Use when designing the real-data validation of a 《中国管理科学》 (Chinese Journal of Management Science) manuscript — forecasting and financial-engineering strands: data provenance, rolling out-of-sample tests, benchmark batteries, and significance of improvement. Validates methods on data; simulation-based studies belong to cjms-numerical-experiments.
SkillScore64Maintained
Automatic
◆Research pack
Last verified 9/2/2026
What it changes
Passed 14 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill64%
Checks it passed that the model alone missed
The next step section explicitly refers to cjms-managerial-insights.
The response identifies the absence of a naive baseline such as an equal-weight strategy.
The response specifies constructing a specification curve (spec_curve) for parameter sensitivity.
and 3 more in the full report
5 fixed9 passed either way8 still failing0 broke
Pass-rate lift
+23 pp
Tokens
+58%
Agent turns
0%
Response time
+10%
Model gemini-3.6-flashMeasured 9/2/2026v214 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.