FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Accelerating scientific Python on NVIDIA GPUs v1.0.0
Use this resource to accelerate scientific Python code on NVIDIA GPUs while checking results and gains
New
- 563 downloads
- 214 likes
- 105 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install gpu-python-optimizationWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent measures the baseline first, checks that a port makes sense, then applies the least intrusive change and compares end-to-end timings. You get validated GPU code, or a finding that a port brings no gain.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- MIT
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: when to apply, optimization workflow and validation rules
- references/: CuPy, cuDF, cuML, cuGraph, cuVS, cuCIM, KvikIO and other RAPIDS libraries
Good fit for
- Your NumPy or pandas job takes several minutes
- You want to know whether a GPU is worth it for a given computation
Not for
Tags
- GPU
- CUDA
- optimization
About
You say
“My pandas join script on 50 million rows is slow: check whether a cuDF port helps.”
Skill published by k-dense-ai under the MIT license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to accelerate scientific Python code on NVIDIA GPUs while checking results and gains
- Review and adjust the result
Content preview
Files
- LICENSE1.1 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/code_transformation_patterns.md10.1 KB
- references/cucim.md21.8 KB
- references/cudf.md21.4 KB
- references/cugraph.md28.1 KB
- references/cuml.md25.1 KB
- references/cupy.md22.3 KB
- references/cuspatial.md15.5 KB
- references/cuvs.md22.9 KB
- references/cuxfilter.md19.4 KB
- references/decision_framework.md15.9 KB
- references/installation.md5.7 KB
- references/kvikio.md20.7 KB
- references/numba.md27.1 KB
- references/raft.md12.1 KB
- references/warp.md21 KB
- SKILL.md13.7 KB
Origin and licence
Listed unmodified
- Author
- k-dense-ai
- Source
- github.com/k-dense-ai/scientific-agent-skills/tree/5f2bc0341354fd5590aef76a533ada1e1e5b4e62/skills/optimize-for-gpu
- Licence
- MIT
Notice
« optimize-for-gpu » (k-dense-ai, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…