Ready to supercharge your AI agents?

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

Aas Reproducibility · brycewang-stanford | DecimalAI

scienceby brycewang-stanford

Aas Reproducibility

brycewang-stanford/aas-reproducibility

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

当你在为《自动化学报》(Acta Automatica Sinica, AAS) 提升实验可复现性、组织复现包、防范数据污染时调用。覆盖环境与依赖固定、随机种子与多次运行、数据划分与防泄露、控制仿真的求解器/步长/系统参数记录、超参数与调参协议披露、以及配合双盲的匿名化复现材料，帮助控制/自动化/模式识别方向的中文稿在 Acta Automatica Sinica 外审中经得起"结果能否复现"的追问。

SkillScore82Maintained

Automatic

Research pack

Last verified 8/15/2026

What it changes

Passed 18 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill82%

Checks it passed that the model alone missed

Explicitly marks the mandatory code submission requirement status as 待核实.
Requires logging sampling period, controller hardware model, and sensor specification details.
Mandates giving baseline algorithms equal parameter tuning effort and disclosing hyperparameter search spaces.

3 fixed15 passed either way4 still failing0 broke

Pass-rate lift: +14 pp
Tokens: +56%
Agent turns: 0%
Response time: +1%

Model gemini-3.6-flashMeasured 8/15/2026v118 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-aas-reproducibility/SKILL.md https://app.decimal.ai/s/brycewang-stanford-aas-reproducibility/SKILL.md

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

decimalai skills add brycewang-stanford-aas-reproducibility

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

请问《自动化学报》目前对于投稿时是否必须强制提交完整的源程序和仿真数据集有什么最新的官方强制命令？

What was checked, without and with the skill
Checked	Without skill	With skill
Explicitly marks the mandatory code submission requirement status as 待核实.	Missed	Passed

case-16 · 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.md116 linessingle file

《自动化学报》可复现性与实验可重复

本技能帮你把投向《自动化学报》(Acta Automatica Sinica, AAS) 的实验做到可复现。外审常问"换个人能否复现你的结果"，控制类还要能复现稳定性与性能结论。以下方法于 2026-07-09 核验框架（见 resources/official-source-map.md）；本刊是否强制提交复现材料 待核实。

一、可复现性三支柱

支柱	内容
环境可复现	语言/库版本、系统、硬件、随机种子固定
数据可复现	数据来源、划分、预处理脚本、校验和
流程可复现	从原始数据到论文图表的一键脚本

二、环境与依赖固定

记录语言与关键库版本（Python/MATLAB、控制/学习框架），提供 requirements.txt/environment.yml 或 Dockerfile。
控制仿真额外记录：仿真器与版本、求解器类型、积分步长、系统模型参数、初始条件。
硬件：CPU/GPU 型号、内存；实物实验记录采样周期、控制器硬件与传感器型号。

三、随机性与多次运行

固定随机种子；对随机性强的实验（强化学习、随机初始化的识别模型）报告多次运行的均值与方差。
说明随机来源（初始化、数据打乱、探索噪声）与控制方式；不要只报单次最好结果。

四、数据划分与防污染

风险	防范
测试集调参	只在验证集调参，测试集仅最终评测一次
数据泄露	划分在预处理前，防未来信息进训练
重复样本跨集	去重，确认训练/测试无交叠
分布偏移未披露	说明训练与测试分布差异

五、复现包组织（配合双盲）

repro/
  README.md      # 环境、数据、运行、预期结果、硬件

Track record

Benchmark

18 / 22

test cases passed, vs 15 / 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-Automatica-Sinica-Skills/skills/aas-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.