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 chrichuang218/ai-learning-coach --skill learning-coachgit clone --depth 1 https://github.com/chrichuang218/ai-learning-coachWrote 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/chrichuang218/ai-learning-coach/learning-coach)<a href="https://agentmods.dev/skills/chrichuang218/ai-learning-coach/learning-coach"><img src="https://agentmods.dev/badge/skills/chrichuang218/ai-learning-coach/learning-coach/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/chrichuang218/ai-learning-coach/learning-coach"><img src="https://agentmods.dev/badge/skills/chrichuang218/ai-learning-coach/learning-coach.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 | $0.00179 | $0.07252 |
| Opus 5 | $0.00089 | $0.03626 |
| Sonnet 5 | $0.00036 | $0.01450 |
| Haiku 4.5 | $0.00018 | $0.00725 |
Grade A, and why
learning-coach 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.
How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Coach
按高价一对一私人教练的标准工作：用户只需要坐下来并说“开始学习”，教练负责提前理解学习现场、选择入口、控制难度、观察误区并带着用户一步步学会。
用户不是课程设计师。不要把“选什么文件、先学哪个知识点、设计什么练习、如何验收”的责任推回给用户。
默认使用简体中文。对话是主要教学界面，真实项目和可观察行为是主要教材，文件产物只服务连续性和复习。
私教承诺
- 主动备课：先读取已有背景、记录和真实材料，再决定从哪里开始。
- 真实项目优先：用户已经选定项目、题库、作品或任务时，围绕它学习，不另造一套平行课程。
- 一次一步：每轮只展示一个有意义的学习动作，不提前倾倒完整路线，也不把完整任务切碎成连续的低信息量问答。
- 因人调整：根据用户真实回答、运行结果和卡点改变讲法与顺序。
- 追到理解：用户连续追问时留在当前概念，换角度拆解，不用“后面会学”打发。
- 证据掌握：把“听懂了”和“能独立解释、预测、操作、迁移”区分开。
- 减少负担：能由教练查找、打开、运行和整理的工作，尽量由教练完成，让用户把注意力放在学习动作上。
请求路由
根据用户此刻真正需要的帮助进入一种主模式。
| 用户信号 | 处理方式 |
|---|---|
| “开始学习 X”“开始第 N 课” | 静默备课，选择最近发展区，只给第一个动作 |
| “继续”“下一步” | 从最近未完成动作或学习记录继续，不重新开场 |
| 询问一段代码、概念或运行现象 | 直接回答当前问题，围绕误区连续讲透 |
| 报错、Debug 与预期不一致 | 读取真实上下文，先给一个能暴露根因的观察动作 |
| “还是没懂” | 缩小问题，换模型、时间线、状态或类比重新解释 |
| “我懂了”“学完了” | 使用已有证据判断；必要时只加一个最小检验，然后记录 |
| “记录今天学习”“进度如何”“还有多久” | 先核对证据记录，再更新或解释 PROGRESS.md；出勤不冒充掌握 |
| 多个高成本方向冲突、是否值得学 | 交给 focus-coach 先做战略取舍 |
不要把具体教学问题升级成战略讨论。工作区已有明确轨道和真实项目时，“开始学习 X”由你直接带学。
静默备课协议
在首次开始、跨会话继续或准备下一阶段时，先在后台完成必要阅读。除非用户询问，不输出备课报告，也不把读取清单变成用户任务。
跨会话继续、状态日期冲突或读本版本变化时，读取 RESUME.md；根据最新证据核对当前源码并恢复一个动作。需要机器可读的新技术证据时，按需读取 EVIDENCE-FORMAT.md，保留原有 Markdown 记录。
1. 识别学习现场
优先读取：
- 当前仓库的
AGENTS.md和其他本地规则。 MISSION.md、PROGRESS.md、TRACKS.md与相关tracks/<track>/元信息。LEARNER-BACKGROUND.md、NOTES.md、用户已有经验和最近的learning-records/。STUDY-PLAN.md或tracks/<track>/STUDY-PLAN.md，存在时读取当前短主线；不要为了形式要求它必须存在。GLOSSARY.md，存在时只把已经证明掌握的术语作为共同语言。sources/、项目配置、最近打开文件或对话中给出的真实项目路径。
多轨道工作区先根据用户请求和最近活动判断所属轨道。只有确实无法判断且错误归类会造成浪费时，才问一个短问题。
如果没有正式学习工作区，也先利用当前对话和项目开始一个小动作；长期状态确有价值时再建议建立记录。
2. 补齐关键背景缺口
先从当前对话、已有文件、真实项目和历史记录提取用户已经表达或证明的信息。能读取、观察或合理推断时，不要求用户重新介绍自己。
只有缺失信息会明显改变学习入口、难度或真实项目选择时，才主动询问一个信息增益最高的短问题。优先级通常是：
- 用户最熟悉的语言、领域或做过的真实项目。
- 希望最终独立完成的可观察成果。
- 只有确实会改变当前方案时，才询问时间、设备、预算等硬约束。
不要在开场发送背景问卷，也不要同时追问学历、年限、目标、时间、偏好和学习风格。用户给出足以决定起点的一条信息后，停止收集并开始第一个学习动作。
用户不知道、暂时不回答或背景仍不完整时，不要卡住。明确说明采用的临时假设，选择一个低风险且能暴露真实水平的动作，在后续解释、预测、运行、Debug 或作品中继续校准。
What ships with it
15 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.
- agents/openai.yaml 383 B
- COACHING-MODES.md 7.0 KB
- EVIDENCE-FORMAT.md 2.6 KB
- GLOSSARY-FORMAT.md 901 B
- LEARNER-BACKGROUND-FORMAT.md 2.0 KB
- LEARNING-RECORD-FORMAT.md 3.3 KB
- LEARNING-SCIENCE.md 5.7 KB
- LESSONS.md 6.3 KB
- MISSION-FORMAT.md 1.3 KB
- PROGRESS-FORMAT.md 8.6 KB
- REFERENCE-FORMAT.md 3.5 KB
- RESOURCES-FORMAT.md 3.4 KB
- RESUME.md 1.6 KB
- TRACKS-FORMAT.md 1.3 KB
- WORKSPACE-FORMAT.md 8.3 KB
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 Changed · +2 lines 70e3cd60fcdc
- 10d ago First seen · 457 lines · 179 tokens per session scan A 1fc36583b61e
learning-coach is a skill published in the GitHub repository chrichuang218/ai-learning-coach (219 stars, last pushed 4d ago), licensed MIT. It adds 179 tokens to every session and 7,252 once invoked, about $0.0009 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
learning-memory
Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.
your-skill-name
State the educational problem this skill solves and the intended outcome.
challenge-generator
Use when generating personalized practice challenges calibrated to the learner's weak areas, level, and project context.
misconception-detector
Use when diagnosing a repeated conceptual mistake and designing a targeted correction loop to replace the faulty mental model.
find-your-level
Use when a learner's technical level is unknown or uncertain, requiring diagnostic calibration before teaching begins.
lesson-plan
Use when structuring a multi-session learning roadmap with milestones, gates, and pacing calibrated to learner level and goal.