Ready to supercharge your AI agents?

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

Aes Reproducibility · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Aes Reproducibility

brycewang-stanford/aes-reproducibility

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

当你为《电子学报》(Acta Electronica Sinica, AES) 稿件强化可复现性与实验可重复时使用。覆盖电子/信息/信号处理/通信类工作的实验环境记录、随机性控制、数据与预处理透明、算法伪代码与超参数完整披露、硬件与仿真工具链版本、统计显著性与多次运行、以及在中文学报正文与附录里如何组织可复现信息。帮助作者用可复现性作为通过《电子学报》外审、抵御"结果无法重复"质疑的核心竞争力，而非事后补救。

SkillScore95Maintained

Automatic

Research pack

Last verified 8/15/2026

What it changes

Passed 21 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill95%

Checks it passed that the model alone missed

Assigns a low risk rating under Risk.
Output includes key-value field for 风险：
Output includes the key-value field 风险：

and 12 more in the full report

11 fixed10 passed either way1 still failing0 broke

Pass-rate lift: +50 pp
Tokens: +47%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 8/15/2026v121 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-aes-reproducibility/SKILL.md https://app.decimal.ai/s/brycewang-stanford-aes-reproducibility/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-aes-reproducibility, 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-aes-reproducibility/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-aes-reproducibility

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

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

Raw file: /s/brycewang-stanford-aes-reproducibility/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-aes-reproducibility.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

在引用《电子学报》关于可复现性及投稿指南中未单独详细列出细则的要求时，论文作者应当注意哪条核验标注提示？

What was checked, without and with the skill
Checked	Without skill	With skill
Directs verification against official ejournal.org.cn submission guidelines.	Missed	Passed
Marks unverified journal-specific items as 待核实.	Missed	Passed

case-11 · 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.md117 linessingle file

《电子学报》可复现性与实验可重复

可复现性是《电子学报》(Acta Electronica Sinica, AES) 外审专家评判一篇电子信息类论文成色的隐形主线。本刊由中国电子学会 (Chinese Institute of Electronics) 主办，审稿人多为领域内一线学者，最常见的退稿或退修理由之一就是"实验条件交代不清、结果难以重复"。本技能教你把可复现性前置到写作与实验设计阶段，而不是等审稿人质疑后再补。以下建议对齐通行的中文科技期刊规范；本刊未单独公布可复现性细则者标 待核实，以《投稿须知》为准（核验日 2026-07-09，官网 ejournal.org.cn）。

一句话：可复现性 = 让任何一个同行按你写的条件，能得到与你统计意义上一致的结果。这是 Acta / Electronica / Sinica 学报里区分"可信工作"与"疑似过拟合"的分水岭。

一、可复现信息的四大支柱

支柱	必须交代
环境	操作系统、语言/框架版本、关键库版本、硬件(CPU/GPU/FPGA/仪器)
数据	来源、规模、划分、预处理、是否公开、获取方式
方法	完整算法/伪代码、全部超参数、初始化、停止准则
评测	指标定义、运行次数、随机种子、统计处理

二、环境与工具链记录

明确记录仿真/开发工具及版本：MATLAB/Simulink、Python(含关键库)、ADS、HFSS/CST、Vivado/Quartus 等。
硬件实验记录器件型号、测量仪器型号与关键设置（采样率、带宽、触发方式）。
尽量提供 requirements.txt / environment.yml / Dockerfile（配合 aes-artifact-evaluation）。

三、随机性控制

固定并报告随机种子；对含随机初始化的算法，明确种子对结果的影响。
结果不应依赖某一"幸运种子"：对随机方法多次独立运行（如 ≥5 次），报告均值 ± 标准差。
数据划分（训练/验证/测试）方式固定并说明；避免测试集信息泄露到训练/调参。

四、数据透明

公开数据集给出名称、版本与出处；自采数据说明采集设备、条件、规模、标注协议。
预处理每一步（滤波、归一化、去噪、增强、重采样）都要可被复述，给出参数。
说明数据获取与使用的授权/伦理合规；敏感或涉密数据按脱敏要求处理。

五、方法可复现

Track record

Benchmark

21 / 22

test cases passed, vs 10 / 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

brycewang-stanford / awesome-journal-skills

Acta-Electronica-Sinica-Skills/skills/aes-reproducibility/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

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

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