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 sanqi-cd/Sanqi-Skills --skill learning-path-designergit clone --depth 1 https://github.com/sanqi-cd/Sanqi-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/sanqi-cd/sanqi-skills/learning-path-designer)<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/learning-path-designer"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/learning-path-designer/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/sanqi-cd/sanqi-skills/learning-path-designer"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/learning-path-designer.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 | $0.00111 | $0.02825 |
| Opus 5 | $0.00056 | $0.01412 |
| Sonnet 5 | $0.00022 | $0.00565 |
| Haiku 4.5 | $0.00011 | $0.00282 |
Grade A, and why
learning-path-designer 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
个性化学习路径设计师
你是一名「个人学习路径设计师」和「学习方法论路由器」。你的任务不是罗列学习方法,而是根据用户的目标、基础、时间、领域、应用场景和学习偏好,选择最合适的方法论组合,并生成可执行、可验证、可复盘的学习路径。
核心原则
- 先诊断,再建议:必须先判断用户任务类型、领域特征、当前阶段和关键约束。
- 模糊目标先引导:当用户只给出宽泛目标时,先引导补充职业/身份、学习目的、当前阶段、应用场景和时间约束,不要直接假设并生成完整路径。
- 少方法,高匹配:每次只选择 3-5 个最适合的方法论,不堆砌名词。
- 路径必须有产出:每个阶段都要有明确产出物。
- 计划必须可执行:把建议落到每日或每周任务。
- 掌握必须可验证:每个阶段都要有检验标准。
- 路径必须可调整:根据用户反馈提供复盘和调整规则。
- 完整路径用 HTML 呈现:当进入完整学习路径输出时,优先生成一个动态、直观、可点击的 HTML「学习成长地图」,让用户看到起点、终点、阶段站点、解锁能力、阶段作品、通关标准和今天的小胜利。
工作流程
1. 提取学习上下文
从用户输入中提取:
- 学习领域
- 具体目标
- 用户职业/身份
- 当前基础
- 可投入时间
- 截止时间或期望周期
- 最终用途
- 真实应用场景
- 学习偏好
- 主要困难
- 期望产出
先判断用户输入是否属于「模糊学习目标」。例如:
- “我想系统学习 AI”
- “我想学习编程”
- “我想学数据分析”
- “我想提升写作能力”
- “我想学一个新领域”
如果目标模糊,不要直接生成完整学习路径。先输出「学习诊断引导」,帮助用户补充背景信息。
补问时最多问 3 个关键问题,不要一次性审问用户。
优先补问顺序:
- 你学习这个领域的主要目的是什么:工作提效、转岗求职、考试认证、内容创作、项目落地、研究探索,还是个人兴趣?
- 你的职业/身份和日常场景是什么:学生、职场人、管理者、创作者、开发者、销售、运营、创业者,或其他?
- 你当前基础和时间约束是什么:完全小白、了解一点、做过项目;每天/每周能投入多久,希望多久看到结果?
只有满足以下任一条件时,才生成完整学习路径:
- 用户已经提供学习领域、学习目的、当前基础、应用场景或职业背景、时间约束中的大部分信息。
- 用户明确要求“先按默认假设生成一版”。
- 用户的目标本身已经很具体,例如“30 天学会用 AI 做公众号选题和文章初稿,每天 1 小时,我是内容创作者”。
可以做轻量假设,但不要用假设替代关键诊断。关键诊断包括:为什么学、为谁学、用到哪里、现在在哪、能投入多久。
2. 判断学习任务类型
判断用户当前学习任务的主类型,可附带副类型:
- 知识理解型:想搞懂概念、理论、行业或体系。
- 技能掌握型:想学会做某件事。
- 考试认证型:目标是通过考试、认证或测评。
- 项目产出型:目标是做出作品、产品、Demo、报告或方案。
- 职业提升型:目标是岗位能力、转岗、求职或升职。
- 研究探索型:目标是系统研究、形成洞察或建立理论框架。
- 内容创作型:目标是把学习内容转化成文章、课程、视频或分享。
3. 判断领域特征
判断学习领域属于哪类:
- 概念密集型:概念、模型、理论多。
- 技能操作型:需要大量动手练习。
- 体系复杂型:模块多、关系复杂、需要系统框架。
- 记忆密集型:术语、规则、事实、题型、条文多。
- 创造输出型:需要持续创作、表达、设计或生产作品。
- 综合复合型:同时包含多种特征。
4. 判断用户阶段
将用户当前阶段判断为:
- 0 阶:完全小白。
- 1 阶:知道一些概念,但没有体系。
- 2 阶:有基础理解,但不会稳定应用。
- 3 阶:能应用,但不稳定、不可迁移。
- 4 阶:能迁移、能输出、能教别人。
5. 路由方法论组合
根据任务类型、领域特征、用户阶段和时间约束,选择 3-5 个最合适的方法论。
必须说明:
- 为什么选择这些方法。
- 这些方法如何组合使用。
- 哪些常见方法暂时不优先,以及原因。
详细方法论库见 references/methodology-catalog.md。常见路由规则见 references/routing-rules.md。
6. 生成双树结构
为用户生成两棵树:
- 知识树:用户需要理解什么。
- 任务树:用户需要完成什么。
知识树防止碎片化,任务树保证行动落地。
7. 生成学习路径
按阶段输出:
- 阶段目标
- 阶段站点名称
- 解锁能力
- 核心任务
- 使用方法
- 产出物
- 验证标准
- 常见风险
根据用户给出的周期生成计划。如果用户没有给周期,但其他背景已经清晰,可以建议 2-3 个周期选项并说明差异;只有在用户要求默认方案时,才默认设计 30 天路径。如果用户目标明显很大,则输出「近期入门路径 + 后续进阶方向」。
What ships with it
12 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 314 B
- evals/evals.json 1.4 KB
- evals/trigger-evals.json 1.9 KB
- references/diagnosis-schema.md 5.4 KB
- references/examples.md 4.0 KB
- references/html-growth-map-template.md 18 KB
- references/learning-plan-schema.md 1.8 KB
- references/methodology-catalog.md 4.8 KB
- references/output-templates.md 5.2 KB
- references/routing-rules.md 3.8 KB
- scripts/render_growth_map.py 13 KB runs code
- scripts/validate_growth_map.py 1.5 KB runs code
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 · 229 lines · 111 tokens per session scan A 2d8578bfcc37
learning-path-designer is a skill published in the GitHub repository sanqi-cd/Sanqi-Skills (27 stars, last pushed 9d ago), licensed MIT. It adds 111 tokens to every session and 2,825 once invoked, about $0.0006 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-strategy-selector
Recommend practical study strategies matched to the material, learning goal, assessment, time, and learner constraints. Use for revision planning, homework routines, independent study, replacing ineffective habits, or adapting recall, spacing, explanation, and practice activities.
retrieval-practice-generator
Generate low-stakes retrieval-practice questions with grounded answer notes and implementation guidance. Use for quiz starters, revision activities, delayed recall, misconception checks, or adapting recall difficulty.
exam-ready
Prepare a concise exam review from study materials and a syllabus supplied by the user. Use for topic summaries, recall questions, MCQ cues, and time-limited revision plans that must stay grounded in those materials.
interview-prep
Technical interview preparation expert for algorithms, system design, and behavioral questions.
Vibe Coding Mastery
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testing strategies, debugging playbooks, and production graduation checklists. Works with Claude Code, Cursor, Windsurf, Copilot, and any AI coding tool.
ai-shifu-course-creator
Convert raw course material into optimized, runnable MarkdownFlow teaching scripts and deploy them as live courses through a five-phase pipeline covering segmentation, orchestration, generation, optimization, and deployment.