Agent skill

Triton Generate Artifacts

by toyaix in toyaix/triton-runner

Generate Triton Runner ttir, ttgir, llir, ptx, cubin, and metadata artifacts inside examples/runner/vX.Y.Z for the active Triton version and the current machine's GPU capability.

MITAuto-check passed

Install Triton Generate Artifacts

skills CLI
$ npx skills add toyaix/triton-runner --skill triton-generate-artifacts -a claude-code

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

GitHub CLI
$ gh skill install toyaix/triton-runner triton-generate-artifacts --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/toyaix/triton-runner.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/triton-generate-artifacts .claude/skills/triton-generate-artifacts && 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
triton-generate-artifacts
GitHub stars
100
Token cost
~471 tokens
SKILL.md length
159 words
Files
3 (incl. scripts)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Generate Triton Runner ttir, ttgir, llir, ptx, cubin, and metadata artifacts inside examples/runner/vX.Y.Z for the active Triton version and the current machine's GPU capability.

  • Works in 5 steps: Confirm the active Triton version with… → Use the bundled generator script in this… → Default to the current machine's GPU… → …
  • Publishing a new Triton versions runner artifacts
  • SKILL.md covers Workflow, Commands and Validation
  • Runs Python scripts from its folder; calls python

What it does

Triton Generate Artifacts is an agent skill from toyaix/triton-runner. Generate Triton Runner ttir, ttgir, llir, ptx, cubin, and metadata artifacts inside examples/runner/vX.Y.Z for the active Triton version and the current machine's GPU capability. Use when publishing a new Triton version's runner artifacts, regenerating checked-in example kernels, or producing compile-only artifacts for extra NVIDIA capabilities on another machine.

Its SKILL.md is about 470 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/generate_runner_artifacts.py`).

It works with NVIDIA AI Platform. The repository describes itself as: Multi-Level Triton Runner supporting Python, IR, PTX, AMDGCN, cubin and hasco. The licence is MIT.

When your agent uses it

  • Publishing a new Triton versions runner artifacts
  • Regenerating checked-in example kernels
  • Producing compile-only artifacts for extra NVIDIA capabilities on another machine

Example prompts

  • “s GPU capability. Use when publishing a new Triton version”
  • “/triton-generate-artifacts”

Requirements

  • Python 3

Workflow steps

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

  1. Confirm the active Triton version with python -c "import triton; print(triton.version)".
  2. Use the bundled generator script in this skill as the source of truth.
  3. Default to the current machine's GPU capability only.
  4. Generate extra capabilities only when the user explicitly asks for them.
  5. Keep README commands pointing at checked-in static artifacts; use this skill only to produce or refresh those files.

What it can do on your machine

Read from SKILL.md and the folder at commit ef0efe9. 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

Triton Generate Artifacts loads about 471 tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 159 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~471

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 toyaix/triton-runner at commit ef0efe9, republished under its MIT licence (© toyaix). 159 words, ~471 tokens.

Download SKILL.mdSave it as .claude/skills/triton-generate-artifacts/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
triton-generate-artifacts
description
Generate Triton Runner ttir, ttgir, llir, ptx, cubin, and metadata artifacts inside examples/runner/vX.Y.Z for the active Triton version and the current machine's GPU capability. Use when publishing a new Triton version's runner artifacts, regenerating checked-in example kernels, or producing compile-only artifacts for extra NVIDIA capabilities on another machine.

Triton Generate Artifacts

Use this skill when the task is to generate or refresh versioned runner artifacts under examples/runner/vX.Y.Z.

Workflow

  1. Confirm the active Triton version with python -c "import triton; print(triton.__version__)".
  2. Use the bundled generator script in this skill as the source of truth.
  3. Default to the current machine's GPU capability only.
  4. Generate extra capabilities only when the user explicitly asks for them.
  5. Keep README commands pointing at checked-in static artifacts; use this skill only to produce or refresh those files.

Commands

From the repository root:

bash
python skills/triton-generate-artifacts/scripts/generate_runner_artifacts.py

To target explicit capabilities:

bash
python skills/triton-generate-artifacts/scripts/generate_runner_artifacts.py 75 80 86 90 120

To target another Triton version directory without changing the environment:

bash
python skills/triton-generate-artifacts/scripts/generate_runner_artifacts.py --version 3.7.0 75

Validation

  • Verify the target version directory contains ttir, ttgir, llir, ptx, and cubin outputs plus metadata json where applicable.
  • For the local machine capability, run the corresponding README example commands when GPU execution is available.
  • For extra capabilities generated via compile-only override, validate file presence and metadata arch and triton_version instead of runtime execution.

© toyaix, 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 2 other files (scripts) in skills/triton-generate-artifacts of toyaix/triton-runner.

  • SKILL.md
  • agents/openai.yaml
  • scripts/generate_runner_artifacts.py

Open the folder on GitHubat commit ef0efe9

Compare with similar skills

Triton Generate Artifacts 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.

Triton Generate Artifacts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Triton Generate Artifacts this skilltoyaix/triton-runner100—~471Automated safety check: PassMIT
LLM Torch Profiler Analysissgl-project/sglang37k2 repos~6.4kAutomated safety check: PassApache-2.0
Skill InspectorNVIDIA/SkillSpector20k—~1.8kAutomated safety check: PassApache-2.0
Megatron-LM Container and Dependency SetupNVIDIA/Megatron-LM18k—~2.6kAutomated safety check: PassApache-2.0
Embeddings via 9Routerdecolua/9router31k—~604Automated safety check: PassMIT
Megatron-LM Base Image BumpNVIDIA/Megatron-LM18k—~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • LLM Torch Profiler Analysis

    sgl-project/sglang

    Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

    37k GitHub starsUsed in 2 repos~6.4k tokens
    DevelopmentAuto-check passed
  • Skill Inspector

    NVIDIA/SkillSpector

    Official

    Decides whether an agent skill is safe to install by combining a SkillSpector static scan with the agent's own source review, ending in APPROVE, CAUTION or REJECT.

    20k GitHub stars~1.8k tokensUpdated today
    SecurityAuto-check passed
  • Official

    Walks an agent through working inside the Megatron-LM CI container and changing dependencies with uv, so lock files resolve the same locally and in CI.

    18k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Embeddings via 9Router

    decolua/9router

    Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

    31k GitHub stars~604 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Megatron-LM Base Image Bump

    NVIDIA/Megatron-LM

    Official

    Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.

    18k GitHub stars~2.8k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Remove bracketed NemoClaw tags from GitHub issue and PR titles.

    23k GitHub stars~693 tokensUpdated today
    Marketing & SEOAuto-check passed

More from toyaix/triton-runner

  • Triton Version Support

    toyaix/triton-runner

    Add, fix, or validate Triton Runner support for an exact Triton version.

    100 GitHub stars~1.1k tokensUpdated 24 days ago
    Auto-check passed

Questions about Triton Generate Artifacts

What does Triton Generate Artifacts do?

Generate Triton Runner ttir, ttgir, llir, ptx, cubin, and metadata artifacts inside examples/runner/vX.Y.Z for the active Triton version and the current machine's GPU capability. Triton Generate Artifacts is an agent skill from toyaix/triton-runner.Z for the active Triton version and the current machine's GPU capability.

When should I use Triton Generate Artifacts?

Triton Generate Artifacts fits situations like: publishing a new Triton versions runner artifacts; regenerating checked-in example kernels; producing compile-only artifacts for extra NVIDIA capabilities on another machine.

How do I install Triton Generate Artifacts in Claude Code?

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

How do I install Triton Generate Artifacts in Codex?

Run `npx skills add toyaix/triton-runner --skill triton-generate-artifacts -a codex`. Or copy the skill folder (skills/triton-generate-artifacts in toyaix/triton-runner) into .agents/skills/triton-generate-artifacts in your project. Codex loads it when a task matches its description.

Can I use Triton Generate Artifacts 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 toyaix/triton-runner --skill triton-generate-artifacts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/triton-generate-artifacts, .gemini/skills/triton-generate-artifacts, .github/skills/triton-generate-artifacts and .opencode/skills/triton-generate-artifacts in your project.

What does Triton Generate Artifacts need to run?

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

Does Triton Generate Artifacts 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 Triton Generate Artifacts 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 Triton Generate Artifacts use?

Triton Generate Artifacts 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 Triton Generate Artifacts use?

About 471 tokens (SKILL.md is roughly 1.9k 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 Triton Generate Artifacts?

Skills that share tags, products or a category with Triton Generate Artifacts: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Skill Inspector (NVIDIA/SkillSpector, 20k stars), Megatron-LM Container and Dependency Setup (NVIDIA/Megatron-LM, 18k stars) and Embeddings via 9Router (decolua/9router, 31k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Triton Generate Artifacts?

toyaix (a GitHub organization) maintains it in toyaix/triton-runner, which has 100 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 17, 2026.

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