Keras3 (R)
Idiomatic Keras3 patterns for R: Sequential/Functional/Subclassing APIs, multi-backend, callbacks.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · c34e41b
Baseline R code used the keras2-era `layer_input()` (not exported by keras3, would error at runtime) and `%>%`/c()-based tensor merging; the skill's own patterns correctly use `keras_input()`, `layer_add(list(...))`, and named callback constructors — a real, verifiable correctness fix, not just style.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Keras3 (R) does
Reference skill for building deep learning models with the keras3 R package. Covers the three model-building APIs, the audio/image/text preprocessing layer ecosystem, 30+ pretrained applications, multi-backend (TensorFlow/JAX/PyTorch) switching, and correct R-idiomatic function names. Triggers on keras3-specific terms like 'Functional API', 'layer_*', 'JAX backend', or 'custom training loop'.
How to install Keras3 (R)
git clone https://github.com/GiulSposito/r-claude-skills.git
mkdir -p ~/.claude/skills
cp -r r-claude-skills/.claude/skills/keras3 ~/.claude/skills/keras3
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Keras3 (R)
-
/keras3Idiomatic Keras3 patterns for R: Sequential/Functional/Subclassing APIs, multi-backend, callbacks.
It also activates on plain-language prompts like these:
-
Build a Keras3 R model with a ResNet-style skip connection -
Add early stopping and checkpoint callbacks to my keras3 model in R -
Switch my R keras3 training loop from TensorFlow to the JAX backend
Frequently asked questions
- Is the Keras3 (R) skill free?
- Yes. The skill itself is free from GiulSposito/r-claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Keras3 (R) work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Baseline R code used the keras2-era `layer_input()` (not exported by keras3, would error at runtime) and `%>%`/c()-based tensor merging; the skill's own patterns correctly use `keras_input()`, `layer_add(list(...))`, and named callback constructors — a real, verifiable correctness fix, not just style.
- What is the Keras3 (R) SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Keras3 (R)?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Keras3 (R) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.