mkl-extension-advisor SKILL.md skillA
mkl-extension-advisor from intel/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add intel/skills/mkl-extension-advisor@v1.0Pins v1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- intel/skills
- Path
skills/mkl-extension-advisor/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0, committed Sep 3, 2026
- Size
- 11,281 bytes
- Repository stars
- 29
- License
- Apache-2.0
Deciding whether Intel's MKL extension packages apply to NumPy or SciPy code on Intel CPUs. Use when a user asks whether mkl_fft, mkl_random, or mkl_umath help their code, or points at a snippet, function, file, or codebase using np.fft, scipy.fft, np.random, or element-wise math ufuncs. Also use to check whether these extensions are already active in an environment, to fix an install so they and the SciPy FFT backend actually work, or to judge whether patching would change results and break…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# MKL extension advisor ## Purpose Given NumPy or SciPy code, decides whether `mkl_fft`, `mkl_random`, or `mkl_umath` apply to it, and presents verified changes with short reasons. A fit check, not a profiler. The judgement runs on two independent axes: - **Install** — which numpy binary is present and what it links against. - **Runtime** — whether call sites dispatch to oneMKL, which is set either by an activation call or by build-level pre-wiring. They are genuinely independent. An MKL-backed BLAS says nothing about FFT: numpy's FFT is bundled pocketfft with no BLAS linkage, so `threadpool_info()` can report `mkl` while `np.fft.fft.__module__` is still `numpy.fft`. The reverse inference is just as wrong. An `mkl` entry in the threadpool does not prove numpy's BLAS is MKL — importing any `mkl_*` extension loads oneMKL into the process, so a stock OpenBLAS numpy reports `['mkl', 'openblas', 'openmp']` after `import mkl_fft`. For the BLAS question read `np.__config__.show()`, not the pool. ## When to Use This Skill Use this skill when: - The user asks whether the MKL extensions apply to a snippet, file, or codebase. …
Read the whole file at its exact version.
How to install
mdr add intel/skills/mkl-extension-advisor@sha256:3b9b994aedb11088The line at the top of this page pins the label v1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_37wpsqva2x32rvjs)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 3, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11281 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
intel/skills · 29 stars · license Apache-2.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_37wpsqva2x32rvjs GET https://markdownregistry.com/api/v1/resolve?ref=intel/skills/mkl-extension-advisor GET https://markdownregistry.com/api/v1/blob/3b9b994aedb110884eddab184d16d93b2e1f39e34f221f1059e93bc602040545
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.