Quark Onnx Shapeshifter Run

What it does

When your agent uses it

• Run ShapeShifter on my .onnx
• Apply an onnx pass
• Fold batch norm / simplify / convert opset / fuse LayerNorm on my ONNX model
• Preprocess my .onnx before quantization

Example prompts

• “run ShapeShifter on my .onnx”
• “apply an onnx pass”
• “preprocess my .onnx before quantization”
• “/quark-onnx-shapeshifter-run”

Workflow steps

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

1. 1Intake — confirm the input .onnx path exists, capture the requested transformation(s) and
2. 2Route — verify every requested pass is an ONNX pass (onnx_*) and exists in
3. 3Plan — present the YAML config (pass order + config keys) before writing. Confirm the config
4. 4Confirm — get approval before running the CLI (it writes the output file).
5. 5Execute or Summarize — write shapeshifter_config.yaml, run the CLI, then verify the output

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 yaml 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 Onnx Shapeshifter Run loads about 1.9k tokens when it runs. Until then it costs about 134 tokens; SKILL.md has 776 words of instructions outside code blocks.

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

~134

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). 776 words, ~1,922 tokens.

name

quark-onnx-shapeshifter-run

description

Apply existing ShapeShifter graph passes to an .onnx model via the quark-cli shapeshifter CLI or a ShapeShifter YAML. Trigger for "run ShapeShifter on my .onnx", "apply an onnx_ pass", "fold batch norm / simplify / convert opset / fuse LayerNorm on my ONNX model", "preprocess my .onnx before quantization", "postprocess my quantized .onnx for XINT8/NPU". Operates on .onnx only. NOT authoring a new pass (use quark-create-shapeshifter-pass), NOT full quantization (use quark-onnx-ptq), NOT PyTorch models.

layer

l1-atomic

backend

onnx

primary_artifact

shapeshifter_config.yaml

source_knowledge

docs/source/quark_shapeshifter.rst, docs/source/quark_shapeshifter_onnx_passes.rst, quark/shapeshifter/engine.py, quark/shapeshifter/utils.py…

input_model_path: /path/to/model.onnx
passes:
  onnx_convert_opset_version:
    target_opset_version: 21
  onnx_simplify:
    simplify: true
  onnx_fold_batch_norm:
    fold_batch_norm: true
output_model_path: /path/to/model_out.onnx

quark-cli shapeshifter shapeshifter_config.yaml

input_model_config:
  model_type: onnx        # discriminator
  input_model_path: /path/to/model.onnx
passes: { ... }
output_model_path: /path/to/model_out.onnx

© 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

SKILL.md and 1 other file in skills/_legacy_impl/l1-atomic/onnx/quark-onnx-shapeshifter-run of amd/Quark.

• SKILL.md
• evals/evals.json

Open the folder on GitHubat commit 313cb0b