Neural Network Visualization

What it does

When your agent uses it

• Tasks that involve Deep learning
• Tasks that involve Embeddings

Example prompts

• “/neural-network-visualization”

Requirements

• Python 3

Workflow steps

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

1. 1Import most public neural-network classes directly from manim_ml.neural_network.
2. 2Use a list of layer objects for sequential networks and a dictionary of named layer objects when later manual connections should address…
3. 3Keep image examples self-contained by generating tiny PNGs or by converting a caller-supplied image with Pillow; do not reference…
4. 4Use exact activation names: "ReLU" and "Sigmoid".
5. 5make_forward_pass_animation(layer_args=...) keys are layer/connective object instances, not layer names.
6. 6add_connection(...) supports the default connection style; choose arc_direction="straight", "up", "down", "left", or "right" for the…
7. 7Treat full video rendering as optional and potentially slow. For quick checks, render a still with manim -ql -s.

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.

  Shell commands in SKILL.md call:

  • python

  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 Visualization loads about 1.3k tokens when it runs, and up to ~8.9k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 424 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~97

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~8.9k

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

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). 424 words, ~1,300 tokens.

name

neural-network-visualization

description

Use this operating sub-skill to create, adapt, and troubleshoot ManimML neural-network scenes: NeuralNetwork containers, feed-forward and convolutional layers, image/embedding/vector/math/triplet/paired-query layers, connective layers, forward-pass animations, dropout, residual/manual connections, insertion/removal animations, and small safe render scripts.

disable-model-invocation

true

metadata.disco-role

operating

metadata.package

manim_ml

metadata.repo-skill

manim-ml

metadata.sub-skill

neural-network-visualization

license

MIT

python - <<'PY'
import manim
from manim_ml.neural_network import NeuralNetwork, FeedForwardLayer
print("manim", getattr(manim, "__version__", "unknown"))
print(NeuralNetwork, FeedForwardLayer)
PY

python sub-skills/neural-network-visualization/scripts/render_neural_network_example.py --help
python sub-skills/neural-network-visualization/scripts/render_neural_network_example.py --mode feed-forward --scene-file nn_example.py
manim -ql -s nn_example.py ManimMLNeuralNetworkExample

from manim import *
from manim_ml.neural_network import NeuralNetwork, FeedForwardLayer

class MyScene(Scene):
    def construct(self):
        nn = NeuralNetwork([
            FeedForwardLayer(3),
            FeedForwardLayer(5, activation_function="ReLU"),
            FeedForwardLayer(2),
        ])
        nn.move_to(ORIGIN)
        self.add(nn)
        self.play(nn.make_forward_pass_animation(run_time=3))

© 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/manim-ml/sub-skills/neural-network-visualization of VectorSpaceLab/AREX-Skill.

• SKILL.md
• references/api-reference.md
• references/troubleshooting.md
• references/workflows.md
• scripts/render_neural_network_example.py

Open the folder on GitHubat commit ac3fe1a