New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Review Transform

by albumentations-team in albumentations-team/AlbumentationsX

Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage.

AGPL-3.0Auto-check passedAI & LLM Engineering

Install Review Transform

skills CLI
$ npx skills add albumentations-team/AlbumentationsX --skill review-transform -a claude-code

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

GitHub CLI
$ gh skill install albumentations-team/AlbumentationsX review-transform --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/review-transform .claude/skills/review-transform && 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
review-transform
GitHub stars
567
Token cost
~973 tokens
SKILL.md length
423 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage.

  • Tasks that involve Computer vision
  • SKILL.md covers Correctness and API, Sampling and replay, Performance and Documentation and tests, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Test coverage

What it does

Review Transform is an agent skill from albumentations-team/AlbumentationsX. Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage.

Its SKILL.md is about 970 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, Test coverage and Deep learning. It works with NumPy. 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

  • Tasks that involve Computer vision
  • Tasks that involve Test coverage
  • Tasks that involve Deep learning

Example prompts

  • “/review-transform”

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.

    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

Review Transform loads about 973 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 423 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~973

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). 423 words, ~973 tokens.

Download SKILL.mdSave it as .claude/skills/review-transform/SKILL.md (or your agent's skills folder).
name
review-transform
description
Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage.

Review a transform

Start with pre-commit run check-ax-rules --all-files. Report failing diagnostics with their rule and location. The hook and Coding Guidelines own deterministic source contracts. Then review the behavior the hook cannot prove.

Correctness and API

  • Check the public Targets: docstring, effective _targets, and active dispatch as one contract. Inherited working handlers count; stubs do not. images and masks require their own declarations, and user_data is active only for a custom transform that explicitly declares and implements it. See Generated Transform Target Contracts.
  • When frame-aligned annotations are involved, review the binding configuration and supported data shape in Instance and Frame Binding; do not infer frame ownership from collection lengths alone.
  • Check the mathematical operation, coordinate boundaries, dtype range, and annotation semantics.
  • Verify that constructor fields, validators, and defaults express a coherent public policy.
  • Check empty inputs, ownership, aliasing, and unsupported input handling through the public route.
  • Distinguish public grayscale inputs from internal execution: Compose normalizes NumPy inputs to explicit channels before dispatch. Use NumPy and Tensor routing for boundary changes.
  • Take bbox type from BboxParams.bbox_type, never column count. Convert OpenCV rotated rectangles through cv2.boxPoints and polygons_to_obb.
  • Remove unreachable code and unused helpers after checking external callers and inherited dispatch.

Sampling and replay

Use Applied Configuration Replay Contracts when reviewing constructor serialization, applied configuration, or ReplayCompose.

  • Identify what is sampled per invocation and which constructor fields remain policy.
  • Check target prerequisites, deterministic sampling, and representation-dependent parameters.
  • Verify that applied configuration records realized constructor values and clears conflicting source policy fields.
  • Claim exact replay only when the recorded configuration captures every output-changing random value.
  • Reconstruct through the public API and execute on fresh equivalent data without mutating caller-owned inputs.
Show full SKILL.md (145 more words)Show less

Performance

Read Performance Optimization and its required reference before inspecting runtime code. Tie each proposed optimization to an affected route and a measurement. Consider removable work, existing Albucore primitives, allocation and conversion costs, and setup that can be shared across a batch.

Documentation and tests

Use Public docstring review for reader-facing quality and Generated Transform Target Contracts for coverage.

  • Register each public constructor mode, including mutually exclusive behavior.
  • Derive target-profile applicability from declared capabilities and prerequisites.
  • Keep focused tests for semantic properties the generated profiles cannot express.
  • Check strict JSON transport, public reconstruction, fresh-data execution, and the declared replay strength.

Report

For each finding, give severity, file and line, the affected public behavior, and evidence that demonstrates the issue. Distinguish confirmed defects from benchmark hypotheses or design decisions. Report checks actually run and any unresolved validation limits. If there are no actionable findings, say so.

© albumentations-team, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .codex/skills/review-transform of albumentations-team/AlbumentationsX.

Open the folder on GitHubat commit 1458043

Compare with similar skills

Review Transform 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.

Review Transform compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Transform this skillalbumentations-team/AlbumentationsX567—~973Automated safety check: PassAGPL-3.0
GPU OptimizerMathews-Tom/armory328—~3.5kAutomated safety check: NotesMIT
Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs13k8 repos~3.3kAutomated safety check: PassMIT
CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs13k7 repos~1.7kAutomated safety check: PassMIT
Image Matcher IntegrationVincentqyw/image-matching-webui1.3k—~4.8kAutomated safety check: PassApache-2.0
Neuron Nki Writinguw-syfi/vibesys103—~5kAutomated safety check: PassMIT

Similar skills

  • GPU Optimizer

    Mathews-Tom/armory

    GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile.

    328 GitHub stars~3.5k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check: notes

  • 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 8 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 7 repos~1.7k tokens
    AI & LLM EngineeringAuto-check passed

  • Image Matcher Integration

    Vincentqyw/image-matching-webui

    Adds a new local feature matching model from a GitHub repository to the image-matching-webui project as a working WebUI option.

    1.3k GitHub stars~4.8k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Neuron Nki Writing

    uw-syfi/vibesys

    Guide for writing and modifying NKI kernels. An agent skill from uw-syfi/vibesys.

    103 GitHub stars~5k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Torch Performance Optimization

    albumentations-team/albucore

    Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.

    123 GitHub stars~895 tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

More from albumentations-team/AlbumentationsX

All 10 skills in this repo

  • Mixing Transforms

    albumentations-team/AlbumentationsX

    Policy for AlbumentationsX transforms that combine multiple images or objects.

    567 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Release Notes

    albumentations-team/AlbumentationsX

    Generate release notes for AlbumentationsX. An agent skill from albumentations-team/AlbumentationsX.

    567 GitHub stars~685 tokensUpdated today
    Auto-check passed

  • Performance Optimization

    albumentations-team/AlbumentationsX

    Systematic performance audit for AlbumentationsX runtime code.

    567 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Add Transform

    albumentations-team/AlbumentationsX

    Full checklist for adding a new transform to AlbumentationsX.

    567 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Docstring Deep Dive

    albumentations-team/AlbumentationsX

    Review public AlbumentationsX docstrings for useful descriptions, runnable examples, parameter semantics, and related transforms.

    567 GitHub stars~534 tokensUpdated today
    Auto-check passed

  • License Integrity

    albumentations-team/AlbumentationsX

    Maintain AlbumentationsX license, CLA, provenance notices, and packaged legal artifacts consistently.

    567 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Review Transform

What does Review Transform do?

Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage. Review Transform is an agent skill from albumentations-team/AlbumentationsX. Review an AlbumentationsX transform for correctness, public API coherence, performance, documentation, and test coverage.

When should I use Review Transform?

Review Transform fits situations like: tasks that involve Computer vision; tasks that involve Test coverage; tasks that involve Deep learning.

How do I install Review Transform in Claude Code?

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

How do I install Review Transform in Codex?

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

Can I use Review Transform 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 review-transform -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-transform, .gemini/skills/review-transform, .github/skills/review-transform and .opencode/skills/review-transform in your project.

What does Review Transform need to run?

SKILL.md names no scripts, command-line tools or credentials: Review Transform is instructions for the agent only.

Does Review Transform 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 Review Transform 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 Review Transform use?

Review Transform 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 Review Transform use?

About 973 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 Review Transform?

Skills that share tags, products or a category with Review Transform: GPU Optimizer (Mathews-Tom/armory, 328 stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Image Matcher Integration (Vincentqyw/image-matching-webui, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Transform?

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 9, 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.