analyze-kernel-bottleneck SKILL.md skillA
analyze-kernel-bottleneck from pjt222/agent-almanac is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pjt222/agent-almanac/analyze-kernel-bottleneck@v1.0Pins v1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pjt222/agent-almanac
- Path
i18n/caveman-lite/skills/analyze-kernel-bottleneck/SKILL.md- Versions recorded
- 4
- Latest version
- v1.0, committed Aug 17, 2026
- First version recorded
- Apr 19, 2026
- Size
- 17,076 bytes
- Repository stars
- 43
- License
- MIT
Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy calculations, compute/load ratio per tile, and SASS instruction inspection. Produces a decision matrix for optimization strategy selection (cp.async, warp interleaving, tiling, double-buffering, or CuAssembler hand-tuning).
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
# Analyze Kernel Bottleneck Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound by measuring baseline performance, classifying on the roofline, computing occupancy and compute/load ratio per tile, inspecting SASS instruction mix and stall codes, checking the shared memory cliff, and applying a decision matrix to select the right optimization strategy. ## When to Use - Before optimizing any CUDA kernel -- establish baseline and classify bottleneck type - After writing a first working version of a kernel to identify the optimization path - When a kernel underperforms expectations relative to theoretical peak - When deciding between cp.async, larger tiles, or algorithmic restructuring ## Inputs - **Required**: Compiled kernel (`.cubin` or `.cu` source with build command) - **Required**: Benchmark harness that launches the kernel with CUDA event timing - **Required**: Problem dimensions (e.g., M, N, K for GEMM; seq_len, heads, head_dim for attention) - **Optional**: Target GPU architecture (default: GA104 / sm_86 / RTX 3070 Ti) - **Optional**: Expected peak utilization percentage for comparison …
Read the whole file at its exact version.
How to install
mdr add pjt222/agent-almanac/analyze-kernel-bottleneck@sha256:ea09e5404f936b61The 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_4xaqcrcdyfmqptjc)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Apr 19, 2026 and Aug 17, 2026, about one every 40 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0 latest | 2026-08-17 | a784899 | 17,076 B | A | view · diff |
| v1.0 | 2026-06-05 | 75ded7a | 17,047 B | A | view · diff |
| v1.0 | 2026-04-19 | a31852a | 17,106 B | A | view · diff |
| v1.0 | 2026-04-19 | e334ebd | 17,177 B | A | view |
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 (17076 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
pjt222/agent-almanac · 43 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4xaqcrcdyfmqptjc GET https://markdownregistry.com/api/v1/resolve?ref=pjt222/agent-almanac/analyze-kernel-bottleneck GET https://markdownregistry.com/api/v1/blob/ea09e5404f936b61b74ad3c13112d71d13cb83cace4b96313bf1957995123266
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.