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 agentmods add skills/li-evan/bloom/learn-prototypenpx skills add Li-Evan/Bloom --skill learn-prototypegit clone --depth 1 https://github.com/Li-Evan/BloomWhat 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 | $0.00144 | $0.00815 |
| Opus 5 | $0.00072 | $0.00407 |
| Sonnet 5 | $0.00029 | $0.00163 |
| Haiku 4.5 | $0.00014 | $0.00081 |
Grade A, and why
learn-prototype 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 2d 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.
What it actually says
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。
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.
- 2d ago First seen · 44 lines · 144 tokens per session scan A a4f55f2f0f2b
learn-prototype is a skill published in the GitHub repository Li-Evan/Bloom (248 stars, last pushed 2mo ago), licensed MIT. It adds 144 tokens to every session and 815 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.
Other skills, from other repositories
sansheng-distill
Use when 用户要把一本书全文、单个视频(按 1 集)、YouTube/B站视频系列、一个创作者的全部作品,或历史人物的生平材料做成可追溯的深度蒸馏资料;触发词:蒸馏这本书、拆书、蒸馏视频、视频系列蒸馏、蒸馏 UP 主、人物思想蒸馏、人物传记证据库、历史人物事实核验、传记事实入库。只要字幕摘要、单篇文章写作时不用此 Skill;制作「一页」产品或网站时,本 Skill 只负责公共资料与证据契约,产品规则、页面工程和发布交给对应产品/网站能力。.
iso-24495
Use when text must be easy for its intended reader to find, understand, and act on — reports, emails, documentation, UI text, announcements, explanations, AI output that reads as dense or bureaucratic. Applies ISO 24495-1 plain language principles with dedicated technique layers for English and Traditional Chinese.…
coc-kp-host
Act as a Chinese-language Keeper (KP) for Call of Cthulhu-style investigative tabletop RPG sessions. Prioritize immersive play, player agency, clean pacing, and faithful dice adjudication over rules lectures.
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…
docx-template-translator
Adaptive conversion of LaTeX, PDF, or Markdown sources into a complete Word .docx that follows a user-supplied .docx template. Use when pandoc --reference-doc alone is not enough — for thesis, dissertation, report, or institutional Word formatting that needs cover pages, declarations, TOC, heading numbering, captions…
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…