Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring.
Install Neural Network Building Blocks
$ npx skills add VectorSpaceLab/AREX-Skill --skill neural-network-building-blocks -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill neural-network-building-blocks --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/ml-algorithms/sub-skills/neural-network-building-blocks .claude/skills/neural-network-building-blocks && 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 "neural-network-building-blocks" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks into .claude/skills/neural-network-building-blocks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "neural-network-building-blocks", 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/ml-algorithms/sub-skills/neural-network-building-blocksType 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 neural-network-building-blocks -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill neural-network-building-blocks --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/ml-algorithms/sub-skills/neural-network-building-blocks .agents/skills/neural-network-building-blocks && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "neural-network-building-blocks" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks into .agents/skills/neural-network-building-blocks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "neural-network-building-blocks", 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 neural-network-building-blocks -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill neural-network-building-blocks --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/ml-algorithms/sub-skills/neural-network-building-blocks .cursor/skills/neural-network-building-blocks && 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 "neural-network-building-blocks" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks into .cursor/skills/neural-network-building-blocks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "neural-network-building-blocks", 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/ml-algorithms/sub-skills/neural-network-building-blocks--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 neural-network-building-blocks -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install VectorSpaceLab/AREX-Skill neural-network-building-blocks --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/ml-algorithms/sub-skills/neural-network-building-blocks .gemini/skills/neural-network-building-blocks && 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 "neural-network-building-blocks" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks into .gemini/skills/neural-network-building-blocks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "neural-network-building-blocks", 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 neural-network-building-blocksInstalls 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 neural-network-building-blocks -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/ml-algorithms/sub-skills/neural-network-building-blocks .github/skills/neural-network-building-blocks && 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 "neural-network-building-blocks" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks into .github/skills/neural-network-building-blocks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "neural-network-building-blocks", 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 neural-network-building-blocks -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 neural-network-building-blocks --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/ml-algorithms/sub-skills/neural-network-building-blocks .opencode/skills/neural-network-building-blocks && 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 "neural-network-building-blocks" agent skill from https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks into .opencode/skills/neural-network-building-blocks/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "neural-network-building-blocks", 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
neural-network-building-blocks- GitHub stars
- 331
- Token cost
- ~941 tokens
- SKILL.md length
- 362 words
- Files
- 7 (incl. scripts, references)
- Skills in repo
- 157
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring.
- Works in 4 steps: Confirm the package imports the neural… → Choose the architecture family → Use explicit one-hot labels for… → …
- Tasks that involve Deep learning
- SKILL.md covers Route elsewhere, Start here, Primary workflows and Bundled references and helpers
- Runs Python scripts from its folder
What it does
Neural Network Building Blocks is an agent skill from VectorSpaceLab/AREX-Skill. Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring.
Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/api-reference.md`, `references/neural-workflows.md` and `references/rl-dqn.md`).
It sits in AI & LLM Engineering, covering Deep learning. The repository describes itself as: A Skill Library for Automated Machine Learning. The licence is MIT.
When your agent uses it
- Tasks that involve Deep learning
Example prompts
- “/neural-network-building-blocks”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Confirm the package imports the neural stack you need
- Choose the architecture family
- Use explicit one-hot labels for categorical_crossentropy, and remember that NeuralNet uses a separate optimizer.setup(self) step when fit…
- Run scripts/run_neural_smoke.py --workflow all for a short no-display check.
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
Neural Network Building Blocks loads about 941 tokens when it runs, and up to ~5.8k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 362 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). 362 words, ~941 tokens.
Download SKILL.mdSave it as
.claude/skills/neural-network-building-blocks/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- neural-network-building-blocks
- description
- Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring.
- disable-model-invocation
- true
- metadata.disco-role
- operating
- license
- MIT
Neural Network Building Blocks
Use this sub-skill when a task asks for the custom MLAlgorithms neural-network stack: how to build a NeuralNet, choose layers or optimizers, debug training phases and shapes, or adapt the repo's MLP/CNN/RNN/LSTM/DQN examples into shorter checks. The implementation is educational and CPU-only, with no external training service or model hub dependency.
Route elsewhere
- Tabular supervised estimators, SVM kernels, ensembles, KNN, Naive Bayes, and factorization machines belong in
../classical-estimators/SKILL.md. - KMeans, Gaussian mixtures, PCA, t-SNE, RBM, and demo dataset loaders belong in
../unsupervised-and-reduction/SKILL.md. - Cross-cutting install, provenance, and route selection remain in the root skill.
Start here
Confirm the package imports the neural stack you need:
python from mla.neuralnet import NeuralNet from mla.neuralnet.layers import Dense, Activation, Dropout from mla.neuralnet.optimizers import AdamChoose the architecture family:
- Simple dense model:
Dense+Activation. - CNN:
Convolution,MaxPooling,Flatten,Dense. - Sequence model:
RNNorLSTM, optionally followed byTimeDistributedDenseorTimeStepSlicer. - Reinforcement learning wrapper:
mla.rl.dqn.DQNwith a user-provided neural model factory.
- Simple dense model:
Use explicit one-hot labels for
categorical_crossentropy, and remember thatNeuralNetuses a separateoptimizer.setup(self)step whenfitstarts.Run
scripts/run_neural_smoke.py --workflow allfor a short no-display check.
Primary workflows
Build a dense network
NeuralNet takes a list of layers plus an optimizer and a loss name. The container sets up layers, performs forward/backward passes, and delegates parameter updates to the optimizer.
from mla.neuralnet import NeuralNet
from mla.neuralnet.layers import Dense, Activation
from mla.neuralnet.optimizers import Adam
model = NeuralNet(
layers=[Dense(16), Activation("relu"), Dense(1)],
optimizer=Adam(),
loss="mse",
batch_size=32,
max_epochs=5,
metric="mse",
)Show full SKILL.md (155 more words)Show less
Convolutional workflow
Use Convolution, MaxPooling, Flatten, and Dense for the repo's MNIST-style example. The ConvNet expects image tensors shaped like (n_samples, n_channels, height, width).
Recurrent workflow
Use RNN or LSTM for sequence problems. The classes accept return_sequences=True by default, which is helpful for per-time-step outputs. TimeDistributedDense applies a dense layer to each time step.
DQN wiring
DQN is a lightweight training loop that asks the user to supply a model factory. It is designed around legacy Gym-style reset()/step() interactions and should be treated as an integration recipe rather than a production RL stack.
Bundled references and helpers
- Read
references/api-reference.mdfor exact constructor signatures and output/shape contracts. - Read
references/workflows.mdfor dense/CNN/RNN/DQN recipes and validation advice. - Read
references/neural-workflows.mdfor longer CNN and sequence reference workflows. - Read
references/rl-dqn.mdbefore touching CartPole or other Gym environments. - Read
references/troubleshooting.mdwhen training stalls, shapes break, or Gym/NumPy compatibility drifts. - Run
scripts/run_neural_smoke.py --workflow mlpor--workflow allfor a small installed-package check.
© 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 6 other files (scripts, references) in skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks of VectorSpaceLab/AREX-Skill.
- SKILL.md
- references/api-reference.md
- references/neural-workflows.md
- references/rl-dqn.md
- references/troubleshooting.md
- references/workflows.md
- scripts/run_neural_smoke.py
Open the folder on GitHubat commit ac3fe1a
Compare with similar skills
Neural Network Building Blocks 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 |
|---|---|---|---|---|---|---|
| Neural Network Building Blocks this skillVectorSpaceLab/AREX-Skill | 331 | — | ~941 | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Add Oponnx/onnx | 22k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Add Function Bodyonnx/onnx | 22k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
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.
Add Op
onnx/onnx
Add a new ONNX operator or update an existing operator to a new opset version.
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.
Add Function Body
onnx/onnx
Add a function body definition to an ONNX operator, defining how it decomposes into simpler ops.
Paddle Design Distributed
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…
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 Neural Network Building Blocks
What does Neural Network Building Blocks do?
Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring. Neural Network Building Blocks is an agent skill from VectorSpaceLab/AREX-Skill. Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring.
When should I use Neural Network Building Blocks?
Neural Network Building Blocks fits situations like: tasks that involve Deep learning.
How do I install Neural Network Building Blocks in Claude Code?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill neural-network-building-blocks -a claude-code`. Or copy the skill folder (skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks in VectorSpaceLab/AREX-Skill) into .claude/skills/neural-network-building-blocks in your project. Claude Code loads it when a task matches its description.
How do I install Neural Network Building Blocks in Codex?
Run `npx skills add VectorSpaceLab/AREX-Skill --skill neural-network-building-blocks -a codex`. Or copy the skill folder (skills/repositories/repo-skills/ml-algorithms/sub-skills/neural-network-building-blocks in VectorSpaceLab/AREX-Skill) into .agents/skills/neural-network-building-blocks in your project. Codex loads it when a task matches its description.
Can I use Neural Network Building Blocks 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 neural-network-building-blocks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/neural-network-building-blocks, .gemini/skills/neural-network-building-blocks, .github/skills/neural-network-building-blocks and .opencode/skills/neural-network-building-blocks in your project.
What does Neural Network Building Blocks need to run?
Going by SKILL.md and its folder, Neural Network Building Blocks needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Neural Network Building Blocks 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 Neural Network Building Blocks 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 Neural Network Building Blocks use?
Neural Network Building Blocks 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 Neural Network Building Blocks use?
About 941 tokens (SKILL.md is roughly 3.8k 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 4.9k tokens, read only when the agent opens those files.
What are the alternatives to Neural Network Building Blocks?
Skills that share tags, products or a category with Neural Network Building Blocks: Add Uint Support (pytorch/pytorch, 104k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Add Op (onnx/onnx, 22k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Neural Network Building Blocks?
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.