Repository
ROCm/FlyDSL agent skills
- skills
- 19
- GitHub stars
- 287
GitHub description: “FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high level.”
- Stars
- 287 (124 forks)
- Licence
- Unknown
- Last push
- Oct 2026
- Created
- Nov 2025
- Source
- github.com/ROCm/FlyDSL
- amdgpu
- cute
- gpu
- mlir
- performance
- python-dsl
- deep-learning
Install all skills
npx skills add ROCm/FlyDSLAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in ROCm/FlyDSL, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.Llvm Tune and analyse a FlyDSL kernel at the LLVM level: pick a compile hint, function attribute, or AMDGPU backend flag, then PROVE it reached codegen. | ROCm/ | 287 | — | ~4.9k | Automated safety check: Notes | Unknown | today |
| 2 | Detect per-kernel GPU resource regressions (VGPR, SGPR, register spills, scratch, static LDS) by diffing the final ISA before and after a change, using its isaresourcetable.py helper. | ROCm/ | 287 | — | ~2.7k | Automated safety check: Notes | Unknown | today |
| 3 | Review a FlyDSL PR, commit, branch, kernel, or consuming module for API-stability compliance. | ROCm/ | 287 | — | ~3.2k | Automated safety check: Notes | Unknown | today |
| 4 | Connect to a remote host via SSH and build a Docker image with rocprofv3, aiter, and FlyDSL. | ROCm/ | 287 | — | ~1.2k | Automated safety check: Notes | Unknown | today |
| 5 | Debug FlyDSL GPU kernels that produce NaN, inf, wrong results, or crash. | ROCm/ | 287 | — | ~2.6k | Automated safety check: Notes | Unknown | today |
| 6 | Guided step-by-step wizard for producing a new FlyDSL GPU kernel from a requirement: classify the kernel type, pick a skeleton, fill in compute, add control flow / sync / LDS, then test on GPU. | ROCm/ | 287 | — | ~4.6k | Automated safety check: Notes | Unknown | today |
| 7 | Format, clean up, and style-check changed files, matching the project's CI style gate. | ROCm/ | 287 | — | ~1.9k | Automated safety check: Notes | Unknown | today |
| 8 | Profile GPU kernels using rocprofv3 to collect ATT instruction-level traces, then analyze the trace data using hotspotanalyzer.py to identify top-K stall hotspots (VMEM-load, VMEM-wait… | ROCm/ | 287 | — | ~5k | Automated safety check: Notes | Unknown | today |
| 9 | Detect out-of-bounds memory accesses in CPU or GPU code using static interval analysis and runtime assertions/printfs. | ROCm/ | 287 | — | ~1k | Automated safety check: Notes | Unknown | today |
| 10 | Apply prefetch optimization to FlyDSL kernel loops: pre-load the first iteration's data before the loop, issue async loads for the next iteration inside the loop body, and swap buffers at the loop… | ROCm/ | 287 | — | ~4.4k | Automated safety check: Notes | Unknown | today |
| 11 | Review a FlyDSL release candidate against published releases for API stability violations, including export paths, signatures, result interfaces, semantics, and deprecation windows. | ROCm/ | 287 | — | ~2.2k | Automated safety check: Pass | Unknown | today |
| 12 | Add a new target-specific Mma / Copy Op type to a FlyDSL backend dialect (lib/Dialect/Fly<TARGET/<SUBTARGET/ + include/flydsl/Dialect/Fly<TARGET/IR/). | ROCm/ | 287 | — | ~6.9k | Automated safety check: Notes | Unknown | today |
| 13 | Comprehensive reference for authoring FlyDSL GPU kernels on AMD GPUs. | ROCm/ | 287 | — | ~10k | Automated safety check: Notes | Unknown | today |
| 14 | Clean up FlyDSL kernels and shared helpers while preserving numerical behavior and performance. | ROCm/ | 287 | — | ~6.5k | Automated safety check: Notes | Unknown | today |
| 15 | Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels. | ROCm/ | 287 | — | ~5.8k | Automated safety check: Notes | Unknown | today |
| 16 | Find the exact commit that caused a GPU kernel performance regression using binary search (git bisect). | ROCm/ | 287 | — | ~4k | Automated safety check: Notes | Unknown | today |
| 17 | 17.Build Flydsl Build and install FlyDSL (Flexible Layout Python DSL) on a remote host or Docker container. | ROCm/ | 287 | — | ~1.3k | Automated safety check: Notes | Unknown | today |
| 18 | Capture GPU kernel ATT (Advanced Thread Trace) via rocprofv3 on a remote Docker container or locally. | ROCm/ | 287 | — | ~2.5k | Automated safety check: Notes | Unknown | today |
| 19 | Comprehensive guide to optimizing GEMM (General Matrix Multiply) kernels in FlyDSL on AMD CDNA GPUs. | ROCm/ | 287 | — | ~6.4k | Automated safety check: Notes | Unknown | today |
Questions, answered from the data.
What is the best skill in ROCm/FlyDSL?
Llvm from ROCm/FlyDSL ranks first of the 19 skills in ROCm/FlyDSL listed here, with the highest score: its repository has 287 GitHub stars, its SKILL.md loads about 4.9k tokens and it has informational notes only in the automated safety check. Next come Isa Resource Diff and API Stability.
Are the skills in ROCm/FlyDSL official?
None yet. All 19 skills in ROCm/FlyDSL 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 ROCm/FlyDSL?
Run npx skills add ROCm/FlyDSL 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.