Files
agent-skills/evals/cases/code-simplification.json
ayobamiseun f1f6fbf398 fix(code-simplification): say the skill applies when the code is pasted inline (#620)
One clause on the description: the skill applies when asked to
simplify, clean up or reduce the nesting of a function that already
works, even when the code is pasted inline. Two Tier 2 positives for
the clause, a fires and stays-quiet pair under evals/plugin/, and a
paragraph in evals/README.md with the measurements.

claude-opus-5-5 pinned, Claude Code 2.1.296, three runs per prompt per
description: the three simplification phrasings went from 0 of 9 to
8 of 9, five adjacent must-not-fire prompts stayed at 0 of 15 both
ways. On the graded pair the judge passed 3 of 3 with the plugin and
0 of 3 without.
2026-10-16 10:46:02 +01:00

54 lines
1.6 KiB
JSON

{
"skill_name": "code-simplification",
"trigger": {
"positive": [
{
"prompt": "This function works but it is way too clever, simplify it without changing behavior",
"top_k": 3
},
{
"prompt": "Reduce the complexity of this module so juniors can maintain it",
"top_k": 3
},
{
"prompt": "Clean up this working code, it has grown hard to follow",
"top_k": 3
},
{
"prompt": "Simplify this function, it works but it is hard to read.",
"top_k": 3
},
{
"prompt": "Clean this up, it works but it has grown hard to follow. Here is the function.",
"top_k": 3
}
],
"negative": [
{
"prompt": "Add a feature flag system to the app",
"owner": "incremental-implementation"
},
{
"prompt": "Diagnose why the build broke overnight",
"owner": "debugging-and-error-recovery"
}
]
},
"evals": [
{
"id": 1,
"prompt": "Simplify the provided 80-line function that parses config files, preserving exact behavior.",
"expected_output": "A simpler implementation with identical behavior and a summary of what was removed and why",
"files": [
"code-simplification"
],
"expectations": [
"Behavior is preserved (tests unchanged and passing, or equivalence argued concretely)",
"Complexity is reduced rather than relocated",
"The response explains what was removed and why it was safe",
"No new features are added during the simplification"
]
}
]
}