Install any skill in seconds. Free to start, no credit card required.
Get Started Free →shinpr/skill-optimization
Evaluates and optimizes skill file quality using 8 content patterns and 9 editing principles.
Passed 19 of 22 test cases with the skill, and 13 of 22 without it.
and 6 more in the full report
6 fixed13 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
在创建新规程的分析检查点(Analysis Checkpoint)时,必须达成哪些条件才能开始编写具体细节?
| Checked | Without skill | With skill |
|---|---|---|
| Verifies raw requirements are documented and pattern criteria BP-001 through BP-009 are evaluated | Missed | Passed |
| Ensures no unresolved missing inputs block faithful execution | Missed | Passed |
The instructions your model reads when the skill loads.
会直接降低 LLM 使用该技能时执行准确性的问题。
| 检测 | 转换 |
|---|---|
| 技能指令中出现“不要”、“禁止”、“永远不要”、“避免” | 首先陈述期望的动作或允许的状态。仅当违反行为是不可逆的操作性动作、调用方通常无法恢复、且纯正向改写会模糊边界时,才保留明确的禁止性表述。将禁止性表述与安全替代方案以及允许跨越该边界的条件配对。可评审的质量策略应改写为正向形式。 |
例外边界示例:
质量策略、角色边界、评分标准和一般工作规则始终使用正向表达。调用方会校验、覆盖或丢弃的输出永远不是不可逆的。
技能示例:
userId 而非 x)”为何对技能而言是关键问题:仅有禁止性表述,会使可执行的目标状态无从确定。
| 检测 | 转换 |
|---|---|
| 模糊用词(“恰当”、“良好”、“合适”、“最佳”、“应当清晰”)遗留了一个预期成果所需的决策,且不同的合理解读会实质性改变执行或验证方式 | 按照下面的解决步骤,用限制最少但足够充分的标准来解决 |
test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.