Ready to supercharge your AI agents?

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

沁言 Nature 投稿前预审 · leonchaox | DecimalAI

researchby leonchaox

沁言 Nature 投稿前预审

leonchaox/qinyan-nature-review

Source leonchaox/qinyan-academic-skills ↗License MIT

面向 Nature、Nature Communications 及高影响力期刊的可追溯投稿前评审技能。用于模拟同行评审、检查原创性与广泛意义、压力测试技术严谨性、核验主张—证据链、评估可重复性与表达清晰度，并生成带严重级别、证据指针和解决标准的审稿报告及交叉综合。触发场景包括 Nature review、模拟审稿、投稿前预审、peer review、reviewer report、manuscript critique、novelty assessment、rigour check、找论文问题和审稿意见模拟。

SkillScore68Maintained

Automatic

Research pack

Last verified 8/15/2026

What it changes

Passed 15 of 22 test cases with the skill, and 8 of 22 without it.

Without skill36%

With skill68%

Checks it passed that the model alone missed

Includes the exact field name Resolution test in issue blocks.
Includes the exact field name Issue key in the issue log card.
Uses NOT_LOCATABLE when pointing to unavailable evidence sources.

and 8 more in the full report

8 fixed7 passed either way6 still failing1 broke

Pass-rate lift: +32 pp
Tokens: +43%
Agent turns: 0%
Response time: -15%

Model gemini-3.6-flashMeasured 8/15/2026v115 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/leonchaox-qinyan-nature-review/SKILL.md https://app.decimal.ai/s/leonchaox-qinyan-nature-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add leonchaox-qinyan-nature-review, 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/leonchaox-qinyan-nature-review/ and pins it in .decimal/skills.lock

decimalai skills add leonchaox-qinyan-nature-review

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

curl -fsSL --create-dirs -o .claude/skills/leonchaox-qinyan-nature-review/SKILL.md https://app.decimal.ai/s/leonchaox-qinyan-nature-review/SKILL.md

Raw file: /s/leonchaox-qinyan-nature-review/SKILL.md ↗ · machine-readable summary at /s/leonchaox-qinyan-nature-review.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

Based on your evaluation of my biophysics draft, please provide an explicit editorial prediction on whether the journal will Accept, Reject, or request Major Revision.

What was checked, without and with the skill
Checked	Without skill	With skill
Refrains from predicting manuscript acceptance outcomes or editorial decisions.	Missed	Passed

case-14 · 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.md75 lines4 filesincludes scripts

沁言 Nature 投稿前预审

以审稿人的证据标准审查稿件，不扮演编辑、不预测录用，也不替作者编写回复信。

默认评审包

除非用户指定其他格式，生成：

Review setup：输入范围、评审边界、稿件核心命题和可见证据。
Lens A — Conceptual significance：问题重要性、原创性、广泛读者价值。
Lens B — Technical integrity：设计、方法、统计、对照、可重复性。
Lens C — Evidence and communication：主张—证据一致性、图文一致性、可读性与透明度。
Cross-review synthesis：共识、分歧、优先修复顺序和未能评估事项。

这些是评审视角，不是虚构的审稿人身份、机构或专业履历。

评审原则

只依据用户提供的稿件、图表、数据和已核验来源。
对每条实质性问题分配稳定 Issue key 和唯一 Concern ID。
为问题绑定 Claim pointer 与 Evidence pointer；缺失时写 NOT_LOCATABLE。
把“缺少材料无法判断”与“材料显示存在缺陷”分开。
只有同一 Issue key 被至少两个评审视角独立提出，才能称为共识。
给出可验证的 Resolution test，不只说“需要更多实验”。
不以写作风格问题掩盖科学问题，也不把偏好包装成硬性要求。

执行流程

界定输入。 说明收到全文还是部分章节，以及缺失材料对结论的影响。
抽取共享事实库。 记录核心命题、关键证据、目标读者、方法设计和作者承认的限制。
建立问题台账。 按评审维度登记证据位置、严重级别、适用性和解决标准。
执行三种视角。 共享事实，但分别强调概念、技术、证据与表达；避免人为制造分歧。
生成交叉综合。 合并相同问题，保留不同权重，按 P0/P1/P2 排序。
运行一致性校验。 把报告保存为 Markdown，执行 python scripts/review_consistency.py <report.md>。
交付边界。 明确哪些判断不能从当前材料得出，避免给出虚假编辑决定。

评审维度与严重级别读取 references/review-framework.md。报告字段与综合规则读取 references/report-contract.md。

严重级别

Track record

Benchmark

15 / 22

test cases passed, vs 8 / 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 — 8/3/2026

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

leonchaox / qinyan-academic-skills

skills/%E6%B2%81%E8%A8%80%E5%AD%A6%E6%9C%AFskills/qinyan-nature-review/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 3 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

leonchaox/qinyan-nature-writing面向 Nature、Nature Communications 及同等级综合期刊的证据驱动论文写作技能。用于从已核验的结果、图表、实验记录或中英文草稿构建标题、摘要、引言、结果、方法、讨论、结论和首次投稿材料；也用于重组论文论证、建立 claim–evidence map、控制声称边界和开展投稿前完整性检查。触发场景包括 Nature 写作、论文起草、章节重写、scientific writing、manuscript drafting、abstract、introduction、results narrative、discussion、cover letter、投稿材料。Close match+39 pp pass-rate lift

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

沁言 Nature 投稿前预审

默认评审包

评审原则

执行流程

严重级别

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills