Quark Torch Router

What it does

When your agent uses it

• A user describes a Quark task in plain language — such as install Quark
• Quantize a model
• Analyze my model
• Build a PTQ plan

Example prompts

• “install Quark”
• “quantize a model”
• “analyze my model”
• “/quark-torch-router”

Workflow steps

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

1. 1Extract the core intent. Strip away filler and figure out what the user actually needs. "I want to quantize Llama-2 with INT4" → the…
2. 2Check for L0 prerequisites. Before routing to an L1 skill, check if the downstream skill needs facts that are missing
3. 3Pick the smallest fit. If the user only wants to check their model's architecture, route to quark-torch-model-intake — do not send them…
4. 4Handle ambiguity honestly. If the goal is unclear, record the likely routes in open_questions and ask the user. Example: "I want to set up…

What it can do on your machine

Read from SKILL.md and the folder at commit 313cb0b. 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 json).

  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

Quark Torch Router loads about 1.9k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 842 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~139

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

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

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 amd/Quark at commit 313cb0b, republished under its MIT licence (© amd). 842 words, ~1,869 tokens.

name

quark-torch-router

description

Route Quark user goals to the correct atomic skill or workflow. Use when a user describes a Quark task in plain language — such as "install Quark", "quantize a model", "analyze my model", "build a PTQ plan", "export the quantized model", "debug a failed run", "run the full PTQ pipeline", "run model quantization", "install Quark", or any request that involves AMD Quark model quantization. This is the entry point skill — trigger it whenever the user's intent involves Quark and the correct downstream skill is not immediately obvious.

layer

l1-atomic

primary_artifact

session_context.json

source_knowledge

docs/source/install.rst, examples/torch/language_modeling/llm_ptq/README.md

{
  "user_goal": "Quantize Qwen/Qwen3-8B with FP8 and export to HuggingFace format",
  "workflow": "quark-torch-llm-ptq-workflow",
  "constraints": {
    "offline": false,
    "execution_mode": "interactive_execute"
  },
  "env_context_ref": null,
  "workspace_context_ref": null,
  "pytorch_install_result_ref": null,
  "quark_install_result_ref": null,
  "open_questions": [
    "GPU type and CUDA/ROCm version not yet confirmed — quark-env-preflight needed"
  ]
}

© amd, 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-impl/l1-atomic/torch/quark-torch-router of amd/Quark.

Open the folder on GitHubat commit 313cb0b