learn-deep

A structured way to learn a new concept or technology from several angles: connections to existing knowledge, the right depth, a knowledge map, a small working example, and questions that test understanding.

In plain words
What is it for?
Use it when you want to understand a new technology, theory, or concept and want both a practical starting point and a way to test your understanding.
Why use it?
It removes the problem of learning disconnected facts without knowing what matters or how to apply them. It also checks whether the concept is truly understood rather than merely familiar.

Skill for Claude CodeCodex

Part of the Bloom plugin — 7 skills shipped together

Install

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.

agentmods
npx agentmods add skills/li-evan/bloom/learn-deep
Any agent
npx skills add Li-Evan/Bloom --skill learn-deep
Clone the repo
git clone --depth 1 https://github.com/Li-Evan/Bloom

Made for: Claude Code, Codex.

Or install Bloom, the plugin that ships this one along with the rest of its 7 skills.

Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,107 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00145 $0.01107
Opus 5 $0.00072 $0.00553
Sonnet 5 $0.00029 $0.00221
Haiku 4.5 $0.00015 $0.00111

Measured 3d ago against content hash 351c1daa5677, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-deep 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 3d ago.

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.

skills/learn-deep/SKILL.md · 46 lines

What it actually says

深度学习一个概念(learn-deep)

learn-crossover / learn-occam / learn-graph / learn-prototype / learn-feynman 五个视角编排成一遍全景,给用户学任何概念的"一次扫透 + 选方向"。

何时用

用户说"想学 / 理解 / 搞懂 / 讲讲一个概念 X"时——这是默认入口,一次跑完五视角,用户再选深入哪个。 例外:用户明确只要某一个角度("用跨界讲""帮我建图谱""考考我")→ 直接用对应的单个 learn-* skill,别全跑。

开跑前

先问清用户的背景:学过哪些相关领域、做过什么、熟悉哪些工具 / 理论。后面 crossover / occam / graph 都要用到。只采纳用户亲口确认学过的。

五视角执行顺序(这个弧线最顺:先降门槛 → 定深度 → 给地图 → 动手 → 验收)

1️⃣ crossover — 先用"你已经会一半"降门槛

抓住 X 的本质结构(剥术语),按三猜想给 🎁其实已学过 / 🔗结构同构(字段级对应表)/ 🧩可用已有知识解释,点出元知识。先激发信心,再谈深入。

2️⃣ occam — 框定"该学多深"

定位"既定问题"(学 X 解决什么)、现有知识够不够、X 的贬值速度与 ROI,给"够用就停 / 只学最小那块 / 值得深挖"的深度边界。不是劝退,是防止一上来过度钻。

3️⃣ graph — 给一张地图,知道 X 在哪、学到哪算够

X 在所属领域的知识图谱骨架(概念/用途/父子节点),标复用价值最高的节点 + 从常识能入门的点,给学习路径。引导用户补节点(自己建图才学得到)。

4️⃣ prototype — 给最小原型起点,把动手的球递给用户

给"最垃圾但能跑的原型"起点 + 引导式提问(让用户自己洞察缺陷),预告会撞到的坑。不替他做。

5️⃣ feynman — 抛 2–4 个直击盲点的问题验收

让用户用自己的话答,答不顺处 = 没真懂的洞。最后一个问题尽量打在 X 的根本局限上(真懂的试金石)。

6️⃣ 收尾:选方向

明确推荐往哪 1–2 个方向深入(综合 occam 的 ROI 判断 + 用户的目标 + 哪个视角最戳中他),并指出对应该接哪个单 skill(要动手→learn-prototype,要验收→learn-feynman)。

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。

  • 五视角各有侧重、严禁重复:crossover 撬动 / occam 只谈该学多深 / graph 只给地图 / prototype 只给动手路径 / feynman 只拷问。同一段内容不要讲五遍。
  • 每个视角精炼——这是"全景扫一遍",深入留给用户选完之后。宁短勿灌。
  • 单视角细分入口(用户只要一个时用):learn-crossover learn-occam learn-graph learn-prototype learn-feynman
Changes

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.

  1. 3d ago First seen · 46 lines · 145 tokens per session scan A 351c1daa5677

Subscribe to this mod's changes

learn-deep is a skill published in the GitHub repository Li-Evan/Bloom (248 stars, last pushed 2mo ago), licensed MIT. It adds 145 tokens to every session and 1,107 once invoked, about $0.0007 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

liu-xiaoyan-english

模拟刘晓燕老师的英语教学风格和方法论,用于四六级/考研英语辅导(已用2026年6月CET-6真题校准)。触发场景:用户提到刘晓燕、晓燕老师、四六级英语、CET-4、CET-6、2026六级、考研英语、英语阅读理解、英语写作模板、长难句分析、英语备考规划、英语翻译技巧、选词填空、背单词方法,或要求用刘晓燕的方式讲课/解题/做规划/对答案。也适用于:用户发来英语阅读/听力/翻译/写作/选词填空题要求讲解。常见触发语:'用刘晓燕的方式'、'燕姐教我'、'像晓燕老师那样讲'、'四六级怎么准备'、'帮我分析这道阅读题'、'这个长难句怎么拆'、'保命班'、'考前急救'、'今年六级'。Use when coaching CET-4/6 or…

tong666-bit/liu-xiaoyan-skill · 272 tokens

ai-pm-atom-lesson

输入一个"原子知识点"(AI 产品经理知识体系里的最小单元概念,如「文本切分」「演绎推理」「思维链 CoT」「向量化」「LLM-as-Judge」),自动展开成一份讲解思路并产出一个单文件、离线可用的交互式 HTML 原子课件——含权威定义+真实出处、通俗解释、贯穿项目案例、实操判断题、以及一个可视交互 Demo。当用户说"做一个 X 的原子课""把这个知识点做成原子课件""按原子课 SOP 做 X""给 X 配一页能点着玩的讲解""atom lesson"时,一定要使用本技能。也适用于:把知识体系/能力地图里的某个词条单点成课、要一系列同构的知识点小课件、批量把能力地图节点做成课。即使用户只说"把 X…

uimarch123-arch/ai-pm-atom-lesson · 286 tokens

DeepTutor

Skill "DeepTutor" from HKUDS/DeepTutor, covering deeptutor cli skill, when to use, prerequisites, commands and chat & capabilities.

HKUDS/DeepTutor · 0 tokens

claude-certification

AI Engineering from Scratch 中四条独立 Claude 认证路线的 AI 原生导师与入门流程。适用于学习者 希望选择 Claude 认证、备考 CCAO-F、CCDV-F、CCAR-F 或 CCAR-P、继续认证路径、以交互方式学习 下一课、运行并验证实践实验、构建并评分产物、参加诊断或模拟测评,或通过 GitHub 上的 Claude Code、 Codex、ChatGPT、Cursor 或其他 agent 补强薄弱考试领域时。.

fancyboi999/ai-engineering-from-scratch-zh · 119 tokens

check-understanding

Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .

fancyboi999/ai-engineering-from-scratch-zh · 44 tokens

find-your-level

Interactive quiz that maps your AI/ML knowledge to a starting point in the 260-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".

fancyboi999/ai-engineering-from-scratch-zh · 71 tokens