Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/additive-bias-defense
Inverts burden of proof for code additions.
Passed 19 of 22 test cases with the skill, and 6 of 22 without it.
and 13 more in the full report
14 fixed5 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
A PR adds null checks and fallback defaults to every line of an internal calculation function where inputs are strictly validated upstream by static typing and schema parsers. Evaluate this addition.
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the gold plating anti-pattern. | Missed | Passed |
| Evaluates what breaks without the redundant checks under scrutiny question 5. | Passed | Passed |
| Outputs a burden-of-proof verdict of unjustified. | Missed | Passed |
The instructions your model reads when the skill loads.
The default answer to "should we add this?" is no. The burden of proof is on the addition.
Note (#444): Frontmatter declares
provides.guidance, notprovides.contract. The scrutiny questions are consumed by partner skills (pensive:code-refinement,conserve:unbloat,imbue:scope-guard) that voluntarily embed them; no validator or hook in leyline enforces them directly. If a future contributor adds enforcement, restore thecontractlabel and link the validator path here.
conserve:bloat-detector)imbue:scope-guard)LLMs are additive by nature. They reinvent wheels, add unnecessary complexity, hallucinate issues and modify tests to justify them, and deviate from priorities. This contract provides a systemic defense.
Applied to every proposed addition (code, files, abstractions, error handling, configuration):
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.