Agent skill

Multicore And Diagnostics

by VectorSpaceLab in VectorSpaceLab/AREX-Skill

A skill your agent uses when running imgaug batches in background processes or threads, tuning Pool/queue behavior, or diagnosing slow and hanging augmentation.

MITAuto-check passed

Install Multicore And Diagnostics

skills CLI
$ npx skills add VectorSpaceLab/AREX-Skill --skill multicore-and-diagnostics -a claude-code

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

GitHub CLI
$ gh skill install VectorSpaceLab/AREX-Skill multicore-and-diagnostics --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/VectorSpaceLab/AREX-Skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repositories/repo-skills/imgaug/sub-skills/multicore-and-diagnostics .claude/skills/multicore-and-diagnostics && 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
multicore-and-diagnostics
GitHub stars
330
Token cost
~922 tokens
SKILL.md length
274 words
Files
5 (incl. scripts, references)
Skills in repo
159
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when running imgaug batches in background processes or threads, tuning Pool/queue behavior, or diagnosing slow and hanging augmentation.

  • Works in 4 steps: Read references/multicore-workflows.md… → Read… → Run scripts/tiny_multicore_smoke.py… → …
  • Running imgaug batches in background processes
  • SKILL.md covers What this sub-skill covers, What it does not cover, Typical triggers and Fast path, plus 3 more sections
  • Runs Python scripts from its folder

What it does

Multicore And Diagnostics is an agent skill from VectorSpaceLab/AREX-Skill. Use when running imgaug batches in background processes or threads, tuning Pool/queue behavior, or diagnosing slow and hanging augmentation.

Its SKILL.md is about 920 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/diagnostics-and-performance.md`, `references/multicore-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

  • Running imgaug batches in background processes
  • Tuning Pool/queue behavior
  • Diagnosing slow and hanging augmentation

Example prompts

  • “/multicore-and-diagnostics”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read references/multicore-workflows.md for API patterns and safe defaults.
  2. Read references/diagnostics-and-performance.md before tuning worker counts or queues.
  3. Run scripts/tiny_multicore_smoke.py before attempting a large workload.
  4. Read references/troubleshooting.md for hangs, pickling errors, platform issues, and queue exhaustion.

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

Multicore And Diagnostics loads about 922 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 42 tokens; SKILL.md has 274 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~922
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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). 274 words, ~922 tokens.

Download SKILL.mdSave it as .claude/skills/multicore-and-diagnostics/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
multicore-and-diagnostics
description
Use when running imgaug batches in background processes or threads, tuning Pool/queue behavior, or diagnosing slow and hanging augmentation.
disable-model-invocation
true
metadata.disco-role
operating
license
MIT

Multicore and Diagnostics

Use this sub-skill for imgaug's CPU parallelism and diagnostic surfaces: augment_batches(..., background=True), Augmenter.pool(), imgaug.multicore.Pool, BatchLoader, BackgroundAugmenter, safe smoke checks, and performance/hang triage.

What this sub-skill covers

  • Batch-oriented background augmentation.
  • Process pools, map_batches, imap_batches, chunksize, processes, seed, and maxtasksperchild.
  • BatchLoader and BackgroundAugmenter queue/worker configuration.
  • Pickling and platform start-method caveats.
  • Small, deterministic diagnostics that do not open GUI windows or run huge loops.

What it does not cover

Typical triggers

  • “How do I augment batches in the background?”
  • “Use all CPUs except one for imgaug.”
  • “Why does BackgroundAugmenter hang?”
  • “What should chunksize or queue size be?”
  • “Prove the multiprocessing path with a tiny fixture before scaling up.”

Fast path

  1. Read references/multicore-workflows.md for API patterns and safe defaults.
  2. Read references/diagnostics-and-performance.md before tuning worker counts or queues.
  3. Run scripts/tiny_multicore_smoke.py before attempting a large workload.
  4. Read references/troubleshooting.md for hangs, pickling errors, platform issues, and queue exhaustion.

Verified signatures

  • Augmenter.augment_batches(batches, hooks=None, background=False)
  • Augmenter.pool(processes=None, maxtasksperchild=None, seed=None)
  • imgaug.multicore.Pool(augseq, processes=None, maxtasksperchild=None, seed=None)
  • Pool.map_batches(batches, chunksize=None)
  • Pool.imap_batches(batches, chunksize=1, output_buffer_size=None)
  • BatchLoader(load_batch_func, queue_size=50, nb_workers=1, threaded=True)
  • BackgroundAugmenter(batch_loader, augseq, queue_size=50, nb_workers='auto')
  • BackgroundAugmenter.get_batch()

Safe starting pattern

python
from imgaug.augmentables.batches import UnnormalizedBatch
import imgaug.augmenters as iaa

seq = iaa.Sequential([iaa.Fliplr(0.5), iaa.GaussianBlur((0.0, 1.0))])
batches_aug = seq.augment_batches(batches, background=True)
for batch in batches_aug:
    consume(batch)

For explicit process control:

python
with seq.pool(processes=-1, seed=1) as pool:
    batches_aug = pool.imap_batches(batches, chunksize=1)
    for batch in batches_aug:
        consume(batch)

Negative processes reserves that many logical cores when possible; -1 means all but one. Start with a tiny batch list and scale only after the smoke passes.

Diagnostic order

  1. Run the root environment check.
  2. Run the tiny multicore smoke with one or two batches.
  3. Replace custom lambdas/callbacks with top-level picklable functions.
  4. Reduce processes, queue sizes, and batch sizes.
  5. Only then tune chunksize, maxtasksperchild, or background queue depth.

© 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/multicore-and-diagnostics of VectorSpaceLab/AREX-Skill.

  • SKILL.md
  • references/diagnostics-and-performance.md
  • references/multicore-workflows.md
  • references/troubleshooting.md
  • scripts/tiny_multicore_smoke.py

Open the folder on GitHubat commit ac3fe1a

Compare with similar skills

Multicore And Diagnostics 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.

Multicore And Diagnostics compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Multicore And Diagnostics this skillVectorSpaceLab/AREX-Skill330—~922Automated safety check: PassMIT
Bio Batch ProcessingFreedomIntelligence/OpenClaw-Medical-Skills3.1k1 repos~2.2kAutomated safety check: PassNone
Batchasgeirtj/system_prompts_leaks69k—~1.3kAutomated safety check: PassCC0-1.0
Batch ProcessZJU-REAL/Easel3.3k—~555Automated safety check: PassApache-2.0
Batch Processing Clinical Textmaziyarpanahi/openmed5.5k—~2.2kAutomated safety check: PassApache-2.0
Batchcodewhale-hq/Codewhale41k—~157Automated safety check: PassMIT

Similar skills

  • Bio Batch Processing

    FreedomIntelligence/OpenClaw-Medical-Skills

    Process multiple sequence files in batch using Biopython. An agent skill from FreedomIntelligence/OpenClaw-Medical-Skills.

    3.1k GitHub starsUsed in 1 repo~2.2k tokens
    Data & AnalyticsAuto-check passed
  • 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.

    69k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Batch Process

    ZJU-REAL/Easel

    批量处理:对一个目录里的一批图片/视频/音频统一套用同一操作——批量压缩、加水印、转格式、缩放、转比例、音量归一化等。当用户说 批量处理、批量压缩、批量加水印、批量转格式、一批图片/视频、给这个文件夹、全部转成、批量缩放、批量转竖版、整个目录 时使用。基于 shared/scripts/batchprocess.py(委派 imageops/videoops/audioops)。与…

    3.3k GitHub stars~555 tokensUpdated today
    Media & CreativeAuto-check passed
  • Batch Processing Clinical Text

    maziyarpanahi/openmed

    Run large-scale batch NER, PII extraction, or de-identification over many clinical notes on-device with OpenMed, with sharding, checkpointing, resumability, and append-only JSONL output.

    5.5k GitHub stars~2.2k tokensUpdated today
    DatabasesAuto-check passed
  • Batch

    codewhale-hq/Codewhale

    Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify.

    41k GitHub stars~157 tokensUpdated today
    DevelopmentAuto-check passed
  • Processing API Batches

    jeremylongshore/tons-of-skills-marketplace

    Optimize bulk API requests with batching, throttling, and parallel execution.

    2.8k GitHub stars~1.5k tokensUpdated today
    Backend & APIsAuto-check passed

More from VectorSpaceLab/AREX-Skill

All 159 skills in this repo
  • Agent 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…

    330 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed
  • 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…

    330 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • 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.

    330 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed
  • 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…

    330 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • 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.

    330 GitHub stars~500 tokensUpdated 1 mo ago
    Auto-check passed
  • Alphafold3

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.

    330 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Multicore And Diagnostics

What does Multicore And Diagnostics do?

A skill your agent uses when running imgaug batches in background processes or threads, tuning Pool/queue behavior, or diagnosing slow and hanging augmentation. Multicore And Diagnostics is an agent skill from VectorSpaceLab/AREX-Skill. Use when running imgaug batches in background processes or threads, tuning Pool/queue behavior, or diagnosing slow and hanging augmentation.

When should I use Multicore And Diagnostics?

Multicore And Diagnostics fits situations like: running imgaug batches in background processes; tuning Pool/queue behavior; diagnosing slow and hanging augmentation.

How do I install Multicore And Diagnostics in Claude Code?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill multicore-and-diagnostics -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/imgaug/sub-skills/multicore-and-diagnostics in VectorSpaceLab/AREX-Skill) into .claude/skills/multicore-and-diagnostics in your project. Claude Code loads it when a task matches its description.

How do I install Multicore And Diagnostics in Codex?

Run `npx skills add VectorSpaceLab/AREX-Skill --skill multicore-and-diagnostics -a codex`. Or copy the skill folder (skills/repositories/repo-skills/imgaug/sub-skills/multicore-and-diagnostics in VectorSpaceLab/AREX-Skill) into .agents/skills/multicore-and-diagnostics in your project. Codex loads it when a task matches its description.

Can I use Multicore And Diagnostics 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 multicore-and-diagnostics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/multicore-and-diagnostics, .gemini/skills/multicore-and-diagnostics, .github/skills/multicore-and-diagnostics and .opencode/skills/multicore-and-diagnostics in your project.

What does Multicore And Diagnostics need to run?

Going by SKILL.md and its folder, Multicore And Diagnostics needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Multicore And Diagnostics 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 Multicore And Diagnostics 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 Multicore And Diagnostics use?

Multicore And Diagnostics 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 Multicore And Diagnostics use?

About 922 tokens (SKILL.md is roughly 3.7k 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 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Multicore And Diagnostics?

Skills that share tags, products or a category with Multicore And Diagnostics: Bio Batch Processing (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars), Batch (asgeirtj/system_prompts_leaks, 69k stars), Batch Process (ZJU-REAL/Easel, 3.3k stars) and Batch Processing Clinical Text (maziyarpanahi/openmed, 5.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Multicore And Diagnostics?

VectorSpaceLab (a GitHub organization) maintains it in VectorSpaceLab/AREX-Skill, which has 330 GitHub stars. The repository holds 159 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.