods, lighting, and composition with optional sub-agent delegation.

prenats/claude-imagine · 40 tokens

image-suggest

Analyze project structure and visual needs, then recommend a prioritized list of images to generate. Optionally generates all suggestions using the image generation workflow.

prenats/claude-imagine · 32 tokens

flux-3-product-ads

Use when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped audio, floating products, off-model plates, and reports that claim a pass the build did not give.

black-forest-labs/skills · 66 tokens

idea-generator

Brainstorm and rank iOS/macOS app ideas tailored to developer skills. Use when user says "what should I build", "give me app ideas", "I don't know what to build", "brainstorm app ideas", or "help me find an app idea".

rshankras/claude-code-apple-skills · 57 tokens

milestone-celebration

Generates achievement celebration UI with confetti animations, badge unlocks, progress milestones, haptic feedback, and optional share-to-social. Use when user wants to celebrate achievements, show confetti, display milestone badges, or trigger rewards on key thresholds.