How do I install the Triton Generate Artifacts skill?

Run npx skillmds@latest add tomevault-io/triton-generate-artifacts in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Triton Generate Artifacts safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Triton Generate Artifacts?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Triton Generate Artifacts free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Triton Generate Artifacts?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Triton Generate Artifacts by tomevault-io

Name: Triton Generate Artifacts
Author: tomevault-io

Triton Generate Artifacts

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. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Triton Generate Artifacts

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

Workflow

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

Commands

From the repository root:

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

To target explicit capabilities:

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:

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.

Source: toyaix/triton-runner — distributed by TomeVault.

---name: triton-generate-artifactsdescription: 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. Use when this capability is needed.---# Triton Generate ArtifactsUse this skill when the task is to generate or refresh versioned runner artifacts under `examples/runner/vX.Y.Z`.## Workflow1. 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.## CommandsFrom the repository root:```bashpython skills/triton-generate-artifacts/scripts/generate_runner_artifacts.py```To target explicit capabilities:```bashpython skills/triton-generate-artifacts/scripts/generate_runner_artifacts.py 75 80 86 90 120```To target another Triton version directory without changing the environment:```bashpython 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.---> Source: [toyaix/triton-runner](https://github.com/toyaix/triton-runner) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions

Triton Generate Artifacts

File contents

Triton Generate Artifacts

Workflow

Commands

Validation

Related skills

Frequently asked questions

How do I install the Triton Generate Artifacts skill?

What does the Triton Generate Artifacts skill do?

Is Triton Generate Artifacts safe to use?

Which AI agents work with Triton Generate Artifacts?

Is Triton Generate Artifacts free to use?

Who published Triton Generate Artifacts?