neural-networks-3blue1brown SKILL.md skillA
neural-networks-3blue1brown from michalstrnadel/source-to-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add michalstrnadel/source-to-skill/neural-networks-3blue1brown@git:20261005.b3e3ebdPins git:20261005.b3e3ebd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- michalstrnadel/source-to-skill
- Path
examples/neural-networks-3blue1brown/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261005.b3e3ebd, committed Oct 5, 2026
- First version recorded
- Oct 4, 2026
- Size
- 9,529 bytes
- Repository stars
- 8
- License
- MIT
Course skill distilled from 3Blue1Brown's "Neural networks" YouTube playlist (10 videos) - from a plain MNIST digit classifier (neurons, weights, biases, sigmoid/ReLU), through cost functions, gradient descent, stochastic gradient descent and backpropagation with its chain-rule calculus, to large language models and transformers (tokens, embeddings, softmax and temperature, attention heads with query/key/value, masking, MLP blocks storing facts, superposition, the full GPT-3 175B parameter…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Neural networks — 3Blue1Brown (course skill) Source: https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi (channel: 3Blue1Brown, 10 videos). Lesson 10 is a guest video by Welch Labs; lesson 9 is "Part 2" of a separate *Compression is Intelligence* series (its Part 1 is not in this playlist). Lesson files open with the video URL and link key moments as `&t=<N>s` deep links (timestamps from ~1-minute caption markers, so each link lands at or shortly before the point described). ## What the course teaches, in order 1. **Structure** (L1) — a network is just a function: 784 pixel inputs → 10 digit outputs, built from weighted sums + bias + a squishing nonlinearity, compactly `a' = σ(W a + b)`. 2. **Learning = minimizing a cost** (L2) — define a cost over all training data, follow the negative gradient downhill. 3. **Backpropagation** (L3 intuition, L4 calculus) — how one training example "wants" every weight and bias nudged; average those wishes; use mini-batches (SGD) for speed. 4. **LLMs in brief** (L5) — next-word prediction, pre-training, RLHF, GPUs and why transformers parallelize. …
Read the whole file at its exact version.
How to install
mdr add michalstrnadel/source-to-skill/neural-networks-3blue1brown@sha256:3c86782da7081e10The line at the top of this page pins the label git:20261005.b3e3ebd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ztvlkbo766nno662)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 4, 2026 and Oct 5, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.b3e3ebd latest | 2026-10-05 | b3e3ebd | 9,529 B | A | view · diff |
| git:20261004.d77ddfa | 2026-10-04 | d77ddfa | 9,415 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9529 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
michalstrnadel/source-to-skill · 8 stars · license MIT · pushed 2026-10-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ztvlkbo766nno662 GET https://markdownregistry.com/api/v1/resolve?ref=michalstrnadel/source-to-skill/neural-networks-3blue1brown GET https://markdownregistry.com/api/v1/blob/3c86782da7081e101044cb2b2f8f18a53f8b046039dd4ee6142ec9c0c7bad747
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.