MiniMax GIF Sticker Maker

Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions. Use when: user wants to create cartoon stickers, GIF expressions, e...

Security Scan

The skill's runtime instructions expect an external MiniMax API key and several local scripts/assets that are not present in the package manifest, creating inconsistencies and privacy risks (photo uploads) that should be resolved before use.

Purpose & Capability

The stated purpose (convert photos to GIF stickers using MiniMax APIs) is coherent with requiring an API key and video/GIF tooling. However the registry metadata claims no required env vars or code files, while SKILL.md explicitly requires MINIMAX_API_KEY, local scripts (scripts/minimax_image.py, scripts/minimax_video.py, scripts/convert_mp4_to_gif.py), and asset/reference files. Those files are not included in the package, which is an inconsistency: either the skill is missing required code or the instructions are assuming an environment the registrar didn't declare.

Instruction Scope

SKILL.md directs the agent to analyze user photos, preserve facial likeness for persons via a '--subject-ref' to the remote API, and upload images to MiniMax image/video generation endpoints. This is expected for an image-generation tool but raises privacy and consent concerns (facial likeness/uploading user photos). The instructions also require reading local reference files (captions.md, prompt templates) and strict machine-parsable deliverables (<deliver_assets> block). The skill demands files and concurrency behavior that are not present in the published bundle, widening the scope unexpectedly.

Install Mechanism

There is no install spec (instruction-only), which is low-risk in general — but SKILL.md expects a Python venv, requirements.txt, and ffmpeg on PATH plus local scripts/assets. Because no code files or install steps are provided, the instructions can't be executed as-is. The missing install/code artifacts are a significant operational incoherence (either the package is incomplete or it assumes an environment not declared).

Credentials

The only credential the instructions require is MINIMAX_API_KEY, which is proportionate to calling the MiniMax APIs. However, the registry metadata incorrectly lists no required env vars, so there's a mismatch between declared and actual credential needs. The skill also expects system tools (ffmpeg) and a Python environment; those are reasonable but should have been declared. No unrelated credentials are requested.

Persistence & Privilege

The skill does not request always: true and does not ask to modify other skills or system-wide settings. Autonomous invocation is allowed (platform default) but is not combined with broad or unexplained privileges here.

What to consider before installing

Before installing or running this skill, consider the following: - Inconsistency: The manifest lists no environment variables or code files, but SKILL.md requires MINIMAX_API_KEY and several local scripts and asset files. Verify the package actually includes scripts/*, assets/*, references/* and requirements.txt or obtain them from a trusted source before running. - Privacy: The workflow explicitly uploads user photos (and for people instructs preserving facial likeness). Only proceed if you have the user's informed consent and you trust the MiniMax service (review its privacy policy and data retention rules). Avoid uploading sensitive photos or faces without explicit permission. - Credential safety: Do not provide your MiniMax API key unless you trust the publisher and have inspected the scripts that will use it. Ideally inspect scripts/minimax_*.py to confirm they call only the expected endpoints and do not exfiltrate other data. - Missing install instructions: The skill expects a Python virtualenv and ffmpeg. Install those from official sources and inspect requirements.txt before pip-installing dependencies. - Output formatting rule: The SKILL.md requires a strict <deliver_assets> block and forbids any text after it. This could hide status or error information — make sure you understand how the agent will report errors and verify outputs on disk. - Operational impact: The instructions ask to run four generation jobs concurrently; this can consume significant CPU/memory and count against any API rate limits or billing on the MiniMax account. If you cannot verify the missing scripts/assets and the API endpoint behavior, treat this skill as incomplete and do not provide credentials or sensitive images. If you want to proceed, request the publisher supply the missing files and a clear install script, then audit those files before use.

GIF Sticker Maker

Convert user photos into 4 animated GIF stickers (Funko Pop / Pop Mart style).

Style Spec

• Funko Pop / Pop Mart blind box 3D figurine
• C4D / Octane rendering quality
• White background, soft studio lighting
• Caption: black text + white outline, bottom of image

Prerequisites

Before starting any generation step, ensure:

1. Python venv is activated with dependencies from requirements.txt installed
2. MINIMAX_API_KEY is exported (e.g. export MINIMAX_API_KEY='your-key')
3. ffmpeg is available on PATH (for Step 3 GIF conversion)

If any prerequisite is missing, set it up first. Do NOT proceed to generation without all three.

Workflow

Step 0: Collect Captions

Ask user (in their language):

"Would you like to customize the captions for your stickers, or use the defaults?"

• Custom: Collect 4 short captions (1–3 words). Actions auto-match caption meaning.
• Default: Look up captions table by detected user language. Never mix languages.

Step 1: Generate 4 Static Sticker Images

Tool: scripts/minimax_image.py

1. Analyze the user's photo — identify subject type (person / animal / object / logo).
2. For each of the 4 stickers, build a prompt from image-prompt-template.txt by filling {action} and {caption}.
3. If subject is a person: pass --subject-ref <user_photo_path> so the generated figurine preserves the person's actual facial likeness.
4. Generate (all 4 are independent — run concurrently):

python3 scripts/minimax_image.py "<prompt>" -o output/sticker_hi.png --ratio 1:1 --subject-ref <photo>
python3 scripts/minimax_image.py "<prompt>" -o output/sticker_laugh.png --ratio 1:1 --subject-ref <photo>
python3 scripts/minimax_image.py "<prompt>" -o output/sticker_cry.png --ratio 1:1 --subject-ref <photo>
python3 scripts/minimax_image.py "<prompt>" -o output/sticker_love.png --ratio 1:1 --subject-ref <photo>

--subject-ref only works for person subjects (API limitation: type=character). For animals/objects/logos, omit the flag and rely on text description.

Step 2: Animate Each Image → Video

Tool: scripts/minimax_video.py with --image flag (image-to-video mode)

For each sticker image, build a prompt from video-prompt-template.txt, then:

python3 scripts/minimax_video.py "<prompt>" --image output/sticker_hi.png -o output/sticker_hi.mp4
python3 scripts/minimax_video.py "<prompt>" --image output/sticker_laugh.png -o output/sticker_laugh.mp4
python3 scripts/minimax_video.py "<prompt>" --image output/sticker_cry.png -o output/sticker_cry.mp4
python3 scripts/minimax_video.py "<prompt>" --image output/sticker_love.png -o output/sticker_love.mp4

All 4 calls are independent — run concurrently.

Step 3: Convert Videos → GIF

Tool: scripts/convert_mp4_to_gif.py

python3 scripts/convert_mp4_to_gif.py output/sticker_hi.mp4 output/sticker_laugh.mp4 output/sticker_cry.mp4 output/sticker_love.mp4

Outputs GIF files alongside each MP4 (e.g. sticker_hi.gif).

Step 4: Deliver

Output format (strict order):

1. Brief status line (e.g. "4 stickers created:")
2. <deliver_assets> block with all GIF files
3. NO text after deliver_assets

<deliver_assets>
<item><path>output/sticker_hi.gif</path></item>
<item><path>output/sticker_laugh.gif</path></item>
<item><path>output/sticker_cry.gif</path></item>
<item><path>output/sticker_love.gif</path></item>
</deliver_assets>

Default Actions

#	Action	Filename ID	Animation
1	Happy waving	hi	Wave hand, slight head tilt
2	Laughing hard	laugh	Shake with laughter, eyes squint
3	Crying tears	cry	Tears stream, body trembles
4	Heart gesture	love	Heart hands, eyes sparkle

See references/captions.md for multilingual caption defaults.

Rules

• Detect user's language, all outputs follow it
• Captions MUST come from captions.md matching user's language column — never mix languages
• All image prompts must be in English regardless of user language (only caption text is localized)
• <deliver_assets> must be LAST in response, no text after