research by brycewang-stanford
文献与贡献定位(ceq-literature-review) brycewang-stanford/ceq-literature-review
Use when positioning a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript's contribution against the literature — benchmarking the precise method/result delta versus specific field papers (English + Chinese), not piling citations. Use after the topic is set and before/alongside identification.
What it changes View full report → Passed 17 of 23 test cases with the skill, and 6 of 23 without it.
Without skill 26%
With skill 74%
Checks it passed that the model alone missed Uses the output tag 【最接近文献】. Uses the output tag 【贡献一句话】. Uses the required tag 【贡献一句话】.and 14 more in the full report
12 fixed5 passed either way5 still failing1 broke
Pass-rate lift +48 pp
Tokens +21%
Agent turns 0%
Response time -22% Model gemini-3.6-flashMeasured 8/31/2026 v1 17 of 23 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-literature-review/SKILL.md https://app.decimal.ai/s/brycewang-stanford-ceq-literature-review/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-ceq-literature-review, 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-literature-review/ and pins it in .decimal/skills.lock
$ decimalai skills add brycewang-stanford-ceq-literature-reviewCopy
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-literature-review/SKILL.md https://app.decimal.ai/s/brycewang-stanford-ceq-literature-review/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 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt 我们在评估产业政策对企业全要素生产率的影响中,提出了一套可被后续研究复用的连续处理变量多期DID识别与估计规范。请帮忙提炼文献定位与贡献表达,按照最接近文献、本文差异、一句话贡献、方法源头、中英并重、下一步的结构返回。
What was checked, without and with the skill Checked Without skill With skill Identifies the contribution type as 方法范本 under 【本文差异】. Missed PassedUses the required tag 【贡献一句话】. Missed Passed
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 92 lines single file
文献与贡献定位(ceq-literature-review)
触发时机
综述只堆近年国内回归,没进 field 的方法/结论脉络
贡献写成"丰富了相关研究 / 填补国内空白"
说不清自己相对某篇具体文献做了什么新东西
CEQ 的文献观:定位,不是清单
文献综述的唯一目的是精确定位贡献 :你比 具体某篇 做得多/不同在哪。审稿人多有海外训练,会逐条核对你引的 field 文献是否到位、是否误读。
贡献陈述模板(对标具体文献)
不要写:"本文丰富了关于 X 的研究。"
要写:"相比 Author (Year, 期刊) 用 <方法> 得到 <结论>,本文用 <更干净的识别/新数据/新机制> 表明 <差异>,并解决了其 <未处理的内生性/异质性/外推问题>。"
贡献类型选一到两类讲清:
识别更可信 (更干净的外生变异 / 现代 DID / 强工具)
机制更明确 (区分竞争渠道 / 给出可证伪含义)
新参数/新事实 (估计一个此前未识别的结构参数或因果量)
方法范本 (识别策略或计量应用本身可被复用)
中英文献并重
必引 field 的方法/理论源头 (识别方法的原始文献、相关机制的经典理论),不能只引应用文章。
国内文献用来定位"本土证据缺口",但不能替代国际对话。
DID/IV/RDD 现代计量文献的引用见 ceq-modern-did 与 ceq-inference,方法用了就要引对应方法论文。
自检清单
反模式
综述按时间流水账(A,2020;B,2021;C,2022)
Track record Benchmark 17 / 23
test cases passed, vs 6 / 23 without
Adoption
Users 1
Times used 49 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-literature-review/SKILL.md
View on GitHub ↗ License MITImported 8/10/2026Version v1