torch-profiler-layer-track SKILL.md skillB
torch-profiler-layer-track from bbuf/ai-infra-auto-driven-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add bbuf/ai-infra-auto-driven-skills/torch-profiler-layer-track@git:20261005.aa3fee7Pins git:20261005.aa3fee7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- bbuf/ai-infra-auto-driven-skills
- Path
skills/torch-profiler-layer-track/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261005.aa3fee7, committed Oct 5, 2026
- First version recorded
- Sep 11, 2026
- Size
- 8,008 bytes
- Repository stars
- 1,120
- License
- none declared
Add verified layer-number guides and compact GPU display lanes to an existing Torch Profiler Chrome JSON trace. Use for L0/L1/... navigation or traces with hundreds of CUDA Graph stream rows. Changes visualization, not runtime streams.
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
# Torch Profiler Layer Track Create a normal Chrome JSON trace with `L0, L1, ...` guides beside at most ten synthetic GPU activity lanes per device. Keep the source file. Compaction changes event placement, not execution: original kernel names, timestamps, durations and `args.stream` remain intact. CPU events stay unchanged. Label the output as a **compact view**, not a runtime stream optimization. First read the [kernel attribution and timing principles](../llm-torch-profiler-analysis/references/heuristics.md#establish-dispatch-and-numerical-contracts). Fused mHC/AR can remove old anchors; graph-launch host gaps and synthetic lane counts do not establish GPU idle time or runtime stream counts. ## Establish what the labels mean Use the user's existing local trace, including a Desktop copy when requested. Obtain the layer count from matching model config/source. Identify the rank/GPU, execution phase, and one complete forward pass before counting. In speculative decoding, separate target verify from draft passes. BS=1 does not imply one token per target verify. A repeated block in the overview can be a whole iteration, not a transformer layer. …
Read the whole file at its exact version.
How to install
mdr add bbuf/ai-infra-auto-driven-skills/torch-profiler-layer-track@sha256:8cba16208a8a4db1The line at the top of this page pins the label git:20261005.aa3fee7, 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_c5zou3f5gltj6huw)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 11, 2026 and Oct 5, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261005.aa3fee7 latest | 2026-10-05 | aa3fee7 | 8,008 B | B | view · diff |
| git:20260918.b4657a2 | 2026-09-18 | b4657a2 | 7,579 B | B | view · diff |
| git:20260913.b84a62a | 2026-09-13 | b84a62a | 7,300 B | B | view · diff |
| git:20260911.53329ec | 2026-09-11 | 53329ec | 5,413 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8008 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 script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
bbuf/ai-infra-auto-driven-skills · 1,120 stars · license none declared · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_c5zou3f5gltj6huw GET https://markdownregistry.com/api/v1/resolve?ref=bbuf/ai-infra-auto-driven-skills/torch-profiler-layer-track GET https://markdownregistry.com/api/v1/blob/8cba16208a8a4db1e3c62e66a1587af68f8023053a1559df50d468575703c423
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.