Research Experiment logo

Research Experiment

Community
HughYau
research-experiment

Design experiments that decide something, and diagnose failing ones by driving from surface symptom to root technical cause before changing anything. Treats improving a method as SGD on the idea, where the root-cause analysis IS the gradient — so it outputs a ranked candidate-cause table with a falsifying experiment for each, never a list of things to try, and ships a fully worked example diagnosis to show the granularity. Also covers minimum-viable exploratory design (binary feasibility criterion, one-day version), what comparison/ablation/demo experiments a paper needs, and which harder data to push to. Use whenever the user reports bad results, a method that doesn't work, metrics dropping after a change, asks what to run next, or asks which ablations a paper needs — and use it BEFORE proposing hyperparameter tweaks, because an unverified guess about the cause is a random gradient that burns a whole cycle. 中文触发:实验不work、效果不好、掉点了、做什么实验、实验设计、消融、ablation、baseline、调不出来、为什么不收敛、要不要试试调参、做什么demo。

Overview

PublisherHughYau
Repositorypengsida-learning-research-skills
Skill nameresearch-experiment
Stars
52
Forks
4
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by HughYau on GitHub. Read the source before you install it.

Installation

Install the Research Experiment AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/HughYau/pengsida-learning-research-skills/tree/main/research-experiment
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/HughYau/pengsida-learning-research-skills.git /tmp/pengsida-learning-research-skills
mkdir -p .claude/skills
cp -r /tmp/pengsida-learning-research-skills/research-experiment .claude/skills/research-experiment
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Research Experiment in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Research Experiment on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Research Experiment is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

实验设计与诊断

改进方法 = 对 idea 做 SGD。 目标函数 || Experiment(idea) − Target result ||, "分析实验为什么不 work" 就是求梯度。

由此得到唯一的效率判据:每次循环是否产出了一条经过验证的本质技术原因。 没有 → 这次循环的梯度是随机的,下一次改动等于掷骰子。 失败的实验不是浪费——它排除了一条路径,前提是那条路径被写下来了 (落进 experiments/LOG.md,见 research-project)。

一、设计实验

核心原则:减少 exploration points

一次实验里的未知量越多,结果越不可归因。两种分解,通常同时用:

分解 pipeline分解实验设置
把 idea 拆成组件,从可控的部分开始,逐步加入探索性模块从简单 setting 开始,逐渐增加难度,最后进入真正的 setting

简单实验:只存在 core technical challenge

明确解法要解决的 core technical challenge
   → 找出当前数据里还有哪些额外的 technical challenge
   → 寻找或构建不含这些额外 challenge 的数据
   → 在这样的数据上验证解法

好处是成本低、且没有其他 challenge 的干扰,能干净地判定解法本身是否 work。 顺序:简单数据验证正确性 → 简单数据上改进 → 真实数据上调 work。

探索性实验的最小可行性三步

第一步:定义二元的可行性标准。 这个实验要验证什么?成功标准是什么?必须是二元、明确、可测量的(是/否)。 写不出二元标准 = 还没想清楚要验证什么,此时做实验是浪费。

第二步:设计最小的实验。 用这句话倒逼:

"如果只有一天时间,我能做的最简单的验证是什么?"

第三步:对照标准判定,只导向三个方向之一。

结果下一步
成功设计更严谨、更大规模的实验巩固;开始增加复杂度
失败用最小成本排除了一条路径。分析是想法错还是实现错,据此 pivot 或终止
模糊**实验设计得不够好,标准没定清楚。**回第一步重定义

第三行最常被处理错:拿到模糊结果时不要"再多跑几个 setting", 模糊结果重复几次仍然是模糊的。

二、诊断实验为什么不 work

表面原因  →  本质技术原因  →  用实验验证这个原因

三步都要走完。只有确认真的是"技术原因",改算法才有意义。

第 1 步 · 表面原因:哪个变量一改就变差(换了数据 / 加了 module / 改了参数)。 方法是对比 work 与不 work 的两组,列出它们的具体差异。

第 2 步 · 本质原因:对表面原因问"为什么",列出尽量多的候选。两类:

  1. 代码有 bug
  2. "xx 算法"在"xx 数据"上确实有问题:超参没设对 / 缺了几个 tricks / 算法本身不行

区分第 2 类的手段:看相关论文为什么能 work、用了什么 tricks (literature-review 检索 → pdf-explore 读实现细节), 给相关论文的算法做 ablation 看哪部分是关键。 有些 idea 单独拿出来不 work,加上 tricks 才 work(NeRF + positional encoding)。

第 3 步 · 验证:设计实验逐个证伪。跳过验证直接改算法 = 猜的梯度。

输出模板

用户说"实验不 work"时,不要直接给改进建议。先产出这张表; 缺哪一格就去补,补不出来就明说"这一格需要你提供 X"。

markdown
## 诊断:<一句话现象>

**表面原因**:<哪个变量一改就变差>
**对照**:work = <配置>  不 work = <配置>  **差异**:<具体列出,不写"设置不同">

| # | 候选本质原因 | 支持证据 | 反对证据 | 怎么用一个实验证伪 |
|---|---|---|---|---|
| 1 | 代码 bug:<具体哪里> | | | |
| 2 | 超参:<哪个> | | | |
| 3 | 缺 tricks:<论文 X 用了 Y> | | | |
| 4 | 算法本身不行:<为什么> | | | |

**下一个实验**(只验证一条,exploration points = 1)
- 验证第 <N> 条 - 二元标准:<若…则该原因成立> - 最小设计:<一天能做完的版本>

**还需要你提供**:<看不到的信息,如训练日志、baseline 配置>

自检:"下一个实验"是从表里推出来的,还是先想好再倒填的? 后者说明在合理化直觉,不是在求梯度。

填满的实例:references/diagnosis-example.md (depth prior 监督后掉点的完整诊断)。它示范三件事: "差异"一格要写到具体配置、候选原因里必须有"代码 bug"这一类、 以及候选的执行顺序按排查成本排而不是按可能性排——十分钟能排除的先做。

三、论文需要哪些实验

实验规划倒推自论文要回答的三个问题:

问题实验
怎么证明方法比已有方法强?comparison:和相关的、较新的 baseline 比。任务太新没有 baseline 时,构造自己方法的 variants
怎么证明各 module 有效?ablation:①一个大表+可视化,列 core contributions 与重要 components 的影响;②若干小表,每个覆盖一个 module 的 design choices(对超参敏感性、对输入质量敏感性、去掉某 choice 的影响)
怎么展示方法的上限?在更有挑战性的数据上做 demo

第三项决定影响力,判据是:

面向下游研究群体做 demo——做给会引用这篇论文的人看,不是做给自己或大众看。

算法在目标数据上 work 之后,尽量在更新、更难的数据上跑,把算法推到极限。 "大家都想看一个算法能做到什么程度"本身就是很大的贡献。 反事实:Neural Body 若没做街舞数据,拿不到 best paper candidate。

缺 ablation / 缺重要 baseline / 缺重要 metric / 数据太简单——这四条都是常见拒稿理由, 见 paper-self-review。

衔接

诊断结论与下一个实验回写 experiments/LOG.md 和 PROJECT.md §4(research-project)。 方案本身有问题(而非实现问题)时回到 research-ideation。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Research Experiment AI skill do?

Design experiments that decide something, and diagnose failing ones by driving from surface symptom to root technical cause before changing anything. Treats improving a method as SGD on the idea, where the root-cause analysis IS the gradient — so it outputs a ranked candidate-cause table with a falsifying experiment for each, never a list of things to try, and ships a fully worked example diagnosis to show the granularity. Also covers minimum-viable exploratory design (binary feasibility criterion, one-day version), what comparison/ablation/demo experiments a paper needs, and which harder d...

Why use Research Experiment on TypingMind?

Because you install it once and use it with any model. Research Experiment is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Research Experiment in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HughYau/pengsida-learning-research-skills/tree/main/research-experiment. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Research Experiment?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Research Experiment?

As many as you like. As long as a model supports skills, you can use Research Experiment with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Research Experiment AI skill free?

It is published on GitHub by HughYau. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇