Use when building the robustness section for a 《会计研究》 (Accounting Research) manuscript — replacing accounting measures with alternatives, adding governance / institutional controls, placebo tests, and endogeneity follow-ups — so the main result survives an accounting referee's scrutiny. Use after mechanism is settled.
SkillScore74Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 17 of 23 test cases with the skill, and 13 of 23 without it.
Without skill57%
With skill74%
Checks it passed that the model alone missed
The response specifies evaluating sensitivity after excluding ST firms.
The response recommends placing the comprehensive executed battery in an appendix.
The response recommends invoking audit_result on the estimation handle to identify missing diagnostic checks.
and 1 more in the full report
4 fixed13 passed either way6 still failing0 broke
Pass-rate lift
+17 pp
Tokens
+56%
Agent turns
0%
Response time
-8%
Model gemini-3.6-flashMeasured 8/15/2026v117 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
An empirical analysis workflow maintains a statistical result handle `res_main_did` representing the baseline regression model. The researcher needs to systematically audit missing diagnostic steps and obtain recommended diagnostic functions. Which handle auditing method should be used?
What was checked, without and with the skill
Checked
Without skill
With skill
The response recommends invoking audit_result on the estimation handle to identify missing diagnostic checks.
Missed
Passed
case-20 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md94 linessingle file
稳健性与敏感性（acr-robustness）
触发时机
主结果只跑了一种度量、一套控制变量
没替换会计度量、没控治理/制度变量
内生性只在主表处理，未做后续敏感性
审稿人质疑"结果是否对度量/设定敏感"
本刊稳健性的四个支柱
替换会计度量：主度量换替代（如 DA 换真实盈余管理、C-Score 换 Basu、披露指数换文本指标），结论不变
Use when finalizing tables and figures for a 《会计研究》 (Accounting Research) manuscript — keeping the main table lean, reporting coefficients with the right precision, and interpreting economic magnitude (not just significance stars) for accounting measures. Use after robustness is settled.