New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Amd Att Trace

by facebookexperimental in facebookexperimental/triton

Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels.

OfficialMITAuto-check passed

Install Amd Att Trace

skills CLI
$ npx skills add facebookexperimental/triton --skill amd-att-trace -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install facebookexperimental/triton amd-att-trace --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/facebookexperimental/triton.git skills-src && mkdir -p .claude/skills && cp -r skills-src/third_party/tlx/tools/agents/skills/amd-att-trace .claude/skills/amd-att-trace && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
amd-att-trace
GitHub stars
201
Token cost
~733 tokens
SKILL.md length
304 words
Files
4 (incl. scripts, references)
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels.

  • Works in 7 steps: Establish the application command,… → Run att_trace.py probe. Use a profiler… → Use collect --dry-run when command… → …
  • Viewer-ready artifacts
  • SKILL.md covers Authorization and scope, Workflow, Commands and References
  • Runs Python scripts from its folder; calls python

What it does

Amd Att Trace is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels. Use for ATT collection, viewer-ready artifacts, or loop cycle windows; do not trigger for ordinary performance benchmarks.

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/rocprofv3.md`, `references/viewer-format.md` and `scripts/att_trace.py`).

The repository describes itself as: Github mirror of trition-lang/triton repo. The licence is MIT.

When your agent uses it

  • Viewer-ready artifacts
  • Loop cycle windows
  • Do not trigger for ordinary performance benchmarks

Example prompts

  • “/amd-att-trace”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Establish the application command, kernel regex, steady-state dispatch
  2. Run att_trace.py probe. Use a profiler that exposes --att and a matching
  3. Use collect --dry-run when command selection or quoting is uncertain.
  4. Collect exactly the requested dispatch. Use a unique output directory.
  5. Treat collection as successful only when the automatic viewer-bundle
  6. Package the complete trace root with package; never transfer only the raw
  7. Report the trace root, archive and checksum if packaged, selected profiler

What it can do on your machine

Read from SKILL.md and the folder at commit 953bd20. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Amd Att Trace loads about 733 tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 304 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~733
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from facebookexperimental/triton at commit 953bd20, republished under its MIT licence (© facebookexperimental). 304 words, ~733 tokens.

Download SKILL.mdSave it as .claude/skills/amd-att-trace/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
amd-att-trace
description
Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels. Use for ATT collection, viewer-ready artifacts, or loop cycle windows; do not trigger for ordinary performance benchmarks.

AMD Advanced Thread Trace

Use scripts/att_trace.py for the reproducible parts of ATT collection. Do not recreate rocprofv3 commands or decide that a raw .att file is viewer-ready by inspection alone.

Authorization and scope

  • Collect a new trace only when the user explicitly asks to run or profile a workload. Reading, validating, or packaging an existing trace is read-only.
  • Check GPU occupancy before collection and choose an idle device. Do not stop another user's job or run killgpu.sh unless explicitly authorized.
  • Keep ATT diagnostics separate from correctness and end-to-end performance measurements. A trace is not a correctness result or a stable benchmark.
  • Never overwrite an existing non-empty output directory or archive.

Workflow

  1. Establish the application command, kernel regex, steady-state dispatch number, GPU, and output label. State any inferred dispatch numbering.
  2. Run att_trace.py probe. Use a profiler that exposes --att and a matching decoder directory. Prefer a profiler and target application from compatible ROCm installations.
  3. Use collect --dry-run when command selection or quoting is uncertain.
  4. Collect exactly the requested dispatch. Use a unique output directory.
  5. Treat collection as successful only when the automatic viewer-bundle validation passes.
  6. Package the complete trace root with package; never transfer only the raw .att files.
  7. Report the trace root, archive and checksum if packaged, selected profiler and decoder, kernel regex, dispatch number, and decoded UI directory.

Commands

bash
python scripts/att_trace.py probe

python scripts/att_trace.py collect \
  --output /tmp/my-att \
  --name my-kernel \
  --gpu 0 \
  --kernel-regex 'my_kernel' \
  --dispatch 6 \
  -- <application> <arguments>

python scripts/att_trace.py validate /tmp/my-att
python scripts/att_trace.py package /tmp/my-att

python scripts/att_trace.py window /tmp/my-att \
  --loop-pc 0x2388 --first 10 --last 14

Iteration windows are zero-based by default and end at the next loop-marker occurrence after --last. Choose a loop marker that appears once per loop iteration; barriers can produce multiple ATT events. Record unrolling such as "one outer iteration represents two logical K tiles" instead of silently equating outer-loop and logical-tile iterations.

References

© facebookexperimental, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in third_party/tlx/tools/agents/skills/amd-att-trace of facebookexperimental/triton.

  • SKILL.md
  • references/rocprofv3.md
  • references/viewer-format.md
  • scripts/att_trace.py

Open the folder on GitHubat commit 953bd20

Compare with similar skills

Amd Att Trace next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Amd Att Trace compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Amd Att Trace this skillfacebookexperimental/triton201—~733Automated safety check: PassMIT
Observe Traceruvnet/ruflo74k—~522Automated safety check: NotesMIT
Dotnet Trace Collectdotnet/skills5.6k2 repos~6.1kAutomated safety check: PassMIT
Node Inspect Debuggeropenclaw/openclaw392k1 repos~894Automated safety check: PassMIT
Motion Advancedaffaan-m/ECC276k1 repos~4.7kAutomated safety check: PassMIT
Arize Tracegithub/awesome-copilot40k1 repos~5.9kAutomated safety check: NotesMIT

Similar skills

  • Observe Trace

    ruvnet/ruflo

    Trace agent execution by collecting spans and building a trace tree for a task

    74k GitHub stars~522 tokensUpdated today
    Auto-check: notes

  • Dotnet Trace Collect

    dotnet/skills

    Official

    Guide developers through capturing diagnostic artifacts to diagnose production .NET performance issues.

    5.6k GitHub starsUsed in 2 repos~6.1k tokens
    Auto-check passed

  • Node Inspect Debugger

    openclaw/openclaw

    Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

    392k GitHub starsUsed in 1 repo~894 tokens
    Frontend & DesignAuto-check passed

  • Motion Advanced

    affaan-m/ECC

    Advanced motion patterns for React / Next.js — drag & drop, gestures, text animations, SVG path drawing, custom hooks, imperative sequences (useAnimate), loaders, and the full API decision tree.

    276k GitHub starsUsed in 1 repo~4.7k tokens
    Auto-check passed

  • Arize Trace

    github/awesome-copilot

    Official

    Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues.

    40k GitHub starsUsed in 1 repo~5.9k tokens
    DevelopmentAuto-check: notes

  • Exploring LLM Traces

    PostHog/posthog

    Official

    Debug and inspect LLM/AI agent traces using PostHog's MCP tools.

    40k GitHub stars~4.4k tokensUpdated today
    DevOps & CloudAuto-check passed

More from facebookexperimental/triton

All 18 skills in this repo

  • Ir Override Ablation

    facebookexperimental/triton

    Official

    Design and run Triton TTGIR debugging ablations using iroverride.

    201 GitHub stars~978 tokensUpdated today
    Auto-check passed

  • Tlx Kernel Optimization Agent

    facebookexperimental/triton

    Official

    Execute the TLX Kernel Optimization Agent CLI on a Triton or TLX kernel.

    201 GitHub stars~3.5k tokensUpdated today
    Auto-check passed

  • Compute Sanitizer

    facebookexperimental/triton

    Official

    Run NVIDIA compute-sanitizer (memcheck, racecheck, initcheck, synccheck) against a Triton/TLX kernel to find runtime memory and synchronization bugs.

    201 GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Debug Failing GPU

    facebookexperimental/triton

    Official

    Recover from GPU-busy / GPU-unavailable failures. An agent skill from facebookexperimental/triton.

    201 GitHub stars~709 tokensUpdated today
    Auto-check passed

  • Ir Debugging

    facebookexperimental/triton

    Official

    Debug Triton compilation by dumping IR at each stage (TTIR, TTGIR, LLVM, PTX).

    201 GitHub stars~644 tokensUpdated today
    Auto-check passed

  • Kernel Perf Testing

    facebookexperimental/triton

    Official

    Run TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs.

    201 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Questions about Amd Att Trace

What does Amd Att Trace do?

Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels. Amd Att Trace is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels.

When should I use Amd Att Trace?

Amd Att Trace fits situations like: viewer-ready artifacts; loop cycle windows; do not trigger for ordinary performance benchmarks.

How do I install Amd Att Trace in Claude Code?

Run `npx skills add facebookexperimental/triton --skill amd-att-trace -a claude-code`. Or copy the skill folder (third_party/tlx/tools/agents/skills/amd-att-trace in facebookexperimental/triton) into .claude/skills/amd-att-trace in your project. Claude Code loads it when a task matches its description.

How do I install Amd Att Trace in Codex?

Run `npx skills add facebookexperimental/triton --skill amd-att-trace -a codex`. Or copy the skill folder (third_party/tlx/tools/agents/skills/amd-att-trace in facebookexperimental/triton) into .agents/skills/amd-att-trace in your project. Codex loads it when a task matches its description.

Can I use Amd Att Trace in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add facebookexperimental/triton --skill amd-att-trace -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/amd-att-trace, .gemini/skills/amd-att-trace, .github/skills/amd-att-trace and .opencode/skills/amd-att-trace in your project.

What does Amd Att Trace need to run?

Going by SKILL.md and its folder, Amd Att Trace needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Amd Att Trace access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Amd Att Trace safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Amd Att Trace use?

Amd Att Trace is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Amd Att Trace use?

About 733 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 964 tokens, read only when the agent opens those files.

What are the alternatives to Amd Att Trace?

Skills that share tags, products or a category with Amd Att Trace: Observe Trace (ruvnet/ruflo, 74k stars), Dotnet Trace Collect (dotnet/skills, 5.6k stars), Node Inspect Debugger (openclaw/openclaw, 392k stars) and Motion Advanced (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Amd Att Trace?

facebookexperimental (a GitHub organization, an official publisher) maintains it in facebookexperimental/triton, which has 201 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 9, 2026.

Source: facebookexperimental/triton on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.