Unverified50% confidenceFactExact time
程序性技能模拟器通过构建可量化评分维度将临床操作转化为可追踪数据，为形成性评估提供工具
1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen
Sources
Related Claims
Unverified锚定样本技术在评估提示词中加入已由人类专家标注明确分数的示例，覆盖评分量表各个档位，可帮助裁判模型准确理解评分标准73% similarUnverifiedThis Skill has built-in auxiliary scripts for scanning, scoring, and failure analysis, used to grade existing selector strategies and identify high-risk fragile selectors.70% similarUnverified赋予模型执行代码和工具调用的能力，使其能在数学、编程等有可验证奖励的领域进行搜索并显著提升表现70% similarUnverified"Doc-based Test Case Generator" is an AI Skill that can automatically generate structured test cases from documents, text, and screenshots and output Markdown files.69% similarUnverifiedUsers can objectively verify whether a model has degraded by building a personal "regression test set"—retaining a fixed set of representative prompts to periodically evaluate model output quality.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/556503API
curl https://kongchang.com/api/v1/knowledge/claims/556503MCP
get_claim(id=556503)