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.
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 fancyboi999/ai-engineering-from-scratch-zh --skill skill-release-gategit 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/skill-release-gate)<a href="https://agentmods.dev/skills/fancyboi999/ai-engineering-from-scratch-zh/skill-release-gate"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/skill-release-gate/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/skill-release-gate"><img src="https://agentmods.dev/badge/skills/fancyboi999/ai-engineering-from-scratch-zh/skill-release-gate.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 | $0.00049 | $0.00981 |
| Opus 5 | $0.00024 | $0.00491 |
| Sonnet 5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
skill-release-gate 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 6d 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.
What it actually says
Skill 发布门禁
在发布或分发 Agent Skill 目录 bundle 前使用此 skill。
工作流
- 将
SKILL_ROOT解析为包含本已安装SKILL.md的绝对目录。不要假定进程 cwd 就是已安装 bundle。 - 从原始工作区工作目录解析
TARGET_ROOT，并将用户提供的候选解析为绝对TARGET_BUNDLE。 - 从
SKILL_ROOT读取references/eval-contract.md。 - 检查
TARGET_BUNDLE下evals/cases.json中的正例和近似请求触发案例。 - 检查
TARGET_BUNDLE下evals/artifacts.json中共享的 baseline 与使用 skill 后断言。 - 检查
TARGET_BUNDLE下evals/evidence.json中显式的脚本和安全结果。 - 检查
TARGET_BUNDLE下assets/hosts.json声明的运行时能力，并对照其assets/manifest.json验证目标文件哈希。 - 对于生产，用捕获结果替换确定性预测、产物、证据和宿主能力；设置四种捕获模式；并将每个原始触发观察、两份产物、完整证据集和非空宿主矩阵绑定到非空来源及匹配的 SHA-256 溯源摘要。这些本地检查可设置
localEvidenceReady，但可在本地重算的哈希不能证明捕获真实性。 - 获取一份外部 JSON 证明，其
evidenceRoot与报告相匹配；并从独立受信策略或发布渠道获得其精确字节的 SHA-256。证明必须是目标 bundle 外的常规文件。 - 执行前展示精确解析后的 argv。已安装评估器位于
SKILL_ROOT下的scripts/evaluate_skill.py。对随附课程 fixture，用python3、该绝对评估器路径、--fixture-demo和绝对TARGET_BUNDLE构建 argv。对生产，使用同一已安装脚本并传入--attestation、--trusted-attestation-sha256和绝对TARGET_BUNDLE，但不传--fixture-demo。 - 返回
checksPassed、fixturePassed、localEvidenceReady、trustAnchorValid、productionReady和passed，同时给出证据根、评估模式、失败检查、精确率、召回率、每个原始触发观察、每案例重复运行率、产物比较、脚本和安全证据、已安装目录树验证及可移植性矩阵。包含已解析脚本路径、已解析目标路径、cwd、精确 argv 和退出码。将不可用观察标为未验证。
Output contract
返回完整 JSON 评估报告。保留每项分层检查及其证据，避免一个通过的汇总掩盖路由、产物、脚本、安全、已安装目录树或可移植性失败。fixturePassed 表示教学 fixture 成功；localEvidenceReady 仅表示本地摘要完整性；只有 productionReady 也具有有效的包外信任锚时，passed 才为 true。
Failure behavior
若配置无效、溯源缺失或不匹配、受信证明缺失或无效、文件哈希不同、必需能力缺失，或任一生产门禁失败，均以非零结果停止并报告失败层。显式 --fixture-demo 路径仅在 fixturePassed 为 true 时才可成功退出，且绝不作出发布声明。绝不自动发布、安装到其他位置、修复证据、创建信任决策或放宽阈值。
不要仅因 SKILL.md 能解析或一个正例 prompt 被激活就发布 bundle。目标宿主丢弃必需伴随文件或忽略必需运行时扩展时，不要将包标为可移植。
What ships with it
7 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.
- 6d ago First seen · 36 lines · 49 tokens per session scan A dbb7a5067c92
skill-release-gate is a skill published in the GitHub repository fancyboi999/ai-engineering-from-scratch-zh (1,048 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 981 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 2026-09-03.
Other skills, from other repositories
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.
skill-contract-reviewer
Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementation.
skill-invocation-router
Design and test explicit human, implicit model or agent, programmatic application, bounded skill-composition, and harness activation policies for an Agent Skill catalog.
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-catalog-builder
Build a bounded Agent Skill catalog across explicit discovery scopes and report collisions before loading instruction bodies.
skill-safety-reviewer
Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy without executing it.