NeVibeCode · repository · 11 items
skills: a set by modular
The modular/skills repository on GitHub: 11 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- modular/skills
- Stars
- ★ 213
- Installs across cards
- 19,024
- License
- Apache-2.0
- Source updated
- 2026-11-13
- In the catalog since
- 2026-10-25
mojo-syntax skill Skill for Claude Code, Codex, and Cursor. Corrects obsolete Mojo syntax generated by pretrained models when writing, translating, or reviewing code.
CX Codex +1
3,100installs
mojo-gpu-fundamentals skill mojo-gpu-fundamentals guides agents to write GPU code in Mojo for NVIDIA, AMD, and Apple silicon without CUDA syntax. Corrects kernel dispatch, buffer allocation, and TileTensor layouts.
CX Codex +1
2,800installs
mojo-python-interop skill mojo-python-interop — a skill that keeps your agent on current Mojo syntax when the code calls Python or exposes Mojo types to it.
CX Codex +1
2,700installs
new-modular-project skill new-modular-project initializes fresh Mojo or MAX projects using pixi or uv package managers. It clarifies missing project settings and configures stable or nightly release channels.
CX Codex +1
2,600installs
import-model skill import-model — a skill for Claude Code ports new neural network architectures from Hugging Face into MAX. Executes when importing model weights or scaffolding ModuleV3 layers.
CX Codex +1
1,600installs
debug-model skill The debug-model skill for Claude Code diagnoses a MAX model that serves and emits tokens but disagrees with a reference. It compares tensor dumps before fixes.
CX Codex +1
1,400installs
profile-model skill profile-model — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode that profiles models running on MAX — identifying which kernels consume GPU time and whether the GPU is saturated.
CX Codex +1
1,300installs
serve-model skill serve-model — a skill that takes you from no environment to an Anthropic-compatible server via max serve, flags included.
CX Codex +1
1,100installs
eval-model skill eval-model runs a text model served by MAX through standard benchmarks and writes reproducible per-task scores. Useful when you need to check a served model against its card.
CX Codex +1
1,100installs
benchmark-model skill benchmark-model drives load against a running max serve endpoint and reports tokens/sec, TTFT and TPOT. Useful when you need to know what a MAX model actually holds.
CX Codex +1
1,000installs
migrate-max-v2-to-v3 skill migrate-max-v2-to-v3 — a skill for Claude Code and Codex that migrates MAX framework models from the legacy V2 graph API to ModuleV3. It updates imports, swaps TensorValue for Tensor, and switches graph building to compile().
CX Codex +1
324installs