Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
A skill your agent uses when building, combining, or debugging imgaug image augmentation pipelines, augmenter families, or deterministic image-only transforms.
Install Augmentation Pipelines
$ npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentation-pipelines --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines .claude/skills/augmentation-pipelines && rm -rf skills-srcUse ~/.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/
Install the "augmentation-pipelines" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines into .claude/skills/augmentation-pipelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentation-pipelines", 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 install https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelinesType 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.
$ npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentation-pipelines --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines .agents/skills/augmentation-pipelines && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "augmentation-pipelines" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines into .agents/skills/augmentation-pipelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentation-pipelines", 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.
$ npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentation-pipelines --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines .cursor/skills/augmentation-pipelines && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "augmentation-pipelines" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines into .cursor/skills/augmentation-pipelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentation-pipelines", 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 https://github.com/VectorSpaceLab/AREX-Skill.git --path skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentation-pipelines --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines .gemini/skills/augmentation-pipelines && rm -rf skills-srcUse ~/.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/
Install the "augmentation-pipelines" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines into .gemini/skills/augmentation-pipelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentation-pipelines", 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.
$ gh skill install VectorSpaceLab/AREX-Skill augmentation-pipelinesInstalls 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).
$ npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines .github/skills/augmentation-pipelines && rm -rf skills-srcUse ~/.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/
Install the "augmentation-pipelines" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines into .github/skills/augmentation-pipelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentation-pipelines", 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.
$ npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentation-pipelines --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines .opencode/skills/augmentation-pipelines && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "augmentation-pipelines" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines into .opencode/skills/augmentation-pipelines/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentation-pipelines", 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
augmentation-pipelines- GitHub stars
- 328
- Token cost
- ~1.3k tokens
- SKILL.md length
- 465 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when building, combining, or debugging imgaug image augmentation pipelines, augmenter families, or deterministic image-only transforms.
- Works in 4 steps: Read references/pipeline-workflows.md… → Read… → Run… → …
- Debugging imgaug image augmentation pipelines
- SKILL.md covers What this sub-skill covers, What it does not cover, Typical triggers and Fast path, plus 4 more sections
- Runs Python scripts from its folder
What it does
Augmentation Pipelines is an agent skill from VectorSpaceLab/AREX-Skill. Use when building, combining, or debugging imgaug image augmentation pipelines, augmenter families, or deterministic image-only transforms.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/augmenter-family-reference.md`, `references/pipeline-workflows.md` and `references/troubleshooting.md`).
It sits in Development. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is MIT.
When your agent uses it
- Debugging imgaug image augmentation pipelines
- Augmenter families
- Deterministic image-only transforms
Example prompts
- “/augmentation-pipelines”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Read references/pipeline-workflows.md for the minimal image-pipeline recipes.
- Read references/augmenter-family-reference.md for family selection and parameter defaults.
- Run scripts/generate_augmentation_contact_sheet.py when you need a safe contact sheet or a tiny visual smoke.
- Read references/troubleshooting.md if the pipeline gives unexpected shapes, dtypes, or color results.
What it can do on your machine
Read from SKILL.md and the folder at commit ac3fe1a. 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
Ships 1 file in scripts/ (Python), which the agent can run.
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
Augmentation Pipelines loads about 1.3k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 465 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from VectorSpaceLab/AREX-Skill at commit ac3fe1a, republished under its MIT licence (© VectorSpaceLab). 465 words, ~1,250 tokens.
Download SKILL.mdSave it as
.claude/skills/augmentation-pipelines/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- augmentation-pipelines
- description
- Use when building, combining, or debugging imgaug image augmentation pipelines, augmenter families, or deterministic image-only transforms.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- MIT
Augmentation Pipelines
Use this sub-skill when the task is about image augmentation pipelines in imgaug: choosing augmenter families, composing them with Sequential/SomeOf/OneOf/Sometimes, applying transforms deterministically, or debugging image-only augmentation behavior.
What this sub-skill covers
- Pipeline composition with
iaa.Sequential,iaa.SomeOf,iaa.OneOf,iaa.Sometimes, andiaa.WithChannels. - Image-only use of common augmenter families: affine/geometric, crop/pad/resize, blur, arithmetic/noise, color, contrast, blend/overlay, segmentation/superpixels, weather, PIL-like effects, and
imgcorruptlikewhen installed. - Deterministic pipeline reuse with
to_deterministic(). - Basic image input/output conventions: NHWC arrays, RGB order,
uint8expectations, and shape preservation whenkeep_size=True. - Safe visualization and contact-sheet generation via bundled helpers.
What it does not cover
- Annotation object construction and batch normalization details belong to
../augmentables-and-batches/SKILL.md. - Random seed, stochastic parameter, dtype, and sample-data details belong to
../parameters-random-and-utilities/SKILL.md. - Background multiprocessing and
Poolbehavior belong to../multicore-and-diagnostics/SKILL.md.
Typical triggers
- “How do I build an imgaug pipeline with flips, affine, blur, and color jitter?”
- “Why did my augmentation change the image shape?”
- “How do I apply the same sampled transform twice?”
- “Which augmenter should I use for cropping, padding, weather, or superpixels?”
Fast path
- Read
references/pipeline-workflows.mdfor the minimal image-pipeline recipes. - Read
references/augmenter-family-reference.mdfor family selection and parameter defaults. - Run
scripts/generate_augmentation_contact_sheet.pywhen you need a safe contact sheet or a tiny visual smoke. - Read
references/troubleshooting.mdif the pipeline gives unexpected shapes, dtypes, or color results.
Core usage pattern
Image pipelines usually take numpy.ndarray input of shape (N, H, W, C) or a list of (H, W, C) arrays. Most examples assume RGB uint8 images.
import numpy as np
import imgaug.augmenters as iaa
images = np.zeros((4, 64, 64, 3), dtype=np.uint8)
seq = iaa.Sequential([
iaa.Fliplr(0.5),
iaa.Affine(rotate=(-10, 10), translate_px={"x": (-2, 2)}),
iaa.GaussianBlur(sigma=(0.0, 1.0)),
])
images_aug = seq(images=images)Use to_deterministic() when you need the same sampled transform in separate calls. Prefer a single call containing all aligned data whenever the task also includes annotations.
Show full SKILL.md (193 more words)Show less
Common pipeline decisions
- Use
Sequentialfor ordered pipelines. - Use
SomeOfwhen a bounded subset of augmenters should run. - Use
OneOfwhen exactly one branch should run. - Use
Sometimesfor probability-gated branches. - Use
WithChannelswhen only selected channels should change. - Use
fit_output=Falseandkeep_size=Trueas safe defaults until a task explicitly needs output resizing. - Keep
uint8/RGB in mind when the task starts from OpenCV or camera data.
Handy families and when to reach for them
Affine,PerspectiveTransform,ElasticTransformation,Jigsaw: geometric distortions.Crop,Pad,CropAndPad,Resize,KeepSizeByResize: size and framing.GaussianBlur,AverageBlur,MedianBlur,MotionBlur,BilateralBlur,MeanShiftBlur: smoothing/blur.Add,Multiply,Dropout,CoarseDropout,Invert,Solarize,JpegCompression: arithmetic/noise/compression.WithHueAndSaturation,ChangeColorspace,Grayscale,Posterize,KMeansColorQuantization,UniformColorQuantization: color and palette changes.LinearContrast,GammaContrast,HistogramEqualization,CLAHE: contrast shaping.BlendAlpha,SimplexNoiseAlpha,FrequencyNoiseAlpha: masked blending and partial effects.Superpixels,Voronoi,Snowflakes,Rain,Fog,Clouds,FastSnowyLandscape: segmentation-like and weather effects.
Validation mindset
A good image-pipeline smoke should prove three things:
- The output image array keeps the expected shape and dtype.
- The pipeline actually changes pixels when it should.
- A deterministic replay produces identical results.
Use the bundled script to check those properties with tiny arrays before moving to annotation-aware or multicore workflows.
© VectorSpaceLab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references) in skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/augmenter-family-reference.md
- references/pipeline-workflows.md
- references/troubleshooting.md
- scripts/generate_augmentation_contact_sheet.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Augmentation Pipelines 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Augmentation Pipelines this skillVectorSpaceLab/AREX-Skill | 328 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from VectorSpaceLab/AREX-Skill
All 157 skills in this repoAgent Lightning
VectorSpaceLab/AREX-Skill
Use this repo skill for Agent Lightning package tasks: authoring trainable agents, tracing rewards and spans, running LightningStore/Trainer loops, using agl CLI services, choosing examples, and…
Agent Tools
VectorSpaceLab/AREX-Skill
A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…
Agents And Awel
VectorSpaceLab/AREX-Skill
Build and debug DB-GPT agents, tools, skills, teams, and AWEL workflows, including deterministic local DAG runs and HTTP-trigger topology without assuming an LLM, credential, or external service.
Agents And Middleware
VectorSpaceLab/AREX-Skill
Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…
Agents Workflows
VectorSpaceLab/AREX-Skill
A skill your agent uses for giskard.agents async chat workflows, tools, prompt templates, structured outputs, retries, rate limiting, embeddings, and optional LiteLLM backend.
Alphafold3
VectorSpaceLab/AREX-Skill
A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
Related
Categories
Questions about Augmentation Pipelines
What does Augmentation Pipelines do?
A skill your agent uses when building, combining, or debugging imgaug image augmentation pipelines, augmenter families, or deterministic image-only transforms. Augmentation Pipelines is an agent skill from VectorSpaceLab/AREX-Skill. Use when building, combining, or debugging imgaug image augmentation pipelines, augmenter families, or deterministic image-only transforms.
When should I use Augmentation Pipelines?
Augmentation Pipelines fits situations like: debugging imgaug image augmentation pipelines; augmenter families; deterministic image-only transforms.
How do I install Augmentation Pipelines in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines in VectorSpaceLab/AREX-Skill) into .claude/skills/augmentation-pipelines in your project. Claude Code loads it when a task matches its description.
How do I install Augmentation Pipelines in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a codex`. Or copy the skill folder (skills/repositories/repo-skills/imgaug/sub-skills/augmentation-pipelines in VectorSpaceLab/AREX-Skill) into .agents/skills/augmentation-pipelines in your project. Codex loads it when a task matches its description.
Can I use Augmentation Pipelines 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 VectorSpaceLab/AREX-Skill --skill augmentation-pipelines -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/augmentation-pipelines, .gemini/skills/augmentation-pipelines, .github/skills/augmentation-pipelines and .opencode/skills/augmentation-pipelines in your project.
What does Augmentation Pipelines need to run?
Going by SKILL.md and its folder, Augmentation Pipelines needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Augmentation Pipelines 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 Augmentation Pipelines 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Augmentation Pipelines use?
Augmentation Pipelines is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Augmentation Pipelines 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. Its references folder adds about 2.2k tokens, read only when the agent opens those files.
What are the alternatives to Augmentation Pipelines?
Skills that share tags, products or a category with Augmentation Pipelines: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Augmentation Pipelines?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 328 GitHub stars. The repository holds 157 skills in this directory. The repository was last updated on September 3, 2026.
Source: VectorSpaceLab/AREX-Skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.