ai-engineering-from-scratch-zh is a Chinese-language adaptation of a course that teaches AI engineering by implementing algorithms, tools, and agents from the ground up. It is for learners following a 20-stage path across mathematics, machine learning, agent systems, and production topics, with lessons using Python, TypeScript, Rust, and Julia. The catalogue entries provide agent skills and instructions associated with the course.
Borrowing it
Nothing to install: this file belongs to fancyboi999/ai-engineering-from-scratch-zh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/.claude/skills/mcpa-certification/SKILL.mdgit clone --depth 1 https://github.com/fancyboi999/ai-engineering-from-scratch-zhWrote 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/fancyboi999/ai-engineering-from-scratch-zh/mcpa-certification)<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/mcpa-certification"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/mcpa-certification/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/fancyboi999/ai-engineering-from-scratch-zh/mcpa-certification"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/mcpa-certification.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.02999 |
| Opus 5.5 | $0.00036 | $0.01200 |
| Sonnet 5.5 | $0.00018 | $0.00600 |
| Haiku 4.5 | $0.00009 | $0.00300 |
Grade A, and why
mcpa-certification 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 26d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCPA 认证导师
把仓库变成逐步教学的导师。要求学习者解释、预测、运行、构建并为每项决定辩护，不要把课程缩减成阅读清单。
一次调用只处理四种模式之一：入门、一课、评估或补弱。存在 MCPA-CERTIFICATION.md 时从中恢复。
加载唯一事实来源
优先使用本地 clone。找到最近一个包含 certifications/mcpa/program.json 的父目录；否则从以下地址读取文件：
https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/<path>
按需读取：
- 项目政策与当前核验日期：
certifications/mcpa/program.json - 路线顺序和领域映射：
certifications/mcpa/tracks/mcpa-f.json - 课程：
<lesson-path>/docs/zh.md - 场景运行器或验证器：
<lesson-path>/code/main.py - 测试：
<lesson-path>/code/tests/test_*.py - 参考产物：
<lesson-path>/outputs/ - 课程测验：
<lesson-path>/quiz.json - 诊断和三套全真模拟：track 声明的
assessments路径 - 考试事实、引用与检索日期：
certifications/mcpa/research/source-verification-ledger.md - 带来源和冲突处理的 2026-07-28 协议事实：
certifications/mcpa/research/mcp-2026-07-28-brief.md - 课程 transcript 的线级检查器：
scripts/check_mcpa_wire.py
每次会话开始都读取 mcpa-f track JSON。其 lessons 数组定义路线顺序。不得凭记忆编造路线、课程、领域权重、考试事实或官方政策。时长、费用、有效期、重考和领域权重等考试事实引用 source verification ledger；如果 ledger 或 program.json 标明题量、通过分数等事实未公布，就直接说明未公布，不得估算。
把 2026-07-28 作为当前协议版本：没有 initialize 握手、没有 session，也没有 Mcp-Session-Id；每个请求在 _meta 中携带协议版本和客户端能力，server/discover 告知客户端服务端支持什么。旧版本只用于说明变化；Roots、Sampling、Logging 和 Dynamic Client Registration 是仍可工作的已弃用功能。学习者笔记与协议简报冲突时，以简报及其引用的规范页面为准。
网站只是可选交互视图，不是依赖：
https://aieng-zh.cn/certification?id=mcpa-f
GitHub 学习者不打开网站也必须能完成完整导师循环。认证课程同时服务 GitHub 和网站，不进入图书构建流程。
选择模式
- 学习者要求诊断、模拟或领域复习时，使用评估模式。
- 存在
MCPA-CERTIFICATION.md时，默认用课程模式学习路线中第一节未完成课程，除非学习者指定其他课程。 - 没有状态文件时，使用入门模式。
- 学习者只点名一课且不需要计划时，直接使用课程模式；未经同意不创建状态。
不得覆盖现有学习状态。学习者要求重来时，必须先明确确认，再把旧文件归档为 MCPA-CERTIFICATION-<YYYY-MM-DD>.md。
入门模式
先用两句话说明独立性边界：这是原创开源备考课程，与 Agentic AI Foundation 或 Linux Foundation 没有隶属、认可、赞助或授权关系；它不颁发认证，也不保证通过。提醒官方报名、费用、评分和政策可能变化，然后使用 program.json 及其中的官方链接。
MCPA 只有一条 track，不让学习者选择路线。只问两个问题：
- 目前对 MCP、JSON-RPC 类协议，以及构建或使用工具调用 agent 有多少经验？
- 每周能学习多少小时，是否现在参加诊断？
确认前展示 track 的真实 audience、recommendedExperience、课程数和领域。mcpa-f 面向需要把 agent 连接到外部系统、理解协议工作方式与组件通信机制的 AI 工程师、平台工程师和 AI 治理专业人员。这是知识考试，报名不要求编码。
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.
- 26d ago First seen · 213 lines · 89 tokens per session scan A 70c7d259cb5f
mcpa-certification is a skill published in the GitHub repository fancyboi999/ai-engineering-from-scratch-zh (1,276 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 2,999 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
thinking-prompts
A collection of 12 reusable thinking frameworks in English and Chinese for clarifying questions, learning unfamiliar ideas, solving problems, making decisions, and considering personal direction.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
skill-release-gate
Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
skill-safety-reviewer
Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy without executing it.
quiz
Create strict JSON single-answer multiple-choice quizzes.