research by brycewang-stanford
选题（ceq-topic-selection） brycewang-stanford/ceq-topic-selection
Use when shaping or sharpening a 《经济学(季刊)》 (China Economic Quarterly, CEQ) research question — turning data/correlation into a clean causal, model-able, internationally-legible topic that a field economist can recognize as a contribution. Use before literature review and identification.
What it changes View full report → Passed 12 of 22 test cases with the skill, and 3 of 22 without it.
Without skill 14%
With skill 55%
Checks it passed that the model alone missed and 19 more in the full report
11 fixed1 passed either way8 still failing2 broke
Pass-rate lift +41 pp
Tokens +26%
Agent turns 0%
Response time -1% Model gemini-3.6-flashMeasured 9/1/2026 v1 12 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-ceq-topic-selection/SKILL.md https://app.decimal.ai/s/brycewang-stanford-ceq-topic-selection/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-ceq-topic-selection, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/brycewang-stanford-ceq-topic-selection/ and pins it in .decimal/skills.lock
$ decimalai skills add brycewang-stanford-ceq-topic-selectionCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-ceq-topic-selection/SKILL.md https://app.decimal.ai/s/brycewang-stanford-ceq-topic-selection/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt 我想探讨环境规制政策如何影响重污染企业的异质性生产率。目前的想法比较偏向数据回归，缺乏可证伪的理论机制与一般性贡献。请帮我初筛并重塑这个选题，输出格式要求写出：研究问题的单句表述、外生识别冲击来源、关键机制命题、国际同行对话能力（强/弱）、选题可行性建议（推进/重塑及缺失要素），以及后续推荐的对接流程。
What was checked, without and with the skill Checked Without skill With skill Contains the section tag 【一句话问题】 Contains the section tag 【外生变异来源】 Contains the section tag 【核心机制命题】 Contains the section tag 【国际可对话性】 Contains the section tag 【建议】 Designates ceq-literature-review as the next step
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 93 lines single file
选题（ceq-topic-selection）
触发时机
有数据/相关性，但没有"可识别的因果问题"
选题像政策评估或行业描述，缺机制
不确定问题能否让 field 同行立刻看懂贡献
CEQ 选题的三个硬条件
干净因果 ：存在可信的处理/外生变异（政策冲击、断点、自然实验、强工具）。可建模 ：问题能写成一个机制清晰的（结构或简约）模型，含可检验命题。国际可对话 ：问题表述去本土包装后，field 同行仍能识别其一般性贡献。
三者缺一，选题就要重塑而非硬写。
从弱选题到强选题（对照）
选题前置三问
变异从哪来 ？说不出外生变异来源 → 回 ceq-identification 先找设计。机制是什么 ？只有"相关"没有渠道 → 选题不成立。谁会读、为何在意 ？只有本土读者在意 → 重塑为一般性问题。
自检清单
反模式
Track record Benchmark 12 / 22
test cases passed, vs 3 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported brycewang-stanford / awesome-journal-skills
China-Economic-Quarterly-Skills/skills/ceq-topic-selection/SKILL.md
View on GitHub ↗ License MITImported 8/10/2026Version v1