Agent skill

AI Pm Method AI Engineering

by SpaceZephyr in SpaceZephyr/career.skill

《AI Engineering: Building Applications with Foundation Models》(Chip Huyen, O'Reilly 2025) 方法论。

No licenceAuto-check passedAI & LLM Engineering

Install AI Pm Method AI Engineering

skills CLI
$ npx skills add SpaceZephyr/career.skill --skill ai-pm-method-ai-engineering -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install SpaceZephyr/career.skill ai-pm-method-ai-engineering --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/SpaceZephyr/career.skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'已制作Skill/AI产品经理/ai-pm-method-ai-engineering' .claude/skills/ai-pm-method-ai-engineering && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ai-pm-method-ai-engineering
GitHub stars
160
Token cost
~1.2k tokens
SKILL.md length
454 words
Files
2 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
None found

At a glance

《AI Engineering: Building Applications with Foundation Models》(Chip Huyen, O'Reilly 2025) 方法论。

  • Works in 4 steps: 定义评测维度——Domain capability / Generation… → 写 Scoring Rubric——每档配锚定 example,3 人独立标注… → 三套评测集——Production baseline(真实分布)+… → …
  • Tasks that involve Fine-tuning
  • SKILL.md covers 什么时候用我, 核心框架, 决策规则(10 条,来源标注) and 检查清单, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Pm Method AI Engineering is an agent skill from SpaceZephyr/career.skill. 《AI Engineering: Building Applications with Foundation Models》(Chip Huyen, O'Reilly 2025) 方法论。 把 Huyen 的 evaluation-driven development、三层 AI stack、prompt/RAG/finetune 决策树、agent 设计模式 转化为 AI PM 可执行的判断框架。用于 AI 需求评审、方案讨论、发布决策。每条规则标注原书章节。 触发词:「AI Engineering」「Chip Huyen」「evaluation-driven development」「EDD」 「RAG vs fine-tune」「agent 设计」「AI 上线」「AI 评测集」「模型选型」。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/framework.md`).

It sits in AI & LLM Engineering, covering Fine-tuning and Retrieval-augmented generation. The repository describes itself as: 告诉 AI 你的职业,它帮你把工作拆成一套可以用的 Skill 库.

When your agent uses it

  • Tasks that involve Fine-tuning
  • Tasks that involve Retrieval-augmented generation

Example prompts

  • “/ai-pm-method-ai-engineering”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 定义评测维度——Domain capability / Generation quality / Instruction-following / Cost & latency 四支柱,每项定"业务可翻译"阈值(例:事实性 ≥80% → 客服自动化率 30%)
  2. 写 Scoring Rubric——每档配锚定 example,3 人独立标注 Kappa ≥0.6,否则回炉
  3. 三套评测集——Production baseline(真实分布)+ Sliced(按用户段/语言/场景)+ Failure-mode(typo、越界、prompt injection)。样本 <30 不做发布决策
  4. Meta-evaluation——评测本身可靠吗?用 AI judge 必须用人标数据校准(self-bias / position bias / length bias)

What it can do on your machine

Read from SKILL.md and the folder at commit 2627168. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Pm Method AI Engineering loads about 1.2k tokens when it runs, and up to ~4.8k if it reads all its reference files. Until then it costs about 95 tokens; SKILL.md has 454 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 454 words (~1,183 tokens).

“Chip Huyen 的核心主张:AI 产品的胜负不在模型,在系统——评测、数据、组件拆分、可观测性。 PM 的任务不是"想一个 AI 功能",是"先定义'好'长什么样,再决定用什么技术"。”

— opening of SKILL.md by SpaceZephyr
name
ai-pm-method-ai-engineering

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in 已制作Skill/AI产品经理/ai-pm-method-ai-engineering of SpaceZephyr/career.skill.

  • SKILL.md
  • references/framework.md

Open the folder on GitHubat commit 2627168

Compare with similar skills

AI Pm Method AI Engineering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI Pm Method AI Engineering compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Pm Method AI Engineering this skillSpaceZephyr/career.skill160—~1.2kAutomated safety check: PassNone
Jd Gap Analysisstarkyru/learn-ai107—~1.9kAutomated safety check: PassMIT
Enterprise AIoracle/skills876—~1.4kAutomated safety check: PassUPL-1.0
LLM Opsdavila7/claude-code-templates32k3 repos~2kAutomated safety check: PassMIT
AI Learning JournalLeoYeAI/openclaw-master-skills2.2k—~2.6kAutomated safety check: PassMIT
LLM App Builderrevfactory/harness-1001.3k—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Jd Gap Analysis

    starkyru/learn-ai

    Analyze a job description (pasted text OR a URL) and find the AI/ML/GenAI topics it requires that this learn-ai course does NOT yet cover.

    107 GitHub stars~1.9k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Enterprise AI

    oracle/skills

    Official

    Oracle Enterprise AI guidance for building, deploying, securing, estimating cost for, and integrating AI models, agents, RAG, Responses API workflows, custom or imported models, fine-tuning, model…

    876 GitHub stars~1.4k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed
  • LLM Ops

    davila7/claude-code-templates

    LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

    32k GitHub starsUsed in 3 repos~2k tokens
    AI & LLM EngineeringAuto-check passed
  • AI Learning Journal

    LeoYeAI/openclaw-master-skills

    AI 学习记录与成长追踪工具。用于记录 AI/LLM 学习笔记、使用心得、Prompt 技巧、工具体验等,并提供学习指导和规划。当用户提到以下任何话题时都应使用此 skill:AI 学习记录、学习笔记、AI 使用心得、Prompt 工程学习、模型对比体验、AI 工具使用记录、LLM 学习、RAG 学习、Agent 学习、MCP 学习、AI 微调实践、AI 学习规划、怎么学 AI、AI…

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • LLM App Builder

    revfactory/harness-100

    Full pipeline where an agent team collaborates to develop an LLM app.

    1.3k GitHub stars~1.9k tokensUpdated 6 mo ago
    AI & LLM EngineeringAuto-check passed
  • Official

    A skill your agent uses when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or PAIDF Data Mining…

    3.5k GitHub stars~3.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from SpaceZephyr/career.skill

All 15 skills in this repo
  • AI Pm Method Yujun

    SpaceZephyr/career.skill

    《俞军产品方法论》(俞军等,中信出版社 2019) 方法论。把书中的用户价值公式、交易模型、决策效用理论 改造为 AI 产品经理在 AI 化决策 / 需求评估 / 效用比较场景可直接执行的规则集。

    160 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • AI Pm Advisory Board

    SpaceZephyr/career.skill

    AI 产品经理顾问团总控。成员:Marty Cagan、Andrej Karpathy、梁宁(专家视角)+ 《AI Engineering》(Chip Huyen)、《Prediction Machines》(Agrawal/Gans/Goldfarb)、 《俞军产品方法论》(方法论)。

    160 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Investing Advisory Board

    SpaceZephyr/career.skill

    投资专家顾问团总控。成员:段永平、查理·芒格、霍华德·马克斯(专家视角)+ 《聪明的投资者》《穷查理宝典》《投资最重要的事》(方法论)。

    160 GitHub stars~481 tokensUpdated 3 mo ago
    Auto-check passed
  • Career Skill Factory

    SpaceZephyr/career.skill

    职业 Skill 工厂 2.0(career-skill-planner 升级版)。用户输入一个职业或行业,本 Skill 自动完成: (1) 遴选该行业 3 位顶尖专家,蒸馏其心智模型和决策方式,生成 3 个专家视角 Skill(参考女娲方法论); (2) 遴选该行业 3 本顶尖书籍,提炼成可执行方法论,生成 3 个方法论 Skill(参考 book2skills 方法论); (3) 生成…

    160 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check: warnings
  • AI Pm Advisor Cagan

    SpaceZephyr/career.skill

    Marty Cagan 视角顾问。以 Cagan 的心智模型和判断方式,为 AI 产品经理场景做分析. An agent skill from SpaceZephyr/career.skill.

    160 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed
  • AI Pm Advisor Karpathy

    SpaceZephyr/career.skill

    Andrej Karpathy 视角顾问。以 Karpathy 的心智模型和工程师式判断,为 AI 产品经理场景做分析。

    160 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

Questions about AI Pm Method AI Engineering

What does AI Pm Method AI Engineering do?

《AI Engineering: Building Applications with Foundation Models》(Chip Huyen, O'Reilly 2025) 方法论。. skill.

When should I use AI Pm Method AI Engineering?

AI Pm Method AI Engineering fits situations like: tasks that involve Fine-tuning; tasks that involve Retrieval-augmented generation.

How do I install AI Pm Method AI Engineering in Claude Code?

Run `npx skills add SpaceZephyr/career.skill --skill ai-pm-method-ai-engineering -a claude-code`. Or copy the skill folder (已制作Skill/AI产品经理/ai-pm-method-ai-engineering in SpaceZephyr/career.skill) into .claude/skills/ai-pm-method-ai-engineering in your project. Claude Code loads it when a task matches its description.

How do I install AI Pm Method AI Engineering in Codex?

Run `npx skills add SpaceZephyr/career.skill --skill ai-pm-method-ai-engineering -a codex`. Or copy the skill folder (已制作Skill/AI产品经理/ai-pm-method-ai-engineering in SpaceZephyr/career.skill) into .agents/skills/ai-pm-method-ai-engineering in your project. Codex loads it when a task matches its description.

Can I use AI Pm Method AI Engineering in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add SpaceZephyr/career.skill --skill ai-pm-method-ai-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-pm-method-ai-engineering, .gemini/skills/ai-pm-method-ai-engineering, .github/skills/ai-pm-method-ai-engineering and .opencode/skills/ai-pm-method-ai-engineering in your project.

What does AI Pm Method AI Engineering need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Pm Method AI Engineering is instructions for the agent only.

Does AI Pm Method AI Engineering access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Pm Method AI Engineering safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does AI Pm Method AI Engineering use?

No licence was found for AI Pm Method AI Engineering or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does AI Pm Method AI Engineering use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.6k tokens, read only when the agent opens those files.

What are the alternatives to AI Pm Method AI Engineering?

Skills that share tags, products or a category with AI Pm Method AI Engineering: Jd Gap Analysis (starkyru/learn-ai, 107 stars), Enterprise AI (oracle/skills, 876 stars), LLM Ops (davila7/claude-code-templates, 32k stars) and AI Learning Journal (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Pm Method AI Engineering?

SpaceZephyr (a GitHub user) maintains it in SpaceZephyr/career.skill, which has 160 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on July 5, 2026.

Source: SpaceZephyr/career.skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.