Research Methodology

Community

HughYau

research-methodology

Entry point and router for pengsida's research methodology (CV/graphics, CCF 优博). Carries the lifecycle map, the five decision rules that override defaults when they conflict, the anti-pattern table, and routing to the six methodology skills and the five bundled execution skills. Load this first when the request spans stages, when it is unclear where in the lifecycle the user is, or when the user asks you to implement or pursue an idea with no evidence it cleared the novelty gate — those are exactly the requests that look narrow from outside and cost months when mis-scoped. When the request unambiguously names one stage — a failing experiment, a paragraph that reads badly, a rebuttal to write — go straight to that skill instead; routing through here would add a hop without adding a decision. 中文触发：科研流程、研究方法论、怎么做科研、做一篇论文、科研卡住了、不知道该干什么、这个项目该怎么推进。

Overview

Publisher	HughYau
Repository	`pengsida-learning-research-skills`
Skill name	`research-methodology`
Stars	52
Forks	4
Bundled files	Instructions only
Links	Skill source Repository

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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by HughYau on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/HughYau/pengsida-learning-research-skills/tree/main/research-methodology
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/HughYau/pengsida-learning-research-skills/tree/main/research-methodology

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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-methodology .claude/skills/research-methodology

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Research Methodology 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 Methodology 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 Methodology 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.

科研方法论总览

生命周期与路由


0. 项目基础设施   建立/接管项目结构与状态          → research-project
1. 想 idea       建立领域视野 → 选题 → 设计方案    → research-ideation
2. 迭代方案       简单实验验证 → 诊断改进 → 调 work → research-experiment
3. 写论文         规划 → 梳理 story → 分章节写作    → paper-writing
                 改写作 / 回应审稿                → paper-revision
                 投稿前自评审                     → paper-self-review

用户的话像这样	去哪
开新项目 / 这文件夹乱了 / 现在做到哪了 / 接手项目	`research-project`
做什么方向 / 这个题值不值得 / 有没有 novelty / 怎么解决这个问题 / A+B 行不行	`research-ideation`
实验不 work / 掉点了 / 做什么实验 / 要哪些 ablation / 做什么 demo	`research-experiment`
写 introduction / 梳理 story / 章节模板 / 做 slides	`paper-writing`
这段写得清楚吗 / 改一下 / 收到 review 了	`paper-revision`
能中吗 / 会被拒吗 / 投稿前检查	`paper-self-review`

任何会话开始先跑 research-project 的 project_status.py—— 30 秒拿到全局状态和阻塞项，避免在一个方法论上已判死刑的课题上继续投入。不确定用户处于哪一步时，先问项目状态（有没有 roadmap、方案定了没、实验做到哪、离截稿多久），再路由。

五条决策规则

与常识默认冲突时以这五条为准。它们都是可判定的，不是态度。

1. idea 从 roadmap 来，不从别人的论文来。 先定长远目标 → 规划 roadmap（一组重要 task）→ 选 task → 发现 failure case → 想解法。反面是看到一篇 SOTA 论文就去改进它：影响力受限、易撞车、且可能被它的错误路线带偏。

2. 选题的权重高于解法。 选题同时决定 novelty 上限和价值上限。在选题上多花的时间回报最高；在已有 well-established solution 的问题上，再好的解法也救不回来。

3. 一次实验循环的价值 = 是否产出了一条经过验证的本质技术原因。 改进方法是对 idea 做 SGD，根因分析就是求梯度。没有根因的循环，下一次改动等于掷骰子——这比实验跑得慢更致命。

4. 判断一篇论文值不值得做，只问：它给读者带来了什么新知识。 带不来就是浪费时间，甚至收获负面评价。这条同时是选题判据和自评审判据。

5. 不要停在"能看"。 业界反复提的痛点若只做到勉强可用就转向，这个方向上等于没有贡献—— 会变成"发了几篇论文，但什么问题都没真正解决"。判据：现在若有人要把这个方法用进真实产品，第一个卡住的会是什么？解决了吗？

反模式

反模式	为什么错	正确做法
看到 SOTA 论文就想怎么改进它	创新空间小、易撞车、可能被错误路线带偏	从 roadmap 的 milestone task 出发
在某技术的原有 setting/数据上刷点	改进空间往往很小	从新的 failure case 入手
认为某任务"被做完了"	论文只放最好的结果，换数据往往就不 work	在更难的数据上探索算法上限
想到能做的课题就动手	跳过重要程度排序	先排序，再选能力范围内最重要的
实验不 work 就改参数再跑	随机梯度，循环再快也不收敛	先定位并验证本质技术原因
一次想设计出完美实验	拖慢循环	最小可行实验，二元标准
新锤子出来就在锤子自己的 setting 上改进	仍是 follow-up	用新锤子解决自己 roadmap 上的 task
论文快截稿了才开始写	完整度低	提前一个月启动（`init_project.py --deadline` 生成时间表）

执行层（5 个，同目录随本项目分发）

上面六个管判断，下面五个管执行，组合使用。它们与本套 skill 同级，均为 pure skill（无需 API key），加载 helper 的方式是 exec(open("<skills>/literature-review/kernel.py").read())——把中间那段换成下表里要用的那个 skill 名，<skills> 即本套 skill 的根目录（本 skill 的同级）。

场景	方法论层给什么	执行层给什么
文献调研	literature tree / challenge-insight tree 的结构、四类 novelty	`literature-review`：`search_openalex` / `expand_citations` / `verify_dois`
读论文	要提取什么（问题、pipeline、技术见解）	`pdf-explore`：`pdf_outline` / `pdf_pages` / `pdf_scan` / `pdf_grep`
单张图	pipeline 图的修辞要求（要和前人不一样、突出 novel module）	`figure-style`：`apply_figure_style()` + 数据保真/标签经济/渲染后校验
多子图	—	`figure-composer`：`panel_task` / `compose_figure` + 对抗式自审
整套图的叙事	11 步写作顺序与 story 梳理	`paper-narrative`：`narrative_review_task` 审 arc、缺哪张、砍哪张

冲突时：领域修辞以方法论层为准（"pipeline 图是为了突出 novelty 而不是让读者看懂" 是 CV/graphics 投稿的现实）；技术正确性与可读性以 figure-style 为准（数据保真、色觉障碍友好没有商量余地）。 这是全套唯一的裁决规则——其他 skill 遇到两层冲突时引用它，不要各自重述一遍，重述过的规则会随各自的改动漂移。

Frequently asked questions

What does the Research Methodology AI skill do?

Why use Research Methodology on TypingMind?

Because you install it once and use it with any model. Research Methodology 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 Methodology in TypingMind?

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

Which AI models can use Research Methodology?

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 Methodology?

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

Is the Research Methodology 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

Create Agent Adapter

paperclipai

OrganizationPopular

Create or modify Paperclip agent adapters across server, UI, and CLI surfaces. Use when adding support for a new CLI agent, API agent, custom process, or adapter package.

Create Paperclip Bundled Skill

paperclipai

OrganizationPopular

Turn an idea, tweet, or task into a skill in the Paperclip skills catalog (packages/skills-catalog). Use when asked to FIND or MAKE a skill and publish it as a bundled/optional catalog skill: research…

Tavily

Tavily web search, content extraction, and research tools.

Deep Research

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

科研方法论总览

生命周期与路由

五条决策规则

反模式

执行层（5 个，同目录随本项目分发）

Frequently asked questions

Related AI Skills

Set up your own AI workspace now