Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

英文摘要与贡献陈述（ceq-abstract-english） · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

英文摘要与贡献陈述（ceq-abstract-english）

brycewang-stanford/ceq-abstract-english

Source brycewang-stanford/awesome-journal-skills ↗License MIT

Use when writing or polishing the English abstract and contribution statement for a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript — producing a tight English abstract (≤ ~100 words per the journal's guideline) that reads to a field economist and benchmarks the contribution against specific papers. Use at the polish stage, after identification and results are final.

SkillScore91Maintained

Automatic

Writing & Editing pack

Last verified 8/31/2026

What it changes

Passed 20 of 22 test cases with the skill, and 7 of 22 without it.

Without skill32%

With skill91%

Checks it passed that the model alone missed

The next step points to ceq-submission.
The diagnostic section contains 【套话命中】.
The evaluation includes the header 【五要素】.

and 20 more in the full report

14 fixed6 passed either way1 still failing1 broke

Pass-rate lift: +59 pp
Tokens: +36%
Agent turns: 0%
Response time: -16%

Model gemini-3.6-flashMeasured 8/31/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

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-abstract-english/SKILL.md https://app.decimal.ai/s/brycewang-stanford-ceq-abstract-english/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-ceq-abstract-english, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-ceq-abstract-english/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-ceq-abstract-english

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-ceq-abstract-english/SKILL.md https://app.decimal.ai/s/brycewang-stanford-ceq-abstract-english/SKILL.md

Raw file: /s/brycewang-stanford-ceq-abstract-english/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-ceq-abstract-english.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

提交给 CEQ 的稿件摘要拟包含 5 个关键词和 5 个 JEL 代码。请核对 CEQ 关于关键词和 JEL 代码的数量要求，并在诊断框中给出核查结果。

What was checked, without and with the skill
Checked	Without skill	With skill
The output specifies that exactly 3 keywords and 3 JEL codes are required.	Missed	Passed
The diagnostic report includes the check line 【关键词/JEL】.	Missed	Passed

case-14 · gemini-3.6-flash · 8/31/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md106 linessingle file

英文摘要与贡献陈述（ceq-abstract-english）

触发时机

英文摘要质量差 / 中式英语 / 超长
贡献写成"This paper enriches the literature on…"
定稿前，主结果与识别已确定

为什么重要

CEQ 很多读者只读英文摘要 + 图（见 ceq-figures）。英文摘要 = 你的门面。它必须让 field 经济学家在 100 词内看懂：问什么、怎么识别、发现什么、相对谁是新的。CEQ 规范：英文摘要不超过约 100 个单词，三个中英文关键词，三个 JEL 号（详见 resources/journal-profile.md）。

五句法（控制在 ~100 词）

问题：研究的因果问题（一句，去本土包装）。
设计：识别来源（"Using the staggered rollout of …, we …"）。
发现：量化主结果 + 单位（"… raises Y by X%"）。
机制：一句话渠道。
贡献/含义：相对最近文献的差异，或一句政策/理论含义。

好坏对照

黑名单（中式/空话）	白名单（field 可读）
"This paper enriches the literature."	"We provide the first credibly identified estimate of …"
"We use a series of robust methods."	"Using a regression discontinuity at the eligibility cutoff …"
"The results have important policy implications."	"A 10% increase in X reduces Y by 4%, implying …"
"Our study fills a gap in domestic research."	"Unlike Author (Year), who rely on OLS, we exploit …"

英文写作规范

主动语态、现在时陈述发现；避免冗长从句。
量化结果带单位与符号方向，别只说"significant"。
术语用 field 标准词（identification, parallel trends, instrument），不要直译中文。
不堆方法名词；识别策略一句带过即可。
中英文摘要表意一致，但英文不必逐句直译中文。

自检清单

英文摘要 ≤ ~100 词（按官网规范复核）

Track record

Benchmark

20 / 22

test cases passed, vs 7 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / awesome-journal-skills

China-Economic-Quarterly-Skills/skills/ceq-abstract-english/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

英文摘要与贡献陈述（ceq-abstract-english）

触发时机

为什么重要

五句法（控制在 ~100 词）

好坏对照

英文写作规范

自检清单

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills