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

Running With Buck

by facebookexperimental in facebookexperimental/triton

How to build and run GPU targets under Buck in fbcode. An agent skill from facebookexperimental/triton.

OfficialMITAuto-check passedAI & LLM Engineering

Install Running With Buck

skills CLI
$ npx skills add facebookexperimental/triton --skill running-with-buck -a claude-code

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

GitHub CLI
$ gh skill install facebookexperimental/triton running-with-buck --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/.claude/skills/running-with-buck .claude/skills/running-with-buck && 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
running-with-buck
GitHub stars
201
Token cost
~998 tokens
SKILL.md length
317 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

How to build and run GPU targets under Buck in fbcode. An agent skill from facebookexperimental/triton.

  • Works in 6 steps: Run from fbsource/fbcode. cd to… → Use @mode/opt. It provides the core GPU… → Build against the beta Triton with -m… → …
  • Invoking buck2 run / buck2 build for any GPU benchmark
  • SKILL.md covers General requirements, Hardware requirements and Examples
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Running With Buck is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. How to build and run GPU targets under Buck in fbcode. Use when invoking buck2 run / buck2 build for any GPU benchmark, test, or kernel — selecting the GPU architecture and CUDA version, using @mode/opt and the beta Triton modifier, passing environment variables through, and running from the right directory. Covers the general requirements plus the B200/GB200 (b200a, CUDA = 12.8) and GB300 (b300a, CUDA = 13.0) hardware requirements.

Its SKILL.md is about 1000 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Secrets management. It works with CUDA. The repository describes itself as: Github mirror of trition-lang/triton repo. The licence is MIT.

When your agent uses it

  • Invoking buck2 run / buck2 build for any GPU benchmark
  • Kernel — selecting the GPU architecture and CUDA version
  • Using @mode/opt and the beta Triton modifier
  • Passing environment variables through

Example prompts

  • “/running-with-buck”

Workflow steps

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

  1. Run from fbsource/fbcode. cd to fbsource/fbcode before
  2. Use @mode/opt. It provides the core GPU build configuration.
  3. Build against the beta Triton with -m ovr_config//triton:beta. This
  4. Select the GPU architecture with -c fbcode.nvcc_arch= and,
  5. Environment variables prefix the buck2 run and are forwarded to
  6. buck2 build vs buck2 run. Use buck2 build to compile

What it can do on your machine

Read from SKILL.md and the folder at commit 37301d4. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    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

Running With Buck loads about 998 tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 317 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~998

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from facebookexperimental/triton at commit 37301d4, republished under its MIT licence (© facebookexperimental). 317 words, ~998 tokens.

Download SKILL.mdSave it as .claude/skills/running-with-buck/SKILL.md (or your agent's skills folder).
name
running-with-buck
description
How to build and run GPU targets under Buck in fbcode. Use when invoking buck2 run / buck2 build for any GPU benchmark, test, or kernel — selecting the GPU architecture and CUDA version, using @mode/opt and the beta Triton modifier, passing environment variables through, and running from the right directory. Covers the general requirements plus the B200/GB200 (b200a, CUDA >= 12.8) and GB300 (b300a, CUDA >= 13.0) hardware requirements.

Running GPU Targets with Buck

This skill covers the mechanics of building and running GPU targets under Buck in fbcode. It is target-agnostic: substitute your own <buck target> and program arguments.

General requirements

  1. Run from fbsource/fbcode. cd to fbsource/fbcode before invoking Buck. The @mode/opt flags (and other @mode/... files) only resolve when Buck is run from there.
  2. Use @mode/opt. It provides the core GPU build configuration. @mode/opt generally sets up the GPU build, but some tritonbench targets still pass -c fbcode.enable_gpu_sections=true explicitly — add it if a target's GPU sections fail to build.
  3. Build against the beta Triton with -m ovr_config//triton:beta. This directory is the beta Triton compiler. Pass this modifier so the target builds and runs against the beta Triton in this tree rather than the default/stable Triton — without it, changes made here are not exercised.
  4. Select the GPU architecture with -c fbcode.nvcc_arch=<arch> and, where required, the CUDA version with -m ovr_config//third-party/cuda/constraints:<ver> (see Hardware requirements).
  5. Environment variables prefix the buck2 run and are forwarded to the launched process:
    bash
    <ENV VARS> buck2 run @mode/opt -m ovr_config//triton:beta -c fbcode.nvcc_arch=<arch> [-m ovr_config//third-party/cuda/constraints:<ver>] \
  <buck target> -- <program args>
  6. buck2 build vs buck2 run. Use buck2 build <target> to compile only (e.g. to surface a compile failure without executing); use buck2 run <target> -- <args> to build and run. Program arguments go after --.

Hardware requirements

Pick the arch (and CUDA version) for the single GPU you are targeting:

Hardwarefbcode.nvcc_archovr_config//third-party/cuda/constraints:<version>
Hopper (H100)h100a(default)
Blackwell B200 / GB200b200a>= 12.8
Blackwell GB300b300a>= 13.0

Notes:

  • B200 / GB200 require CUDA >= 12.8. Existing tritonbench targets pin 12.8; use the version your build expects.
  • GB300 requires arch b300a and CUDA >= 13.0.
  • Set the CUDA version explicitly whenever a minimum applies, since the platform default may be older than the arch requires.

Examples

Blackwell GB300 (b300a, CUDA 13.0), from fbsource/fbcode:

bash
buck2 run @mode/opt -m ovr_config//triton:beta \
  -c fbcode.nvcc_arch=b300a \
  -m ovr_config//third-party/cuda/constraints:13.0 \
  <buck target> -- <program args>

Blackwell B200 / GB200 (b200a, CUDA >= 12.8):

bash
buck2 run @mode/opt -m ovr_config//triton:beta \
  -c fbcode.nvcc_arch=b200a \
  -m ovr_config//third-party/cuda/constraints:12.8 \
  <buck target> -- <program args>

Hopper (h100a):

bash
buck2 run @mode/opt -m ovr_config//triton:beta \
  -c fbcode.nvcc_arch=h100a \
  <buck target> -- <program args>

With env vars forwarded (e.g. enabling a feature for the run):

bash
SOME_ENV=1 buck2 run @mode/opt -m ovr_config//triton:beta -c fbcode.nvcc_arch=b300a \
  -m ovr_config//third-party/cuda/constraints:13.0 \
  <buck target> -- <program args>

Compile only (surface a build/compile failure without running):

bash
buck2 build @mode/opt -m ovr_config//triton:beta -c fbcode.nvcc_arch=b300a \
  -m ovr_config//third-party/cuda/constraints:13.0 \
  <buck target>

© 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

Just SKILL.md in .claude/skills/running-with-buck of facebookexperimental/triton.

Open the folder on GitHubat commit 37301d4

Compare with similar skills

Running With Buck 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.

Running With Buck compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Running With Buck this skillfacebookexperimental/triton201—~998Automated safety check: PassMIT
Esmfold2JimLiu/science-skills2284 repos~2.5kAutomated safety check: PassApache-2.0
MUSA GPU Training Optimizeropen-infra-skills/infra-skills141—~1.7kAutomated safety check: PassApache-2.0
Benchmark TuneMesh-LLM/mesh-llm3.5k—~1.6kAutomated safety check: PassApache-2.0
Cuda Kernel OptimizerKernelFlow-ops/cuda-optimized-skill214—~4.3kAutomated safety check: PassMIT
Hugging Face Local Modelshuggingface/skills11k3 repos~945Automated safety check: PassApache-2.0

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    228 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • MUSA GPU Training Optimizer

    open-infra-skills/infra-skills

    Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.

    141 GitHub stars~1.7k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Benchmark Tune

    Mesh-LLM/mesh-llm

    A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…

    3.5k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Cuda Kernel Optimizer

    KernelFlow-ops/cuda-optimized-skill

    Iteratively optimize a CUDA/CUTLASS/Triton kernel only when strict on-device compilation, correctness, timing, and NCU evidence gates pass.

    214 GitHub stars~4.3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Models

    huggingface/skills

    Official

    Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.

    11k GitHub starsUsed in 3 repos~945 tokens
    AI & LLM EngineeringAuto-check passed

  • Areno Develop Kernel

    inclusionAI/AReno

    Develop, optimize, debug, and validate an AReno CUDA, Triton, fused, attention, convolution, routing, or MoE operator.

    323 GitHub stars~498 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from facebookexperimental/triton

All 18 skills in this repo

  • Amd Att Trace

    facebookexperimental/triton

    Official

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

    201 GitHub stars~733 tokensUpdated today
    Auto-check passed

  • 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

Works with

Categories

Questions about Running With Buck

What does Running With Buck do?

How to build and run GPU targets under Buck in fbcode. An agent skill from facebookexperimental/triton. Running With Buck is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. How to build and run GPU targets under Buck in fbcode.

When should I use Running With Buck?

Running With Buck fits situations like: invoking buck2 run / buck2 build for any GPU benchmark; kernel — selecting the GPU architecture and CUDA version; using @mode/opt and the beta Triton modifier; passing environment variables through.

How do I install Running With Buck in Claude Code?

Run `npx skills add facebookexperimental/triton --skill running-with-buck -a claude-code`. Or copy the skill folder (.claude/skills/running-with-buck in facebookexperimental/triton) into .claude/skills/running-with-buck in your project. Claude Code loads it when a task matches its description.

How do I install Running With Buck in Codex?

Run `npx skills add facebookexperimental/triton --skill running-with-buck -a codex`. Or copy the skill folder (.claude/skills/running-with-buck in facebookexperimental/triton) into .agents/skills/running-with-buck in your project. Codex loads it when a task matches its description.

Can I use Running With Buck 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 running-with-buck -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/running-with-buck, .gemini/skills/running-with-buck, .github/skills/running-with-buck and .opencode/skills/running-with-buck in your project.

What does Running With Buck need to run?

SKILL.md names no scripts, command-line tools or credentials: Running With Buck is instructions for the agent only.

Does Running With Buck 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 Running With Buck 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. Review the folder before installing.

What licence does Running With Buck use?

Running With Buck 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 Running With Buck use?

About 998 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Running With Buck?

Skills that share tags, products or a category with Running With Buck: Esmfold2 (JimLiu/science-skills, 228 stars), MUSA GPU Training Optimizer (open-infra-skills/infra-skills, 141 stars), Benchmark Tune (Mesh-LLM/mesh-llm, 3.5k stars) and Cuda Kernel Optimizer (KernelFlow-ops/cuda-optimized-skill, 214 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Running With Buck?

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 11, 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.