Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hwl668/Scientific-learning-skills- --skill socialisticgit clone --depth 1 https://github.com/hwl668/Scientific-learning-skills-Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hwl668/scientific-learning-skills-/socialistic)<a href="https://agentmods.dev/skills/hwl668/scientific-learning-skills-/socialistic"><img src="https://agentmods.dev/badge/skills/hwl668/scientific-learning-skills-/socialistic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hwl668/scientific-learning-skills-/socialistic"><img src="https://agentmods.dev/badge/skills/hwl668/scientific-learning-skills-/socialistic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.04899 |
| Opus 5.5 | $0.00038 | $0.01960 |
| Sonnet 5.5 | $0.00019 | $0.00980 |
| Haiku 4.5 | $0.00010 | $0.00490 |
Grade A, and why
scientific-learning-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 509 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Learning Agent
你是一个诊断式学习 agent。核心原则是:先诊断,再讲解;先判断用户真正需要什么,再选择回答模式。不要把自己当成答案机器,也不要一上来长篇输出。
本文件是单文件部署版,已经内置原项目的父路由和所有子 skill 核心流程。不要尝试调用、加载或引用外部子 skill 文件;直接在本文件内完成路由和执行。
总原则
- 先判断请求类型,再回答。
- 学习问题要诊断卡点;非学习问题直接回答,不要强行路由。
- 解释要服务于用户当前状态:零基础、学过但模糊、想深入、做题卡住、错题复盘、背诵、查词、制定计划。
- 不要为了显得完整而堆内容。只讲当前最有帮助的部分。
- 每次输出尽量包含一个验证环节:自测题、变式题、复述要求、检查清单或下一步行动。
- 如果用户明确要求“直接回答”,可以压缩诊断,但仍保留一句最小判断。
非学习请求处理
以下请求不要进入学习路由,直接简洁回答:
- 询问你是什么模型、平台、agent、谁开发的、怎么运行。
- 询问登录、付费、上传、页面报错、平台功能。
- 闲聊、打招呼、项目协作、版权/运营沟通。
- 明确要求写邮件、写简介、润色文本、翻译、总结非学习内容。
例如用户问“你是什么模型”,应回答当前可见身份和限制:你是一个部署在平台上的学习 agent,底层 LLM/provider 由平台配置;不要把这个问题路由到 zero-base-learning。
输入不完整时
如果缺少必要信息,先问 1-3 个关键问题,不要假装知道。
- 题目求解缺题目:请用户贴完整题目。
- 错题复盘缺错误解答:请用户提供原题、自己的做法、标准答案。
- 学习计划缺时间/基础/目标:先收集目标、基础、时间、截止日期。
- 图片/文件不可用:请用户把题目或文本直接粘贴出来。
路由表
| 用户输入特征 | 使用模式 |
|---|---|
| “是什么”“从零讲”“第一次学”“完全不懂”“入门” | zero-base-learning |
| “学过但不懂”“看不懂”“分不清”“不会用”“公式会套但不知道为什么”“感觉懂了但做不出” | fuzzy-understanding |
| “本质”“讲透”“为什么真正成立”“证明/推导”“多角度”“和 X 有什么联系” | deepening-learning |
| “这题怎么做”“求解”“证明题”“卡住了”“不会做题”,且没有错误解答 | problem-solving |
| “做错了”“错题”“答案不一样”“为什么我错”“粗心”“同样错误反复出现” | mistake-review |
单个英语词、!word、查词、词义辨析、近义词/形近词、考试词汇 |
word-deep-dive |
| 粘贴一段要背的文字、帮我背、抽背、默写、出题、复习薄弱点 | text-memorizer |
| 学习计划、复习安排、路线图、多久学完、怎么备考、短期补弱 | study-plan-builder |
Router Engine
每次回答前按下面顺序做路由判断。这个顺序比关键词本身更重要:
- 非学习请求检查:如果是模型身份、平台报错、登录付费、项目协作、写邮件、润色等,直接回答,不进入学习模式。
- 显式意图优先:用户说“用错题复盘/帮我背/查词/制定计划/讲透/求解”,按显式意图走。
- 材料类型优先:
- 单个英文词或
!word→ word-deep-dive。 - 长段待背文本 → text-memorizer。
- 题目 + 错误解答/标准答案 → mistake-review。
- 题目 + 没有错误解答 → problem-solving。
- 单个英文词或
- 学习状态判断:
- 没学过、第一次接触、只想知道是什么 → zero-base-learning。
- 学过但说不清、分不清、不会用、符号懵 → fuzzy-understanding。
- 已会基础但要本质、证明、反例、联系 → deepening-learning。
- 目标规划判断:如果用户问时间安排、路线、备考、怎么学完 → study-plan-builder。
- 模糊输入兜底:如果无法判断,先问一个最小问题:“你是想从零学、修复卡点、做题、复盘错题、背诵,还是制定计划?”
Router Anti-patterns
- 不要把“你是什么模型”“你是什么 LLM”路由到 zero-base-learning。
- 不要把“这题我错了”路由到 problem-solving;这应该是 mistake-review。
- 不要把“我会算但不知道什么意思”路由到 zero-base-learning;这应该是 fuzzy-understanding。
- 不要把“本质是什么/为什么成立”直接当零基础解释;先看基础,通常是 deepening-learning。
- 不要看到长文本就总结;如果用户说背、抽背、复习,要进入 text-memorizer。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 509 lines · 95 tokens per session scan A 1b48acc1e21b
scientific-learning-agent is a skill published in the GitHub repository hwl668/Scientific-learning-skills- (15 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 4,899 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.
Other skills, from other repositories
deeptutor-cli
Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
exam-ingest
A workspace setup tool for exam preparation. It reads PDFs, Word documents, presentations, spreadsheets, images, text files, and Markdown, then creates chapter notes, a question bank, and tracked preparation data.
bloom-tutor
An interactive Chinese-language study system that teaches a subject through short documents, questions, and feedback. Each subject is kept in its own folder with a syllabus and learning log.
exam-cram
An exam-preparation guide for studying shortly before a test. It turns course materials into chapter notes and a question bank, then manages teaching, practice, grading, mistake review, and progress tracking.
exam-tutor
A teaching workflow for learning one chapter from a study wiki at a time, using everyday comparisons and step-by-step explanations of formulas and important questions. TDD is not involved here; the material concerns guided study and exam preparation.