Skip to content
cccskills
FreePublished on GitHub

img2mo-std

Standardize a 2D animation baseline image with `/img2mo-std xxx.png/pos`. Use when preparing a character, creature, prop, or weapon baseline before motion generation, especially if the source image is too large, tightly cropped, lacks transparent action margin, has a white background, or later walk/attack/idle frames show clipping, overlap, scale popping, or inconsistent character size.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Img2mo-std

Overview

Use this skill when the user invokes:

/img2mo-std xxx.png/pos

The command audits and standardizes a baseline frame before animation generation. It creates a smaller, padded, transparent-canvas source image that leaves enough room for walk, attack, idle, weapon swing, cape, tail, horn, or limb stretch poses.

Input Resolution

Resolve the argument after /img2mo-std as follows:

  1. If it is an existing relative or absolute path, use it directly.
  2. If it is a bare file name such as s7.png, first try sample\s7.png.
  3. If it has no extension such as s7, first try sample\s7.png, then sample\s7.jpg, then sample\s7.webp.
  4. If no matching image exists, report the missing path and do not guess from unrelated files.

Examples:

/img2mo-std s7
/img2mo-std s7.png
/img2mo-std sample\s7.png
/img2mo-std C:\AI\2dimg2motion-v1\sample\s7.png

Audit Criteria

A baseline is not standard if any of these are true:

  • The foreground subject is larger than about 300-400 px on its longest side.
  • The subject touches or nearly touches the canvas edge.
  • There is not enough empty transparent space for arms, legs, weapons, tails, capes, horns, or effects to extend during motion.
  • The background is opaque white or near-white when the character should be isolated.
  • The source has a huge canvas that will slow generation without adding useful detail.
  • Previous generated frames show inconsistent character size, off-center motion, clipped body parts, or crowded sprite-sheet cells.

Tool

Run the repository tool from the workspace root after resolving the image path:

python scripts\standardize_baseline.py <resolved-image-path>

Default output:

sample\<input-stem>-standard.png

Useful options:

python scripts\standardize_baseline.py sample\s7.png --subject-max 360 --margin-ratio 0.75
python scripts\standardize_baseline.py sample\s7.png --output sample\s7-standard.png
python scripts\standardize_baseline.py sample\s7.png --check-only

Recommended default target:

  • Subject longest side: 360
  • Margin ratio: 0.65 to 0.85
  • Output format: PNG with transparency

Report Interpretation

The tool prints a JSON report. Treat the standardized output as ready when:

  • needs_standardization is false after processing.
  • subject_longest_side is between 300 and 400.
  • edge_clearance_ratio leaves enough room for the intended motion.
  • warnings is empty or only contains acceptable notes.

If the report still warns that the image is tight or too large, rerun with a smaller --subject-max or larger --margin-ratio.

Animation Workflow Rule

After /img2mo-std, use the standardized output image as the baseline for all later walk, attack, idle, or other sprite generation. Do not continue from the original oversized or tightly cropped source unless the user explicitly asks to bypass standardization.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use when a user provides one baseline image and requests game animation frames, sprite sequences, attack/walk/idle/hit/death/casting motion, transparent PNG frames, a spritesheet, keyframe prompts, or consistent whole-character pose animation.

The English summary is being prepared. Showing the original description.

WU-HAOTIAN34/2dimg2motion224Updated Jul 2, 2026

Learn reusable 2D motion-generation knowledge from user-specified action resources with `/img2mo-learn <resource>`. Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style traits, prompt patterns, extraction/cropping rules, or failure lessons into the project `img2mo-knowledge/` folder for later `/img2motion` generation.

The English summary is being prepared. Showing the original description.

WU-HAOTIAN34/2dimg2motion224Updated Jul 2, 2026

See all skills by WU-HAOTIAN34

Report a problem with this skill