Quark Workspace Validate

What it does

When your agent uses it

• A skill needs confirmed file paths
• The user provides a model path
• Output directory
• You need to distinguish a local model from a HuggingFace ID

Example prompts

• “where should I put outputs”
• “is my model path right”
• “/quark-workspace-validate”

Workflow steps

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

1. 1Local directory — contains config.json, *.safetensors or *.bin files (e.g., /models/Llama-2-7b-hf/)
2. 2HuggingFace ID — format org/model-name (e.g., Qwen/Qwen3-8B)
3. 3Ambiguous — could be either (e.g., ./qwen3-8b might be a local dir or a typo)

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 and 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

Quark Workspace Validate loads about 1.3k tokens when it runs. Until then it costs about 120 tokens; SKILL.md has 497 words of instructions outside code blocks.

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

~120

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

~1.3k

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). 497 words, ~1,290 tokens.

name

quark-workspace-validate

description

Validate workspace shape, model paths, output directories, and repo structure before downstream Quark skills proceed. Use this skill whenever a skill needs confirmed file paths, when the user provides a model path or output directory, when you need to distinguish a local model from a HuggingFace ID, or when any path assumption is unverified. Also trigger for "where should I put outputs", "is my model path right", or before model-intake/export steps.

layer

l0-foundation

primary_artifact

workspace_context.json

source_knowledge

examples/torch/language_modeling/llm_ptq/README.md, examples/torch/language_modeling/llm_ptq/quantize_quark.py

{
  "model_path": "/models/Qwen3-8B",
  "model_source": "local",
  "trust_remote_code_required": false,
  "output_dir": "./output/qwen3-8b-fp8",
  "output_dir_exists": false,
  "output_dir_parent_writable": true,
  "disk_space_gb_free": 250,
  "quark_script_path": null
}

# Check model directory
ls -la /path/to/model/config.json 2>/dev/null
ls /path/to/model/*.safetensors 2>/dev/null

# Check output directory parent
test -d /path/to/output/.. && echo "parent exists"
test -w /path/to/output/.. && echo "parent writable"

# Check disk space (rough)
df -h /path/to/output/..

© 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/l0-foundation/shared/quark-workspace-validate of amd/Quark.

Open the folder on GitHubat commit 313cb0b