debug-matmul-mx

debug-matmul-mx is a Runtime diagnostics & profiling skill for AI agents, published by hw-native-sys in the PTOAS repository on GitHub. Skillspace rates debug-matmul-mx D (60/100) and it passed the safety scan; the rating is based on static analysis only.

Debug MX and cube matmul failures involving `mad_mx`, `mte_l1_l0a`, `mte_l1_l0b`, `mte_l1_l0a_mx`, `mte_l1_l0b_mx`, FP4 packed-byte MTE shapes, MX scale packing, fractal layout mapping, TileLang/PTODSL wrapper expansion, or `mte_l0c_gm` writeback. Use when a cube matmul case fails in simulator or validation and the issue may be in `golden.py`, layout/fractal mapping, wrapper lowering, emitter control packing, FP4 data movement, or host test shape synchronization.

Grade
D
Quality
60 / 100
Safety
Passed
GitHub stars
28

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubhw-native-sys/PTOAS

Our review

Architecture
86 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Runtime diagnostics & profiling

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.