Box
asgeirtj/system_prompts_leaks
Search, read, upload, download, move, rename, delete, restore, and share Box content; manage comments and metadata.
A skill your agent uses when applying imgaug transforms to keypoints, boxes, polygons, line strings, heatmaps, segmentation maps, or mixed batches.
MITAuto-check passed
Install Augmentables And Batches
$ npx skills add VectorSpaceLab/AREX-Skill --skill augmentables-and-batches -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentables-and-batches --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/augmentables-and-batches .claude/skills/augmentables-and-batches && 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 "augmentables-and-batches" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches into .claude/skills/augmentables-and-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentables-and-batches", 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/augmentables-and-batchesType 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 augmentables-and-batches -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentables-and-batches --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/augmentables-and-batches .agents/skills/augmentables-and-batches && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "augmentables-and-batches" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches into .agents/skills/augmentables-and-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentables-and-batches", 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 augmentables-and-batches -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentables-and-batches --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/augmentables-and-batches .cursor/skills/augmentables-and-batches && 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 "augmentables-and-batches" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches into .cursor/skills/augmentables-and-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentables-and-batches", 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/augmentables-and-batches--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 augmentables-and-batches -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill augmentables-and-batches --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/augmentables-and-batches .gemini/skills/augmentables-and-batches && 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 "augmentables-and-batches" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches into .gemini/skills/augmentables-and-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentables-and-batches", 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 augmentables-and-batchesInstalls 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 augmentables-and-batches -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/augmentables-and-batches .github/skills/augmentables-and-batches && 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 "augmentables-and-batches" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches into .github/skills/augmentables-and-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentables-and-batches", 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 augmentables-and-batches -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 augmentables-and-batches --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/augmentables-and-batches .opencode/skills/augmentables-and-batches && 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 "augmentables-and-batches" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches into .opencode/skills/augmentables-and-batches/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "augmentables-and-batches", 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
augmentables-and-batches- GitHub stars
- 331
- Token cost
- ~1k tokens
- SKILL.md length
- 368 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 applying imgaug transforms to keypoints, boxes, polygons, line strings, heatmaps, segmentation maps, or mixed batches.
- Works in 4 steps: Read… → Read references/batch-workflows.md when… → Run… → …
- Applying imgaug transforms to keypoints
- 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
Augmentables And Batches is an agent skill from VectorSpaceLab/AREX-Skill. Use when applying imgaug transforms to keypoints, boxes, polygons, line strings, heatmaps, segmentation maps, or mixed batches.
Its SKILL.md is about 1k 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/augmentables-data-formats.md`, `references/batch-workflows.md` and `references/troubleshooting.md`).
The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is MIT.
When your agent uses it
- Applying imgaug transforms to keypoints
- Segmentation maps
Example prompts
- “/augmentables-and-batches”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Read references/augmentables-data-formats.md to choose object types and data layouts.
- Read references/batch-workflows.md when the task uses Batch, UnnormalizedBatch, or background augmentation.
- Run scripts/smoke_aligned_augmentables.py for a tiny alignment smoke.
- Read references/troubleshooting.md for shape/count mismatches, invalid polygons, dense-map interpolation, or out-of-image coordinate issues.
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
Augmentables And Batches loads about 1k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 368 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). 368 words, ~1,025 tokens.
Download SKILL.mdSave it as
.claude/skills/augmentables-and-batches/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- augmentables-and-batches
- description
- Use when applying imgaug transforms to keypoints, boxes, polygons, line strings, heatmaps, segmentation maps, or mixed batches.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- MIT
Augmentables and Batches
Use this sub-skill when the task involves applying imgaug transforms to images and aligned non-image data: keypoints, bounding boxes, polygons, line strings, heatmaps, segmentation maps, or Batch/UnnormalizedBatch containers.
What this sub-skill covers
- Construction and validation of
KeypointsOnImage,BoundingBoxesOnImage,PolygonsOnImage,LineStringsOnImage,HeatmapsOnImage, andSegmentationMapsOnImage. - Passing aligned augmentables in the same augmenter call as images.
- Image shape metadata, coordinate projection,
on(...), drawing, clipping, and out-of-image handling. - Dense heatmap versus segmentation-map semantics.
BatchandUnnormalizedBatchworkflows for mixed data and background augmentation.
What it does not cover
- Choosing image augmenter families belongs to
../augmentation-pipelines/SKILL.md. - Stochastic parameters, RNG, dtype helper internals, and sample data belong to
../parameters-random-and-utilities/SKILL.md. - Background pool execution belongs to
../multicore-and-diagnostics/SKILL.md.
Typical triggers
- “Apply affine augmentation to images and bounding boxes.”
- “How do I augment lower-resolution heatmaps or segmentation maps with images?”
- “Why are my keypoints out of image bounds after augmentation?”
- “How should I package images, boxes, and metadata into batches?”
Fast path
- Read
references/augmentables-data-formats.mdto choose object types and data layouts. - Read
references/batch-workflows.mdwhen the task usesBatch,UnnormalizedBatch, or background augmentation. - Run
scripts/smoke_aligned_augmentables.pyfor a tiny alignment smoke. - Read
references/troubleshooting.mdfor shape/count mismatches, invalid polygons, dense-map interpolation, or out-of-image coordinate issues.
Core aligned-call pattern
import numpy as np
import imgaug as ia
import imgaug.augmenters as iaa
images = np.zeros((2, 64, 64, 3), dtype=np.uint8)
keypoints = [[ia.Keypoint(x=10.5, y=20.5)], [ia.Keypoint(x=30.5, y=40.5)]]
boxes = [[ia.BoundingBox(x1=5, y1=5, x2=20, y2=20)], [ia.BoundingBox(x1=8, y1=8, x2=24, y2=24)]]
seq = iaa.Sequential([iaa.Fliplr(1.0), iaa.Affine(translate_px={"x": 2})])
images_aug, keypoints_aug, boxes_aug = seq(
images=images,
keypoints=keypoints,
bounding_boxes=boxes,
)Use one call for all aligned data whenever possible. This ensures the same sampled geometric transform is applied to every augmentable group.
Show full SKILL.md (144 more words)Show less
Dense-map rules of thumb
- Heatmaps are continuous arrays; they are usually float-like and may be lower resolution than images.
- Segmentation maps are categorical; nearest-neighbor semantics are expected during resizing or spatial transforms.
- Always provide the original image
shapeto dense augmentable objects so imgaug can project coordinates correctly.
Batch guidance
Use UnnormalizedBatch when a loader naturally returns flexible Python lists or arrays and you want imgaug to normalize and restore output forms. Use Batch when inputs are already normalized imgaug augmentable objects. For multiprocessing, combine this sub-skill with the multicore sub-skill.
Validation mindset
A safe aligned-data smoke should assert:
- The number of image items and annotation groups is preserved.
- Output shapes match expectations for both images and dense maps.
- Coordinate objects remain instances of the expected imgaug classes.
- Out-of-image objects are explicitly clipped, removed, or allowed according to task requirements.
© 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/augmentables-and-batches of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/augmentables-data-formats.md
- references/batch-workflows.md
- references/troubleshooting.md
- scripts/smoke_aligned_augmentables.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Augmentables And Batches 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 |
|---|---|---|---|---|---|---|
| Augmentables And Batches this skillVectorSpaceLab/AREX-Skill | 331 | — | ~1k | Automated safety check: Pass | MIT | |
| Boxasgeirtj/system_prompts_leaks | 69k | — | ~1.1k | Automated safety check: Pass | CC0-1.0 | |
| Batchasgeirtj/system_prompts_leaks | 69k | — | ~1.3k | Automated safety check: Pass | CC0-1.0 | |
| TransformersK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~2.8k | Automated safety check: Notes | Apache-2.0 | |
| Batchcodewhale-hq/Codewhale | 41k | — | ~157 | Automated safety check: Pass | MIT | |
| Batch API PlannerQwenLM/qwen-code | 28k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Batch
asgeirtj/system_prompts_leaks
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
Transformers
K-Dense-AI/scientific-agent-skills
Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks.
Batch
codewhale-hq/Codewhale
Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify.
Batch API Planner
QwenLM/qwen-code
Prepares many-file, single-turn transforms such as translating or rewriting as a plan, then submits it to the asynchronous, half-price DashScope Batch API through the qwen batch CLI.
Polygon Automation
ComposioHQ/awesome-claude-skills
Automate Polygon tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.
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.
Questions about Augmentables And Batches
What does Augmentables And Batches do?
A skill your agent uses when applying imgaug transforms to keypoints, boxes, polygons, line strings, heatmaps, segmentation maps, or mixed batches. Augmentables And Batches is an agent skill from VectorSpaceLab/AREX-Skill. Use when applying imgaug transforms to keypoints, boxes, polygons, line strings, heatmaps, segmentation maps, or mixed batches.
When should I use Augmentables And Batches?
Augmentables And Batches fits situations like: applying imgaug transforms to keypoints; segmentation maps.
How do I install Augmentables And Batches in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill augmentables-and-batches -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches in VectorSpaceLab/AREX-Skill) into .claude/skills/augmentables-and-batches in your project. Claude Code loads it when a task matches its description.
How do I install Augmentables And Batches in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill augmentables-and-batches -a codex`. Or copy the skill folder (skills/repositories/repo-skills/imgaug/sub-skills/augmentables-and-batches in VectorSpaceLab/AREX-Skill) into .agents/skills/augmentables-and-batches in your project. Codex loads it when a task matches its description.
Can I use Augmentables And Batches 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 augmentables-and-batches -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/augmentables-and-batches, .gemini/skills/augmentables-and-batches, .github/skills/augmentables-and-batches and .opencode/skills/augmentables-and-batches in your project.
What does Augmentables And Batches need to run?
Going by SKILL.md and its folder, Augmentables And Batches needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Augmentables And Batches 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 Augmentables And Batches 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 Augmentables And Batches use?
Augmentables And Batches 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 Augmentables And Batches use?
About 1k tokens (SKILL.md is roughly 4.1k 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 1.7k tokens, read only when the agent opens those files.
What are the alternatives to Augmentables And Batches?
Skills that share tags, products or a category with Augmentables And Batches: Box (asgeirtj/system_prompts_leaks, 69k stars), Batch (asgeirtj/system_prompts_leaks, 69k stars), Transformers (K-Dense-AI/scientific-agent-skills, 48k stars) and Batch (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Augmentables And Batches?
VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 331 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.