Ready to supercharge your AI agents?

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

Aas Experiments · brycewang-stanford | DecimalAI

scienceby brycewang-stanford

Aas Experiments

brycewang-stanford/aas-experiments

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

当你在为《自动化学报》(Acta Automatica Sinica, AAS) 设计与呈现实验、仿真或实物验证时调用。覆盖研究问题(RQ)驱动的实验设计、公平基线与对照、控制类的稳定性/收敛性/鲁棒性分析、模式识别类的指标与统计显著性、消融实验、仿真与实物平台的报告要素，帮助为控制理论、机器人、智能系统方向的中文稿搭建经得起 Acta Automatica Sinica 双盲外审的实证与理论证据链。

SkillScore82Maintained

Automatic

Research pack

Last verified 8/15/2026

What it changes

Passed 17 of 21 test cases with the skill, and 13 of 21 without it.

Without skill64%

With skill82%

Checks it passed that the model alone missed

Includes explicit ablation experiments testing individual design components.
Recommends box plots to visualize statistical variance across multiple runs.
Requires ablation studies isolating component contribution from gain tuning.

and 3 more in the full report

4 fixed14 passed either way4 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +67%
Agent turns: 0%
Response time: +6%

Model gemini-3.6-flashMeasured 8/15/2026v118 of 22 cases passed with skill · 21 comparable

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-experiments/SKILL.md https://app.decimal.ai/s/brycewang-stanford-aas-experiments/SKILL.md

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

decimalai skills add brycewang-stanford-aas-experiments

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

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

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

I am preparing a control manuscript on adaptive sliding mode control for a non-linear system targeting Acta Automatica Sinica (《自动化学报》). I need you to draft a comprehensive experimental and simulation plan. Please format the output as a structured outline that details research questions, validation flows combining theoretical proofs with simulations, criteria for selecting fair baselines, a parameter sensitivity setup, and an evaluation self-check list.

What was checked, without and with the skill
Checked	Without skill	With skill
Includes explicit ablation experiments testing individual design components.	Missed	Passed
Requires combining theoretical Lyapunov stability proofs with numerical simulation validation.	Passed	Passed
Includes testing parameter uncertainty scanning to identify failure boundaries.	Missed	Passed

case-01 · 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.md118 linessingle file

《自动化学报》实验与仿真设计

本技能帮你为《自动化学报》(Acta Automatica Sinica, AAS) 搭建经得起双盲外审的证据链。控制/自动化稿件的证据不只是"跑得好"，还包括理论保证（稳定性、收敛性）与公平对照。以下方法于 2026-07-09 核验框架（见 resources/official-source-map.md）。

一、RQ 驱动的实验设计

先把要回答的研究问题写清，再据此设计实验：

RQ1 所提控制律是否保证闭环稳定/收敛？——理论证明 + 仿真验证
RQ2 相比基线，性能指标是否显著改进？——对比实验 + 定量指标
RQ3 各设计模块是否必要？——消融实验
RQ4 对扰动/参数摄动是否鲁棒？——鲁棒性/敏感性实验

二、公平基线与对照

要点	做法
基线选择	选最接近、最强的已有方法，非弱化版稻草人
同等条件	相同系统模型、初始条件、噪声、算力预算
调参公平	基线也认真调参，报告调参协议
多场景	多个被控对象/数据集，避免单点结论

三、控制类证据（理论 + 仿真 + 实物）

稳定性/收敛性分析：给出 Lyapunov 或等价工具的严格证明，明确假设与充分条件。
性能指标：稳态误差、超调量、调节/收敛时间、控制能量、跟踪误差范数等，口径统一。
仿真：写清仿真器（MATLAB/Simulink、Python 控制库）、步长、求解器、参数。
实物实验（若有）：硬件平台、采样周期、传感器、标定、重复次数与方差。

四、模式识别/学习类证据

指标：准确率、精确率/召回、F1、mAP、误差率等，按任务选取并说明。
统计严谨：多次运行报告均值±方差，必要时做显著性检验；避免单次最好值。
数据划分：训练/验证/测试清晰，防数据泄露与测试集调参（见 aas-reproducibility）。
公平算力：对比方法在相近算力/数据下评测。

Track record

Benchmark

17 / 21

test cases passed, vs 13 / 21 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-experiments/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.