DeepTutor CLI
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
当用户要做/研究一个东西、想提升某个技能、或觉得某个产出不够好想改进时使用。用「改良主义」先逼出一个最垃圾但能跑的原型，再引导他自己洞察缺陷、提出问题，提改良假说→实践检验→迭代，信奉「洞察缺陷 如何优化 最终答案」，并把每次改进的方法本身沉淀成方法论。触发场景：要做 X、研究 X、提升 X、X 做得不好想改进、怎么优化 X、不知从哪下手做。
Install Learn Prototype
$ npx skills add Li-Evan/Bloom --skill learn-prototype -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Li-Evan/Bloom learn-prototype --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Li-Evan/Bloom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/learn-prototype .claude/skills/learn-prototype && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "learn-prototype" agent skill from https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototype into .claude/skills/learn-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-prototype", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototypeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Li-Evan/Bloom --skill learn-prototype -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Li-Evan/Bloom learn-prototype --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Evan/Bloom.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/learn-prototype .agents/skills/learn-prototype && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "learn-prototype" agent skill from https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototype into .agents/skills/learn-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-prototype", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Li-Evan/Bloom --skill learn-prototype -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Li-Evan/Bloom learn-prototype --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Evan/Bloom.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/learn-prototype .cursor/skills/learn-prototype && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "learn-prototype" agent skill from https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototype into .cursor/skills/learn-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-prototype", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Li-Evan/Bloom.git --path skills/learn-prototype--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Li-Evan/Bloom --skill learn-prototype -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Li-Evan/Bloom learn-prototype --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Evan/Bloom.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/learn-prototype .gemini/skills/learn-prototype && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "learn-prototype" agent skill from https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototype into .gemini/skills/learn-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-prototype", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Li-Evan/Bloom learn-prototypeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Li-Evan/Bloom --skill learn-prototype -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Li-Evan/Bloom.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/learn-prototype .github/skills/learn-prototype && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "learn-prototype" agent skill from https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototype into .github/skills/learn-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-prototype", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Li-Evan/Bloom --skill learn-prototype -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Li-Evan/Bloom learn-prototype --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Evan/Bloom.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/learn-prototype .opencode/skills/learn-prototype && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "learn-prototype" agent skill from https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototype into .opencode/skills/learn-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learn-prototype", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
learn-prototype- GitHub stars
- 284
- Token cost
- ~301 tokens
- SKILL.md length
- 49 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
当用户要做/研究一个东西、想提升某个技能、或觉得某个产出不够好想改进时使用。用「改良主义」先逼出一个最垃圾但能跑的原型，再引导他自己洞察缺陷、提出问题，提改良假说→实践检验→迭代，信奉「洞察缺陷 如何优化 最终答案」，并把每次改进的方法本身沉淀成方法论。触发场景：要做 X、研究 X、提升 X、X 做得不好想改进、怎么优化 X、不知从哪下手做。
- Education work in your project
- SKILL.md covers 何时用, 流程（教练模式：引导用户做和提问，不替他做） and 注意
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Learn Prototype is an agent skill from Li-Evan/Bloom. 当用户要做/研究一个东西、想提升某个技能、或觉得某个产出不够好想改进时使用。用「改良主义」先逼出一个最垃圾但能跑的原型，再引导他自己洞察缺陷、提出问题，提改良假说→实践检验→迭代，信奉「洞察缺陷 如何优化 最终答案」，并把每次改进的方法本身沉淀成方法论。触发场景：要做 X、研究 X、提升 X、X 做得不好想改进、怎么优化 X、不知从哪下手做。
Its SKILL.md is about 300 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Education. The repository describes itself as: Hire a private AI tutor for anything — it reads how you actually learn and teaches the next lesson just for you. Bloom's 2-Sigma research as a Claude Code skill + self-hostable…. The licence is MIT.
When your agent uses it
- Education work in your project
Example prompts
- “/learn-prototype”
What it can do on your machine
Read from SKILL.md and the folder at commit b391898. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Learn Prototype loads about 301 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 49 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Li-Evan/Bloom at commit b391898, republished under its MIT licence (© Li-Evan). 49 words, ~301 tokens.
Download SKILL.mdSave it as
.claude/skills/learn-prototype/SKILL.md (or your agent's skills folder).- name
- learn-prototype
- description
- 当用户要做/研究一个东西、想提升某个技能、或觉得某个产出不够好想改进时使用。用「改良主义」先逼出一个最垃圾但能跑的原型，再引导他自己洞察缺陷、提出问题，提改良假说→实践检验→迭代，信奉「洞察缺陷 > 如何优化 > 最终答案」，并把每次改进的方法本身沉淀成方法论。触发场景：要做 X、研究 X、提升 X、X 做得不好想改进、怎么优化 X、不知从哪下手做。
改良主义学习法（learn-prototype）
核心信条：洞察缺陷 > 如何优化 > 最终答案。 试图洞察缺陷、自己提出问题，永远不要害怕问题多简单。学习要努力，但要做有效的努力。
何时用
用户要动手做 / 研究一个东西，或想把某个已有产出改得更好。这是"重输入、轻输出"短板的解药——逼用户从输入切到输出。
流程（教练模式：引导用户做和提问，不替他做）
第一步：先做最垃圾的原型
别追求完美，先有一个能跑 / 能看的最小版本。卡在"还没准备好"就是没进改良主义。
第二步：引导用户自己洞察缺陷
关键且不能代劳：问他"这哪里不好？为什么不好？"哪怕问题很简单。把"自己提问"的动作交给用户——这是能力泛化的来源。你可以追问、补他没看到的角度，但先让他提。
第三步：提改良假说 → 实践 → 检验
针对缺陷提一个改良策略（视为假说，可对可错），动手改，看效果。错了也有用——错误暴露后，下次自动规避这个方向。
第四步：迭代 / 推翻
循环②③，直到无法再优化 → 推翻重做。允许"不正确但有用的版本"——能解决当前问题就够了，不必一开始追求完美架构。
第五步：沉淀方法论
把"这次怎么从 A 改到 B"的方法本身记一笔（每个解决的问题都成为后续的法则）。改得越多，方法越泛化，提问越准。
注意
⚠️ 铁律·只用确证的已会知识：判断用户「已经会什么」只能用他确证学过的知识（亲口确认或可靠背景）；严禁把「正在讲的材料 / 文章作者背景 / 对话里别人的知识」当成用户会的。拿不准 → 直接问「⚠️ 你学过 ___ 吗？」，绝不替他假设。
- 别替用户提问、别替他做——那会废掉这个 skill 的核心价值。引导 > 代劳。
- 提问命中要害需要基本素质，但素质靠迭代泛化，所以"先开始"比"先够格"重要。
- 缺前置知识改不动 → 转
learn-graph；想确认是否真懂 → 转learn-feynman。 - 同族 skill：
learn-occamlearn-crossoverlearn-graphlearn-feynman。
© Li-Evan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/learn-prototype of Li-Evan/Bloom.
Open the folder on GitHubat commit b391898
Compare with similar skills
Learn Prototype next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Learn Prototype this skillLi-Evan/Bloom | 284 | — | ~301 | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Zhang Xuefeng Perspectivealchaincyf/zhangxuefeng-skill | 10k | 1 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Deep Reading Analystginobefun/deep-reading-analyst-skill | 353 | 5 repos | ~3.6k | Automated safety check: Pass | MIT | |
| AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch | 66k | — | ~2k | Automated safety check: Pass | MIT | |
| OpenMAIC Setup and ExtensionTHU-MAIC/OpenMAIC | 40k | — | ~1.7k | Automated safety check: Notes | MIT |
Similar skills
Zhang Xuefeng Perspective
alchaincyf/zhangxuefeng-skill
Answers education and career questions in the voice of Zhang Xuefeng, looking up current employment and admissions data before giving a direct verdict.
Deep Reading Analyst
ginobefun/deep-reading-analyst-skill
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems…
AI Engineering Placement Quiz
rohitg00/ai-engineering-from-scratch
Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.
OpenMAIC Setup and Extension
THU-MAIC/OpenMAIC
Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.
Codebase to Course
zarazhangrui/codebase-to-course
Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.
More from Li-Evan/Bloom
Bloom Tutor
Li-Evan/Bloom
A skill your agent uses when 用户想以一对一苏格拉底导师的方式系统学习一个课题——开一门新课、推进课题的下一篇、提交学习反馈或说「我读完了」、或整理/查看学习日志。基于 Bloom 2 Sigma 的交互式学习系统。触发词：开个文件夹学X、我想学X、帮我学X、继续、下一篇、我读完了、整理学习、查看学习日志、interactive Socratic…
Learn Crossover
Li-Evan/Bloom
当用户学习或接触一个新概念/新技术/新算法/新领域时使用（尤其感到陌生或有点难时）。用「跨界原则」拿用户已掌握的知识快速撬动新知识——指出他其实已经学过的同一个东西（换了名字）、结构同构的旧知识、能解释新知识的已有知识，并点出新概念体现的跨领域元知识模式。让「学新东西」变成「发现你已经会了一半」。触发场景：学 X、接触 X、这个好难、X 是什么、帮我理解 X。
Learn Deep
Li-Evan/Bloom
用户学任何新概念/新技术/新理论的默认深度入口——一次性用五个视角把概念讲透并帮他选深入方向：crossover 用已会的撬动、occam 框定该学多深、graph 建知识地图、prototype 最小原型迭代、feynman 拷问检验。触发场景：我想学 X、理解 X、X 是什么、讲讲 X、搞懂 X、学一下 X、深入 X、给我讲讲 X。除非用户明确只要某一个视角（那时改用对应的单个…
Learn Feynman
Li-Evan/Bloom
当用户学完一个东西想自查是否真懂、或觉得「好像懂了」但不确定时使用。用「费曼学习法」让他用自己的话把概念讲出来，你扮好奇学生专挑他含糊/跳过的地方追问，把「讲不顺的模糊处」揪出来作为没真懂的漏洞，定位是缺前置知识还是没想透，判断理解是否闭环。触发场景：我学完了考考我、自查一下、我好像懂了、我讲讲你看对不对、检验我的理解、这个我真懂了吗。
Learn Graph
Li-Evan/Bloom
当用户要系统学一个新领域、不知道从哪入手、或担心「学得不够系统」时使用。用「知识图谱学习法」和用户一起构建该领域的概念/用途/父子节点图谱（自己建图的过程本身就是学习），标出复用价值最高的节点和「从常识就能入门的点」，给出有效学习路径并回答「学到哪算够」。触发场景：系统学 X 领域、从哪开始学、学得不系统、想要 X 的全貌、规划学习路径、这个领域有多大。
Learn Occam
Li-Evan/Bloom
当用户纠结要不要学某个东西、学到什么程度，或在做时间/精力/项目取舍时使用。用「简易策略」先逼问要解决的既定问题，检验现有知识能否搞定，评估知识贬值速度与 ROI，用「探索 vs 应用」判断该学新的还是用现有的，给出「学 / 不学 / 只学最小够用」的结论，避免囤积会贬值的知识。触发场景：要不要学 X、值不值得深入、学到什么程度够、时间不够该学啥、该深挖还是够用就行。
Related
Categories
Questions about Learn Prototype
What does Learn Prototype do?
当用户要做/研究一个东西、想提升某个技能、或觉得某个产出不够好想改进时使用。用「改良主义」先逼出一个最垃圾但能跑的原型，再引导他自己洞察缺陷、提出问题，提改良假说→实践检验→迭代，信奉「洞察缺陷 如何优化 最终答案」，并把每次改进的方法本身沉淀成方法论。触发场景：要做 X、研究 X、提升 X、X 做得不好想改进、怎么优化 X、不知从哪下手做。. Learn Prototype is an agent skill from Li-Evan/Bloom.
When should I use Learn Prototype?
Learn Prototype fits situations like: education work in your project.
How do I install Learn Prototype in Claude Code?
Run `npx skills add Li-Evan/Bloom --skill learn-prototype -a claude-code`. Or copy the skill folder (skills/learn-prototype in Li-Evan/Bloom) into .claude/skills/learn-prototype in your project. Claude Code loads it when a task matches its description.
How do I install Learn Prototype in Codex?
Run `npx skills add Li-Evan/Bloom --skill learn-prototype -a codex`. Or copy the skill folder (skills/learn-prototype in Li-Evan/Bloom) into .agents/skills/learn-prototype in your project. Codex loads it when a task matches its description.
Can I use Learn Prototype in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Li-Evan/Bloom --skill learn-prototype -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learn-prototype, .gemini/skills/learn-prototype, .github/skills/learn-prototype and .opencode/skills/learn-prototype in your project.
What does Learn Prototype need to run?
SKILL.md names no scripts, command-line tools or credentials: Learn Prototype is instructions for the agent only.
Does Learn Prototype access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Learn Prototype safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Learn Prototype use?
Learn Prototype is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Learn Prototype use?
About 301 tokens (SKILL.md is roughly 1.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Learn Prototype?
Skills that share tags, products or a category with Learn Prototype: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), Zhang Xuefeng Perspective (alchaincyf/zhangxuefeng-skill, 10k stars), Deep Reading Analyst (ginobefun/deep-reading-analyst-skill, 353 stars) and AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Learn Prototype?
Li-Evan (a GitHub user) maintains it in Li-Evan/Bloom, which has 284 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 17, 2026.
Source: Li-Evan/Bloom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.