AI Skills Catalog
Skills pack Tools

Deep Learning Book

Use an original study companion to navigate Deep Learning, plan prerequisite reading and examine training diagnostics or model arithmetic without replacing the source textbook.
SKILL SCORE87How it is scored
VerifiedFreeMIT

Works with

Packaged from the source skill for Claude, Codex and 4 more.

About this skill

Deep Learning Study Companion is an original learning aid organised around the 2016 textbook by Ian Goodfellow, Yoshua Bengio and Aaron Courville. It links readers to the official chapters, provides short concept notes and adds prerequisite planning, study templates and small diagnostic tools. The textbook itself is not included.

Use this skill when

  • You want a reading route through the book based on your background and a specific learning goal.
  • A training problem needs a structured first-pass explanation of possible numerical, optimisation or generalisation issues.
  • You need to work through tensor shapes or capacity assumptions while keeping the limits of a simplified model visible.

What it can do

Twenty chapter notes connect topics such as regularisation, optimisation and probabilistic modelling to a glossary and a reference map. Four standard-library Python tools support reading-path planning, training triage, capacity questions and model arithmetic. The companion also separates the book’s original scope from later developments described in its update notes.

The MIT licence covers this repository’s original companion and tools; it does not grant redistribution rights to the MIT Press textbook. Use the official links to read the source, and do not paste book passages into a shared package. Diagnostic rules are simplified heuristics, not experimental proof, and historical or later-practice claims need checking against the relevant research. No training run was performed for this listing.

Typical workflows

  1. Plan a study sequence. Supply your background, available study time and a goal. Use the prerequisite map to choose chapters and pair the reading with a small exercise and study-log entry.
  2. Investigate a training symptom. Bring actual training and validation measurements with their context. Use the diagnostic suggestions to choose one hypothesis to test, then compare it with the observed run.
  3. Check a model specification. Provide the layer specification and input shapes. Work through the arithmetic, flag unsupported cases and verify the result in the implementation separately.

What is inside the skill

Section headings from the original SKILL.md (about 1,347 words of instructions). Read the full text in the source repository before installing.

  1. How to Use This Skill
  2. Core Frameworks & Mental Models
  3. The (T, P, E) frame — ch05
  4. Every loss is a negative log-likelihood — ch03, ch06
  5. KL asymmetry decides your failure mode — ch03, ch19, ch20
  6. Train-error-first triage — ch11, ch05
  7. Capacity, the gap, and the U-curve's caveat — ch05, ch07
  8. Architecture is a prior, not a trick — ch09, ch10, ch15
  9. Depth's real cost is gradient flow and activation memory — ch06, ch08, ch10
  10. The partition function organizes Part III — ch16, ch17, ch18, ch19
  11. Diagnose before you redesign — ch04, ch08, ch11
  12. Chapter Index
  13. Topic Index
  14. Supporting Files
  15. Tools
  16. Scope & Limits

Bundled files

  • assets/chapter_worksheet.md
  • assets/example_layer_spec.json
  • assets/study_log_template.md
  • chapters/ch01-introduction.md
  • chapters/ch02-linear-algebra.md
  • chapters/ch03-probability-information-theory.md
  • chapters/ch04-numerical-computation.md
  • chapters/ch05-machine-learning-basics.md
  • chapters/ch06-deep-feedforward-networks.md
  • chapters/ch07-regularization.md
  • chapters/ch08-optimization.md
  • chapters/ch09-convolutional-networks.md
  • chapters/ch10-sequence-modeling.md
  • chapters/ch11-practical-methodology.md
  • chapters/ch12-applications.md
  • chapters/ch13-linear-factor-models.md
  • chapters/ch14-autoencoders.md
  • chapters/ch15-representation-learning.md
  • chapters/ch16-structured-probabilistic-models.md
  • chapters/ch17-monte-carlo-methods.md
  • chapters/ch18-partition-function.md
  • chapters/ch19-approximate-inference.md
  • chapters/ch20-deep-generative-models.md
  • cheatsheet.md
  • glossary.md
  • patterns.md
  • references/book_to_2026_delta.md
  • references/prerequisite_map.md
  • references/rights_and_use.md
  • references/study_method_canon.md
  • scripts/capacity_planner.py
  • scripts/model_arithmetic.py
  • scripts/reading_path_planner.py
  • scripts/training_diagnostics.py
  • LICENSE

Example prompts

  • Plan a six-week reading route for a software engineer who knows basic probability and wants to understand regularisation and optimisation. Point to the official chapters, list prerequisites and propose one small exercise for each week.
  • Use these training and validation curves, gradient measurements and dataset notes to produce a first-pass diagnosis. Distinguish observations from hypotheses and suggest one controlled experiment for each likely cause.
  • Review this supplied layer-specification JSON for tensor-shape and parameter-count reasoning. Flag unsupported operations and describe how we should independently verify the arithmetic in our model code.

How to install Deep Learning Book

Claude Packaged
  1. Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files.
  2. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.
  3. For Claude apps, upload the ZIP in the Skills section of the capabilities settings.
  4. Start a new session and describe the task in your own words. Claude picks the skill when the request matches its description.
More about skills for Claude
Codex Packaged
  1. Download the Codex package. The ZIP contains one folder named after the skill, with SKILL.md and bundled resources.
  2. Unpack the complete folder into .agents/skills/ inside your repository, or into ~/.agents/skills/ for personal use. Preserve its relative reference-file paths.
  3. Start a new Codex session and invoke the skill by name or with $skill-name, or describe a matching task.
  4. AGENTS.md is separate project guidance. The ZIP does not generate or modify that file.
More about skills for Codex
GPT Packaged
  1. Download the GPT package from the skill page.
  2. Create or edit a custom GPT (or a ChatGPT project) and paste the contents of SKILL.md into the instructions field.
  3. Upload the bundled reference files as knowledge so the GPT can consult them.
  4. Test with one of the example prompts from the skill page and adjust the instructions if your use case differs.
More about skills for GPT
Gemini Packaged
  1. Download the Gemini package from the skill page.
  2. For a project, unpack the complete folder into .gemini/skills/ or .agents/skills/. For personal use, use ~/.gemini/skills/ or ~/.agents/skills/.
  3. Run /skills reload in Gemini CLI, then /skills list to check discovery. There is no need to paste the skill into GEMINI.md.
  4. Test a matching task and verify the referenced tools and files are available.
More about skills for Gemini
Cursor Packaged
  1. Download the Cursor package from the skill page.
  2. Unpack the complete skill folder into .cursor/skills/ or .agents/skills/ in your project. For personal local use, ~/.cursor/skills/ and ~/.agents/skills/ are also supported.
  3. Start a new Cursor session. Type / in Agent chat and select the skill name, or describe a matching task.
  4. Commit the skill folder and resources for team use. Personal local skills are not automatically available to remote agents or automation runs.
More about skills for Cursor
OpenCode Packaged
  1. Download the OpenCode package from the skill page.
  2. Unpack the complete folder into .opencode/skills/ in your project, or ~/.config/opencode/skills/ for personal use. OpenCode also supports .agents/skills/ and .claude/skills/ compatibility locations.
  3. Keep supporting files at their original relative paths. AGENTS.md is separate project-wide guidance and is not generated by this ZIP.
  4. Start OpenCode in the project and test a matching task with the model and permissions you use.
More about skills for OpenCode

Permissions & security

Low risk

Inspect the source, license and declared permissions before use. Read the scripts before running them. Review method

Read project files
Write generated skill files

Deep Learning Book FAQ

What does the Deep Learning Book skill do?

Use an original study companion to navigate Deep Learning, plan prerequisite reading and examine training diagnostics or model arithmetic without replacing the source textbook.

Which AI agents can use Deep Learning Book?

Packages for Claude, Codex and 4 more are built from the same source instructions.

How do I install Deep Learning Book in Claude?

Download the Claude package from the skill page. The ZIP contains one folder named after the skill, with SKILL.md and any bundled reference files. For Claude Code, unpack the folder into ~/.claude/skills/ to use it in every project, or into .claude/skills/ inside a repository to share it with your team.

Who made Deep Learning Book and what is the license?

Deep Learning Book is published by Alireza Rezvani under the MIT license. The source is https://github.com/alirezarezvani/claude-skills/tree/main/engineering/deep-learning-book/skills/deep-learning-book. The catalog keeps the original attribution.

What permissions does Deep Learning Book need?

Declared permissions: read project files, write generated skill files. Risk level: low. Check the scripts in the source before running them.

Deep Learning Book Skill — Alireza Rezvani | AI Skills Catalog