Compressed caveman-style prose for AI coding agents — cuts ~65% output tokens while keeping full technical accuracy
96
100%
Does it follow best practices?
Impact
96%
1.00xAverage score across 38 eval scenarios
Passed
No known issues
{
"context": "Tests whether the response produces a correct modern pyproject.toml with all required configuration.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses pyproject.toml with build-system",
"description": "Includes [build-system] section with requires and build-backend pointing to setuptools",
"max_score": 12
},
{
"name": "Specifies Python version requirement",
"description": "Sets requires-python >= 3.10 in the [project] section",
"max_score": 10
},
{
"name": "Declares dependencies correctly",
"description": "Lists requests and click in the dependencies array under [project]",
"max_score": 10
},
{
"name": "Configures CLI entry point",
"description": "Sets up [project.scripts] with mycli = mypackage.cli:main",
"max_score": 12
},
{
"name": "Configures pytest",
"description": "Includes [tool.pytest.ini_options] or [project.optional-dependencies] with pytest for test configuration",
"max_score": 8
},
{
"name": "Valid TOML syntax",
"description": "The pyproject.toml is syntactically valid TOML",
"max_score": 8
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37