AC ptq
Use when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a quantized HuggingFace checkpoint from a pretrained model using ModelOpt. Do NOT use for multi-candidate recipe exploration or optimization (use quant-recipe-search).
Use when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4…
As a process C 50/100 · Has gaps — References files that are not bundled: examples/hf_ptq/README.md, examples/hf_ptq/hf_ptq.py
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: examples/hf_ptq/README.md - warning
missing-refreference to a missing file: examples/hf_ptq/hf_ptq.py
Process rating: all ten parameters 50/100
- 0Tools and files. 2 referenced file(s) missing: examples/hf_ptq/README.md, examples/hf_ptq/hf_ptq.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 85Steps. 27 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2657 tokens
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 397: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.