Agent skill

Mixing Transforms

by albumentations-team in albumentations-team/AlbumentationsX

Policy for AlbumentationsX transforms that combine multiple images or objects.

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Mixing Transforms

skills CLI

$ npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a claude-code

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

GitHub CLI

$ gh skill install albumentations-team/AlbumentationsX mixing-transforms --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/albumentations-team/AlbumentationsX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/mixing-transforms .claude/skills/mixing-transforms && 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/

Paste into Claude Code

Install the "mixing-transforms" agent skill from https://github.com/albumentations-team/AlbumentationsX/tree/main/.codex/skills/mixing-transforms into .claude/skills/mixing-transforms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixing-transforms", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/albumentations-team/AlbumentationsX/tree/main/.codex/skills/mixing-transforms

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install albumentations-team/AlbumentationsX mixing-transforms --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/albumentations-team/AlbumentationsX.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/mixing-transforms .agents/skills/mixing-transforms && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "mixing-transforms" agent skill from https://github.com/albumentations-team/AlbumentationsX/tree/main/.codex/skills/mixing-transforms into .agents/skills/mixing-transforms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixing-transforms", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install albumentations-team/AlbumentationsX mixing-transforms --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/albumentations-team/AlbumentationsX.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/mixing-transforms .cursor/skills/mixing-transforms && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "mixing-transforms" agent skill from https://github.com/albumentations-team/AlbumentationsX/tree/main/.codex/skills/mixing-transforms into .cursor/skills/mixing-transforms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixing-transforms", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/albumentations-team/AlbumentationsX.git --path .codex/skills/mixing-transforms

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install albumentations-team/AlbumentationsX mixing-transforms --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/albumentations-team/AlbumentationsX.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/mixing-transforms .gemini/skills/mixing-transforms && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "mixing-transforms" agent skill from https://github.com/albumentations-team/AlbumentationsX/tree/main/.codex/skills/mixing-transforms into .gemini/skills/mixing-transforms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixing-transforms", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install albumentations-team/AlbumentationsX mixing-transforms

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/albumentations-team/AlbumentationsX.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/mixing-transforms .github/skills/mixing-transforms && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "mixing-transforms" agent skill from https://github.com/albumentations-team/AlbumentationsX/tree/main/.codex/skills/mixing-transforms into .github/skills/mixing-transforms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixing-transforms", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install albumentations-team/AlbumentationsX mixing-transforms --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/albumentations-team/AlbumentationsX.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/mixing-transforms .opencode/skills/mixing-transforms && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "mixing-transforms" agent skill from https://github.com/albumentations-team/AlbumentationsX/tree/main/.codex/skills/mixing-transforms into .opencode/skills/mixing-transforms/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mixing-transforms", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: mixing-transforms
GitHub stars: 567
Token cost: ~1.3k tokens
SKILL.md length: 382 words
Files: 1
Skills in repo: 10
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Policy for AlbumentationsX transforms that combine multiple images or objects.

Works in 6 steps: The caller owns the donor pool → Metadata format: list[dict] → Label fields: bbox_labels and… → …
OverlayElements
SKILL.md covers 1. The caller owns the donor…, 2. Metadata format: list[dict], 3. Label fields: bbox_labels… and 4. Coordinates use the same…, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mixing Transforms is an agent skill from albumentations-team/AlbumentationsX. Policy for AlbumentationsX transforms that combine multiple images or objects. Use when implementing, reviewing, or using Mosaic, CopyAndPaste, OverlayElements, HistogramMatching, PixelDistributionAdaptation, or other mixing transforms.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Computer vision and Deep learning. The repository describes itself as: Image augmentation for computer vision. AGPL-3.0-only or commercial licensing. The licence is AGPL-3.0.

When your agent uses it

OverlayElements
HistogramMatching
PixelDistributionAdaptation
Other mixing transforms

Example prompts

“/mixing-transforms”

Requirements

Python 3

Workflow steps

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

The caller owns the donor pool
Metadata format: list[dict]
Label fields: bbox_labels and keypoint_labels (dicts)
Coordinates use the same format as BboxParams / KeypointParams
metadata_key pattern
Empty metadata is transform-specific

What it can do on your machine

Read from SKILL.md and the folder at commit 1458043. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mixing Transforms loads about 1.3k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 382 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~64
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from albumentations-team/AlbumentationsX at commit 1458043, republished under its AGPL-3.0 licence (© albumentations-team). 382 words, ~1,250 tokens.

Download SKILL.mdSave it as .claude/skills/mixing-transforms/SKILL.md (or your agent's skills folder).

name: mixing-transforms
description: Policy for AlbumentationsX transforms that combine multiple images or objects. Use when implementing, reviewing, or using Mosaic, CopyAndPaste, OverlayElements, HistogramMatching, PixelDistributionAdaptation, or other mixing transforms.

Mixing Transforms Policy

Apply this skill when implementing, reviewing, or using transforms that combine data from multiple images: Mosaic, CopyAndPaste, OverlayElements, HistogramMatching, PixelDistributionAdaptation, etc.

1. The caller owns the donor pool

The caller supplies donor records under metadata_key; a transform never accesses a dataset, loader, or global donor source. A normal Mosaic call supplies the needed donors, and every valid supplied donor is used.

Mosaic handles caller mistakes deterministically within that pool:

if there are more valid donors than visible cells need, it samples only the surplus away with the invocation's SamplingContext RNG;
if there are fewer, it fills remaining cells by replicating the primary item.

This preserves user control over the candidate set while keeping the public transform usable with an oversized or undersized list.

python

# CORRECT — caller provides candidate donor records
donors = [dataset[random.choice(indices)] for _ in range(n)]
result = transform(image=image, mosaic_metadata=donors)

# INCORRECT — transform reaches into a dataset on its own
result = MosaicWithSampling(dataset=dataset)(image=image)

2. Metadata format: `list[dict]`

All mixing transforms receive auxiliary data as list[dict] under a metadata_key. Each dict is one item (one full image for Mosaic, one object instance for CopyAndPaste). This is consistent across transforms.

python

mosaic_metadata = [
    {"image": img1, "mask": mask1, "bboxes": bboxes1, "bbox_labels": {...}},
    {"image": img2, ...},
]

copy_paste_metadata = [
    {"image": src_img, "mask": obj_mask, "bbox": [x1, y1, x2, y2], "bbox_labels": {"class_id": 3}},
    {"image": src_img, "mask": obj_mask2, "bbox_labels": {"class_id": 7}},
]

3. Label fields: `bbox_labels` and `keypoint_labels` (dicts)

All mixing transforms use the same wrapper dict convention for labels:

bbox_labels: dict[str, Any] — maps each label field name (as declared in BboxParams.label_fields) to its value(s) for this item.
keypoint_labels: dict[str, Any] — maps each label field name (as declared in KeypointParams.label_fields) to its value(s) for this item.

For CopyAndPaste (one object per dict), values are scalars (one bbox, one object):

python

{
    "image": src_image,
    "mask": obj_mask,
    "bbox": [10, 20, 50, 80],  # same coord_format as BboxParams
    "bbox_labels": {
        "class_id": 3,
        "is_crowd": 0,
    },
    "keypoints": [[25, 40]],  # same coord_format as KeypointParams
    "keypoint_labels": {
        "joint_name": "left_eye",
    },
}

For Mosaic (one full image per dict), values are lists — one entry per bbox/keypoint:

python

{
    "image": img,
    "bboxes": [[10, 20, 50, 80], [5, 5, 30, 30]],
    "bbox_labels": {
        "class_id": [3, 7],
        "is_crowd": [0, 1],
    },
    "keypoints": [[25, 40], [60, 70]],
    "keypoint_labels": {
        "joint_name": ["left_eye", "nose"],
    },
}

Key rule: the dict keys in bbox_labels / keypoint_labels must exactly match what is declared in BboxParams(label_fields=[...]) and KeypointParams(label_fields=[...]).

Show full SKILL.md (122 more words)Show less

4. Coordinates use the same format as `BboxParams` / `KeypointParams`

Bboxes and keypoints in metadata dicts must use the same coord_format as declared in Compose. The processor's preprocess() converts them to the internal albumentations format — no manual conversion needed.

python

# BboxParams declared with coord_format='pascal_voc'
# → bboxes in metadata must also be pascal_voc [x_min, y_min, x_max, y_max]
copy_paste_metadata = [
    {"image": img, "mask": m, "bbox": [10, 20, 50, 80], "bbox_labels": {"class_id": 3}},
]

5. `metadata_key` pattern

Every mixing transform exposes metadata_key: str in its constructor and lists it in targets_as_params. This ensures Compose validates that the key is present.

python

@property
def targets_as_params(self) -> list[str]:
    return [self.metadata_key]

6. Empty metadata is transform-specific

Do not impose a universal no-op rule on mixing transforms. CopyAndPaste returns no-op parameters when it has no usable donor. Mosaic instead creates its remaining visible cells from replicated primary data, so empty or missing metadata can still produce a mosaic. State this behavior in the transform's public docstring and test it explicitly.

python

# CopyAndPaste: no donor means no change.
if not usable_donors:
    return self._no_op_params()

# Mosaic: remaining cells use copies of the primary item.
final_items = [primary, *usable_donors, *replicated_primary_items]

Files

Just SKILL.md in .codex/skills/mixing-transforms of albumentations-team/AlbumentationsX.

Open the folder on GitHubat commit 1458043

Compare with similar skills

Mixing Transforms 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.

Mixing Transforms compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Mixing Transforms this skillalbumentations-team/AlbumentationsX	567	—	~1.3k	Automated safety check: Pass	AGPL-3.0	yesterday
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs	13k	9 repos	~3.3k	Automated safety check: Pass	MIT	3 mo ago
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs	13k	8 repos	~1.7k	Automated safety check: Pass	MIT	3 mo ago
Kaiming HeK-Dense-AI/mimeo	282	—	~1.6k	Automated safety check: Pass	MIT	1 mo ago
Matlab Analyze Spectral Imagesmatlab/matlab-agentic-toolkit	1.1k	—	~3.7k	Automated safety check: Pass	Custom licence	yesterday
Matlab Process Imagesmatlab/matlab-agentic-toolkit	1.1k	—	~3.7k	Automated safety check: Pass	Custom licence	yesterday

Similar skills

Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
13k GitHub starsUsed in 9 repos~3.3k tokens
AI & LLM EngineeringAuto-check passed
CLIP Image-Text Matching
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
13k GitHub starsUsed in 8 repos~1.7k tokens
AI & LLM EngineeringAuto-check passed
Kaiming He
K-Dense-AI/mimeo
Applies the reasoning style of Kaiming He, computer vision pioneer and creator of ResNet.
282 GitHub stars~1.6k tokensUpdated 1 mo ago
AI & LLM EngineeringAuto-check passed
Matlab Analyze Spectral Images
matlab/matlab-agentic-toolkit
Work with hyperspectral and multispectral images in MATLAB. An agent skill from matlab/matlab-agentic-toolkit.
1.1k GitHub stars~3.7k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Matlab Process Images
matlab/matlab-agentic-toolkit
Load this first for any task involving images, pictures, photos, scans, frames, volumes, or visual data — including reading, writing, filtering, enhancing, denoising, sharpening, deblurring…
1.1k GitHub stars~3.7k tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Scholar Compute
joshzyj/open-scholar-skill
Design and execute computational social science analyses across 11 modules: text-as-data/NLP (STM, BERTopic, Wordfish, BERT, conText embedding regression, LLM annotation + DSL bias correction…
168 GitHub stars~15k tokensUpdated 20 days ago
AI & LLM EngineeringAuto-check passed

Questions about Mixing Transforms

What does Mixing Transforms do?

Policy for AlbumentationsX transforms that combine multiple images or objects. Mixing Transforms is an agent skill from albumentations-team/AlbumentationsX. Policy for AlbumentationsX transforms that combine multiple images or objects.

When should I use Mixing Transforms?

Mixing Transforms fits situations like: overlayElements; histogramMatching; pixelDistributionAdaptation; other mixing transforms.

How do I install Mixing Transforms in Claude Code?

Run `npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a claude-code`. Or copy the skill folder (.codex/skills/mixing-transforms in albumentations-team/AlbumentationsX) into .claude/skills/mixing-transforms in your project. Claude Code loads it when a task matches its description.

How do I install Mixing Transforms in Codex?

Run `npx skills add albumentations-team/AlbumentationsX --skill mixing-transforms -a codex`. Or copy the skill folder (.codex/skills/mixing-transforms in albumentations-team/AlbumentationsX) into .agents/skills/mixing-transforms in your project. Codex loads it when a task matches its description.

Can I use Mixing Transforms 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 albumentations-team/AlbumentationsX --skill mixing-transforms -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mixing-transforms, .gemini/skills/mixing-transforms, .github/skills/mixing-transforms and .opencode/skills/mixing-transforms in your project.

What does Mixing Transforms need to run?

SKILL.md names no scripts, command-line tools or credentials: Mixing Transforms is instructions for the agent only. Our summary lists: Python 3.

Does Mixing Transforms access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Mixing Transforms 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. Review the folder before installing.

What licence does Mixing Transforms use?

Mixing Transforms is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mixing Transforms use?

About 1.3k tokens (SKILL.md is roughly 5k 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 Mixing Transforms?

Skills that share tags, products or a category with Mixing Transforms: Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars), Kaiming He (K-Dense-AI/mimeo, 282 stars) and Matlab Analyze Spectral Images (matlab/matlab-agentic-toolkit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mixing Transforms?

albumentations-team (a GitHub organization) maintains it in albumentations-team/AlbumentationsX, which has 567 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Mixing Transforms

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Mixing Transforms Policy

1. The caller owns the donor pool

2. Metadata format: list[dict]

3. Label fields: bbox_labels and keypoint_labels (dicts)

4. Coordinates use the same format as BboxParams / KeypointParams

5. metadata_key pattern

6. Empty metadata is transform-specific

Files

Compare with similar skills

Similar skills

More from albumentations-team/AlbumentationsX

Related

Questions about Mixing Transforms

2. Metadata format: `list[dict]`

3. Label fields: `bbox_labels` and `keypoint_labels` (dicts)

4. Coordinates use the same format as `BboxParams` / `KeypointParams`

5. `metadata_key` pattern