make-it-stick
Skill1 starsChanged 2 months agoMITView on GitHub
Apply Make It Stick to retention and transfer: retrieval practice, spacing, interleaving, corrective feedback, and calibration of confidence. Use when designing or repairing a learning plan or checking durable learning; a request for a simple explanation is not permission to impose a quiz.
In this repository39 other files it gives its agents.
- algorithms-to-live-bySkill
- analectsSkill
- antifragileSkill
- art-of-doing-scienceSkill
- art-of-warSkill
- beginning-of-infinitySkill
- bhagavad-gitaSkill
- book-of-whySkill
- brothers-karamazovSkill
- capital-volume-oneSkill
- design-of-everyday-thingsSkill
- development-as-freedomSkill
- dhammapadaSkill
- don-quixoteSkill
- dream-of-red-chamberSkill
- euclid-elementsSkill
- feynman-lecturesSkill
- good-strategy-bad-strategySkill
- governing-the-commonsSkill
- how-to-solve-itSkill
- human-understandingSkill
- mans-search-for-meaningSkill
- meditationsSkill
- muqaddimahSkill
- nicomachean-ethicsSkill
- on-libertySkill
- origin-of-speciesSkill
- republicSkill
- scientific-revolutionsSkill
- second-sexSkill
- seeing-like-a-stateSkill
- selfish-geneSkill
- sicpSkill
- superforecastingSkill
- tao-te-chingSkill
- the-mom-testSkill
- thinking-fast-and-slowSkill
- thinking-in-systemsSkill
- wealth-of-nationsSkill
The file
Files
Make It Stick:把熟悉感变成可用知识
把学习目标转成能够独立完成的行为,再安排提取、反馈和延迟检查。依据 Harvard University Press 的合法试读与书籍说明;本项目给出原创练习设计,不承诺读完本书或套用方法就获得能力。
先判断需要什么
取得学习材料或明确主题、目标任务、现有基础和可用时间。若用户要解释,先直接解释;若用户要计划,交付可执行计划;只有其要求练习或检查理解时才进入问答。缺基础材料时,可以给标明假设的示范,不得编造原书引文或学习者表现。
设计一个学习循环
- 把目标写成可观察任务。 例如“独立判断新样本是否被证据支持,并指出哪句越界”,优于“熟悉事实性评估”。确认前置知识;初学者需要简明讲解或例题,不能只用失败测试代替教学。
- 让学习者先从记忆提取。 看过材料后闭卷解释、画关系、解题或判断新例子。用户未作答前不要把完整答案当成其答案;其明确只要答案时直接满足,不强迫练习。
- 在努力尝试后提供可定位的反馈。 区分事实错误、条件遗漏、策略选择与表达问题。指出材料依据,让学习者修正关键一步;答案或评分没有可靠来源时,保留不确定性。反馈是应用设计的一部分,不声称所有情境都应采用相同反馈时机。
- 把重复分散,并混合相近类别。 隔一段时间再提取,按实际遗忘和目标期限调整;需要会选方法时混合容易混淆的题型,让学习者先判断再解答。不要把交错练习变成随机切换无关任务,或把固定的1/3/7天当成普遍最优间隔。
- 用延迟和陌生材料校准信心。 记录答案前的信心与实际表现,比较能否在不看提示的情况下完成新任务。能复述原句只说明该层表现;迁移、长期保持和实际工作能力分别检查。
交付
计划包含一个目标行为、一小组练习、反馈依据、下一次延迟检查方式及判断标准;按用户时间缩放。实际教学每轮集中一个关键问题,避免一次倾倒题库。只在用户提供独立回答后评价该回答,不把 AI 生成的范例称为用户掌握。
书中“有益难度”不等于越难越好。基础不足、没有纠错、过度负荷或高压考核可能妨碍学习。重读有定位信息与补理解的用途,不能说任何阅读都无效。技能演示、工作绩效、实验效应量不能互相冒充。
需核查作者观点时读 来源说明;需设计工作练习时读 评估规则学习案例。书目见 book.json,行为评估见 cases.json。本 Skill 不自动创建复习提醒或后台任务。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

