AF paper-to-pipeline
根据机器学习/深度学习论文的实验规划文档自动生成完整的 Python 实验 pipeline。支持数据预处理、模型构建、训练循环、评估指标、结果可视化。Use when user uploads an experiment plan document and wants to generate runnable PyTorch/TensorFlow/scikit-learn code.
As a process F 35/100 · Will not run — References files that are not bundled: assets/templates/text_classification.py, assets/templates/regression.py, assets/templates/clustering.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: assets/templates/text_classification.py - warning
missing-refreference to a missing file: assets/templates/regression.py - warning
missing-refreference to a missing file: assets/templates/clustering.py - warning
missing-refreference to a missing file: references/training-best-practices.md
Process rating: all ten parameters 35/100
- 0Tools and files. 4 referenced file(s) missing: assets/templates/text_classification.py, assets/templates/regression.py, assets/templates/clustering.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 597 tokens
- 100Running it twice. No mutating operations
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 194: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.