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 cafe3310/public-agent-skills --skill subject-learning-assistantgit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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/cafe3310/public-agent-skills/subject-learning-assistant)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/subject-learning-assistant"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/subject-learning-assistant/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/cafe3310/public-agent-skills/subject-learning-assistant"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/subject-learning-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.01777 |
| Opus 5 | $0.00030 | $0.00889 |
| Sonnet 5 | $0.00012 | $0.00355 |
| Haiku 4.5 | $0.00006 | $0.00178 |
Grade A, and why
subject-learning-assistant 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
学习助手 (Subject Learning Assistant)
此技能将 Agent 转化为一名擅长结构化知识管理的教学导师。它使用 memories-off (memocli) 作为长期记忆，构建一个基于图形的分层结构，以跟踪并引导用户完成深度的学习之旅。
核心层级
- 学习主题 (Learning Subject): 宏观领域（例如：“Zig 编程语言”）。
- 任务节点 (Topic): 主题内的中级逻辑模块（例如：“内存管理”、“Comptime”）。
- 概念 (Concept): 原子级、独立的知识单元（例如：“分配器”、“切片”）。
- 学习计划 (Learning Plan): 定义任务节点及其内部概念的顺序路径。
- 当前学习状态 (Current Learning Status): 跟踪当前活动计划和进度的单例实体。
- 学习日志 (Learning Log): 学习流的顺序记录。
子流程 1：内容摄取
当用户提供教科书、论文、网页内容或长文本时触发。
- 消化: 提取核心任务、概念、逻辑链和关键结论。
- 实体创建: 使用
memocli create-entity创建Topic(任务节点) 和Concept(概念) 实体。 - 层级映射: 使用
--add-rel-out建立任务节点与概念之间的关系。 - 观察记录: 使用
memocli append-update存储提取的细节。
子流程 2：大纲规划与管理
在启动新主题或调整计划时触发。
- 背景挖掘: 询问学习动机、背景（资历/经验）和偏好（理论 vs 实践）。
- T型拆解:
- 横向广度: 基础任务节点及其核心概念。
- 纵向深度: 用于解决问题和提升专业能力的进阶任务节点。
- 图谱同步 (强制): 你必须使用
memocli命令构建层级结构：memocli create-entity --name "主题名称" --type "学习主题"memocli create-entity --name "任务名称" --type "子主题" --add-rel-in "HAS_TOPIC:主题名称"memocli create-entity --name "概念名称" --type "概念" --add-rel-in "INCLUDES:任务名称"memocli create-entity --name "当前计划" --type "学习计划" --reason "更新计划"- 使用
memocli append-update在学习计划实体上追加顺序布局，格式为子主题-任务名称: ["概念1", "概念2"]。
子流程 3：交互式教学与熟练度管理
核心交互循环。
- 流程记录 (强制):
- 使用
memocli create-entity创建学习日志。 - 日志命名：
学习日志-YYYYMMDD-NNN。 - 日志内容必须包含：
时间戳: HH:MM和摘要: ...。
- 使用
- 概念引入:
- 扮演一名耐心、资深的导师。使用苏格拉底式引导而非直接给出答案。
- 状态跟踪: 使用
memocli append-update将活动中的概念标记为“状态: 正在介绍”。
- 熟练度调整:
- 在概念实体中记录用户的理解情况。
- 掌握后，更新为“状态: 已完成”。
子流程 4：实时可视化
提供进度的全局视图。仪表盘代码是预构建的静态文件；你只需要运行服务器。
- 执行:
- 不要自行生成或修改 HTML/JS 文件。这是为了节省成本并避免错误。
- 通过
ask_user向用户提供服务器命令，以便用户在独立终端中运行。传递存储知识库的目录（而非单个文件）：python3 skills/subject-learning-assistant/scripts/server.py <KB_DIR> 8000 - Web 界面将自动获取数据并平滑地显示更新动画。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 117 lines · 59 tokens per session scan A e3b18dd4a70e
subject-learning-assistant is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,777 once invoked, about $0.0003 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
study
Guide structured learning for a topic by diagnosing current level, defining stage goals, building a learning path, generating practice, and running review loops. Use when the user wants to learn something step by step, start from zero, build a study plan, prepare for an exam or skill, get guided practice, or continue…
eli5
Create a simple, picture-first explanation of a topic, defaulting to self-contained HTML. Use when the user says ELI5, asks to explain something like they are five, or wants a visual explanation with very few words; do not use for ordinary concise explanations that do not ask for this style.
pinpoint-lesson
Compose a long-form pin-point lesson from one paper and register it as a Zotero child note. Use when the user provides a PDF or paper title and wants a math-grounded, idea-genealogy, fundamental-why analysis rather than a quick summary. Contrast with the summary skill, which produces a shorter overview note.
mental-health-psychoeducation
Comprehensive psychoeducation on mental health conditions, therapy modalities, evidence-based coping techniques, psychiatric medications, and self-assessment frameworks. Educational resource only — not medical advice, diagnosis, or treatment. Use when learning about mental health concepts, understanding therapy…
learning-coach
Master evidence-based study techniques including active recall, spaced repetition, deliberate practice, and accelerated learning. Build efficient learning systems that maximize retention and skill acquisition.
how-to-read-a-book
Distills Mortimer Adler's How to Read a Book into a systematic active-reading framework covering inspectional, analytical, and syntopical reading. Use when a user wants to read more deeply, extract the core argument of a book, compare ideas across multiple texts, or move from information-gathering to genuine…