Repository
sablin39/tilelang-cuda-skills agent skills
- skills
- 10
- GitHub stars
- 145
GitHub description: “Skills for writing tilelang and debugging with CUDA toolkits. ”
- Stars
- 145 (6 forks)
- Licence
- No licence
- Last push
- Sep 2026
- Created
- May 2026
Install all skills
npx skills add sablin39/tilelang-cuda-skillsAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in sablin39/tilelang-cuda-skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations. | sablin39/ | 145 | — | ~1.3k | Automated safety check: Pass | No licence | 25 days ago |
| 2 | Write human-facing TileLang design documents for proposed or completed kernel implementations. | sablin39/ | 145 | — | ~2.2k | Automated safety check: Pass | No licence | 25 days ago |
| 3 | 3.Cuda Draft, debug, and measure CUDA kernels and host launch workflows. | sablin39/ | 145 | — | ~990 | Automated safety check: Pass | No licence | 25 days ago |
| 4 | Diagnose TileLang compilation, host argument, memory-liveness, runtime, and numerical failures. | sablin39/ | 145 | — | ~1.6k | Automated safety check: Pass | No licence | 25 days ago |
| 5 | Describe model or operator HIR with TileFoundry, inspect topology and placement, run static cost analysis, visualize authored dataflow, and check a runtime implementation against its evaluator. | sablin39/ | 145 | — | ~3.4k | Automated safety check: Pass | No licence | 25 days ago |
| 6 | Measure TileLang kernel and workflow performance, choose benchmark or timeline tools, and compare implementations fairly. | sablin39/ | 145 | — | ~1.6k | Automated safety check: Pass | No licence | 25 days ago |
| 7 | Tune a correct TileLang kernel using measured bottlenecks, tile sizes, layouts, pipelining, fusion, and autotuning. | sablin39/ | 145 | — | ~1k | Automated safety check: Pass | No licence | 25 days ago |
| 8 | Implement and validate forward and backward TileLang kernels integrated with torch.autograd.Function. | sablin39/ | 145 | — | ~1.2k | Automated safety check: Pass | No licence | 25 days ago |
| 9 | Run a bounded TileLang implementation and optimization task from a PyTorch reference or existing kernel through baseline analysis, a written plan, candidate edits, lowering inspection, validation… | sablin39/ | 145 | — | ~2.7k | Automated safety check: Pass | No licence | 25 days ago |
| 10 | Draft TileLang operators using JIT, tensor contracts, tiled computation, and reusable kernel patterns. | sablin39/ | 145 | — | ~1.3k | Automated safety check: Pass | No licence | 25 days ago |
Questions, answered from the data.
What is the best skill in sablin39/tilelang-cuda-skills?
Torch Profiling Tilelang Programs from sablin39/tilelang-cuda-skills ranks first of the 10 skills in sablin39/tilelang-cuda-skills listed here, with the highest score: its repository has 145 GitHub stars, its SKILL.md loads about 1.3k tokens and it passes the automated safety check with no findings. Next come Writing Tilelang Design Docs and Cuda.
Are the skills in sablin39/tilelang-cuda-skills official?
None yet. All 10 skills in sablin39/tilelang-cuda-skills listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from sablin39/tilelang-cuda-skills?
Run npx skills add sablin39/tilelang-cuda-skills in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.