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 yyz666ai/Learning-Agent --skill adaptive-lesson-flowgit clone --depth 1 https://github.com/yyz666ai/Learning-AgentWrote 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/yyz666ai/learning-agent/adaptive-lesson-flow)<a href="https://agentmods.dev/skills/yyz666ai/learning-agent/adaptive-lesson-flow"><img src="https://agentmods.dev/badge/skills/yyz666ai/learning-agent/adaptive-lesson-flow.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00031 | $0.02035 |
| Opus 5 | $0.00015 | $0.01018 |
| Sonnet 5 | $0.00006 | $0.00407 |
| Haiku 4.5 | $0.00003 | $0.00203 |
Grade A, and why
adaptive-lesson-flow 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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自适应快节奏教学
把当前一章变成一份可完整翻阅的 HTML PPT。固定主线是:课堂讲解 → 点击选择题 → 课后独立练习 → 对话答疑。课堂负责讲懂,课后把练习留好;不要把打印输出或表单提交变成推进门禁。
先选节奏
已确认画像时不再追问基础、主题或学习时长。根据当前知识点的难度和已有证据决定:
- 简单且无明显误区:4–8 页、1 道选择题,答对后完成课堂,课后练习单独留好。
- 普通章节:8–16 页、1–3 道选择题;一个页面只承担一个教学动作。
- 概念密集或刚暴露误区:12–24 页、按知识密度安排选择题;每题只验证一个关键判断,不能用 12 页上限挤掉必要推导。
- 有基础或精进路线:跳过已证实的基础,先给一个真实任务或边界案例;只在卡点补最小概念。
不要因“谨慎”连续提问。信息不足但不影响当前第一小步时,给出最小可运行练习并开始。
零基础环境准备页
零基础的第一章只要会第一次运行代码,就必须在第一次运行代码前插入一张 HTML PPT「环境准备」页;纯概念且不运行代码的课程不需要。
这张页面必须写清:
- 需要下载的软件及用途,优先区分“必装”和“可选”;
- 对应操作系统的官方入口,以及不编造版本号的安装说明;
- 安装后的版本验证命令,并说明看到什么算成功;
- 本课程的课程项目目录、如何用 Cursor / Trae / 其他编辑器打开该目录;
- 本课代码文件位置和首次运行命令,命令必须与实际创建的文件名一致。
不要猜测操作系统。画像已有系统时只给该系统步骤;未知时用 macOS、Windows、Linux 三个紧凑分支供学习者对照。验证成功后写入 environment_ready;后续章节不得重复整套下载和安装,只在真正运行前显示一句环境先修检查。环境准备页的“本页请做”只能要求安装/验证或打开课程目录,不能要求写概念长答案。
章节讲义闭环
课堂和课后必须明确分开。课堂练习只包含页面内的点击选择题;课后练习是另外一道让学习者在真实项目里独立完成的任务。
- 一次生成当前章尚未完成的全部知识点;学习者可以从第一页翻到最后一页看完本章,不能在完成第一个练习后再生成同一章其余内容。
- 每个知识点先说它解决什么问题,再给一个可运行的最小例子。简单内容快讲,密集内容增加页面或选择题;但仍在同一份章节讲义内。
- 流程、状态变化、调用顺序或组件关系明显时,读取
visual-explainer,在代码前安排 Mermaid。 - 框架代码超过 10 个有效行或含多个陌生 API 时,读取
progressive-code-teaching,逐步搭建,不第一次展示整段长代码。 - 生成器提供了研究事实时,逐页讲解必须与权威来源一致;版本敏感 API 不得凭记忆补全。
- 点击题由
quiz-designer决定位置和数量;必答题不能被下一页、页码或运行输出绕过。
- 流程、状态变化、调用顺序或组件关系明显时,读取
- 选择题必须是页面内可点击选项,不让学习者在对话框输入 A/B 或写解释。答对时,在讲义内答对后自动进入下一页;答错时给一条最小提示并允许重选。
- 示例代码必须有详细中文注释,讲清陌生 API、关键行的目的和数据变化。课后练习必须指出真实项目文件夹、目标、运行方式与最多三条提示;学习者自己在编辑器或终端完成。
- 用
**关键结论**标出必须记住的一句话,用==核心警告==标出会直接导致误解或 bug 的边界。每页最多 2 处加粗和 1 处高亮;不得滥用高亮,不得把整段都变成重点。
- 用
- 每页 markdown 最后写清“本页请做”,让行动提示显示在 PPT 内;不要在对话输入框上方挂常驻提示。右侧对话框只在用户主动提问或异步生成时说话。
- 唯一的
practice_kind=homework页安排课后独立练习;最后一页类型必须为mastery,汇总目标并指向课后练习的项目目录。不能在 mastery 后追加页面。完成后的代码、运行结果、报错或问题直接发到右侧对话输入栏;不再生成终端输出框、正则验收或逐项打印结果检查。 - 必答课堂选择题通过后即可结束本章或进入下一章。课后练习不作为下一章的门禁,也不把一次运行结果宣称为长期掌握。
- 用户说当前讲义太浅、太长、太难、图少或代码看不懂时,路由
lesson-revision,先展示修订摘要,再由用户选择是否应用新版本。 - 课程内对话完成后,把真实问题和 Agent 总结追加到用户的个人课堂笔记,并在 HTML PPT 中显示。根据本课主题、问题内容和主动追问次数生成专属奖励;不要使用所有人相同的固定夸奖。
What ships with it
1 file 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.
- 7d ago First seen · 80 lines · 31 tokens per session scan A 1153c53c3a0b
adaptive-lesson-flow is a skill published in the GitHub repository yyz666ai/Learning-Agent (1 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 2,035 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
skillpack-creator
Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.
akirule
Aki's contextual rule router — invoke BEFORE acting whenever the task touches any of - .md/.vue/.css/.tsx/.rs/.sql files; docs, plan, README, CHANGELOG; UI, component, CSS, tailwind; SEO, schema, sitemap; release, version, commit, push, deploy; DB schema, migration; Tauri; i18n, UI copy; pricing, biz; UX review…