当前位置：首页 > news >正文

超牛掰的工程化Skills开发必备之初始化你的AI coding Agent环境

news 2026/6/20 13:47:40

如果你安装了一整套skill，Claude Code应该会提示你运行一个skill。

一. 干嘛用的?

/setup-matt-pocock-skills 是mattpocock/skills 整套 AI 工程技能库的一次性环境引导脚本，属于所有其他技能的前置依赖，项目内必须先运行它，其余/tdd``/grill-me``/to-prd等技能才能正常工作。

二. 具体会做什么？

不知道你在vibing coding的时候，是否初始化了你的Agent环境？就是配置 CLAUDE.md, 还有 issue tracker问题跟踪器等。如果没有这些文件，当你在开发代码的过程当中，AI coding很容易会走偏, 以至于最后整个项目混乱不堪, 你不断地调，不断地优化，代码越来越乱，最后甚至会放弃。

校验项目根目录，创建.claude/skills/标准技能存放目录（Claude Code、Cursor、Aider 等 AI 编程工具统一读取该目录）
检测 Git、Node、pnpm 环境，缺少依赖给出安装指引
生成项目专属配置根文件，打通所有 skill 共享上下文

生成全局核心文件（整套技能的公共底座）

(1）CONTEXT.md 或者 Claude.md（最重要产出）

作用：统一领域术语、业务名词、技术黑话，所有 skill 读取这份文档统一认知
内容：项目业务领域模型、通用命名规范、技术栈约定、历史设计决策，后续/grill-with-docs会持续自动更新它
价值：大幅减少 AI 重复提问、降低 token 消耗，保证全项目输出口径一致

(2）docs/adr/ 架构决策记录目录

自动创建 ADR 存放文件夹，规范架构决策归档

/improve-codebase-architecture、/grill-with-docs会读取历史决策，避免重复讨论旧方案

（3）工程规范配置集

Issue 管理规范：定义 bug/feature/refactor 等分类标签、处理流程（供/triage自动分类工单）
文档路径约定：统一 API 文档、需求文档、测试文档存放目录
代码检查基线：对接 pre-commit、ESLint、TS 类型校验标准，配合/setup-pre-commit使用

以下是我的示范：

❯ /setup-matt-pocock-skills ⏺ Bash(git remote -v; printf '\n--- git config remote sections ---\n'; git config --local --get-regexp '^remote\.' || true) ⎿ fatal: not a git repository (or any of the parent directories): .git --- git config remote sections --- fatal: --local can only be used inside a git repository Searched for 1 pattern, listed 1 directory (ctrl+o to expand) ⏺ I looked at /Users/kevin/codes/cvd-qc, and it appears to be an empty directory, not currently a git repo: - No .git / no git remotes. - No CLAUDE.md or AGENTS.md. - No CONTEXT.md / CONTEXT-MAP.md. - No docs/adr/, docs/agents/, or .scratch/. We’ll configure the skills from scratch. Section A — Issue tracker The “issue tracker” is where issues live for this repo. Skills like to-issues, triage, to-prd, and qa read from and write to it — they need to know whether to call gh issue create, write markdown files under .scratch/, or follow some other workflow you describe. Since this directory has no git remote, my default recommendation is Local markdown. Which issue tracker should these skills use for this repo? 1. Local markdown — issues live as files under .scratch/<feature>/ in this repo. Good for a new/solo project or repo without a remote. 2. GitHub — issues live in GitHub Issues, using the gh CLI. 3. GitLab — issues live in GitLab Issues, using the glab CLI. 4. Other — Jira, Linear, etc.; tell me the workflow in one paragraph. Please choose one: Local markdown, GitHub, GitLab, or Other. ✻ Churned for 13s ❯ 永远记住请说中文 Recalled 1 memory, searched memories, wrote 2 memories (ctrl+o to expand) ⏺ 已记住：以后默认用中文回复你。 继续刚才的设置：这个目录目前没有 git remote，也没有现成配置文件。 请选择 Issue Tracker： 1. Local markdown（推荐） — issue 写到本仓库 .scratch/<feature>/ 下 2. GitHub — 使用 GitHub Issues 和 gh CLI 3. GitLab — 使用 GitLab Issues 和 glab CLI 4. Other — Jira、Linear 等；你可以描述流程 ✻ Cogitated for 12s ❯ 1 ⏺ 好的，Issue tracker 选择：Local markdown。 Section B — Triage label vocabulary（三方/状态标签） triage 技能会把 issue 放进一个状态流里：需要评估、等待提问者补充、可以交给 agent、需要人类处理、或不处理。 即使你用的是本地 markdown issue，这些状态名也会写进 issue 文件里，方便后续技能识别。 默认的五个状态名是： - needs-triage — 需要维护者评估 - needs-info — 等待提问者补充信息 - ready-for-agent — 描述完整，可以让 agent 自动处理 - ready-for-human — 需要人类实现 - wontfix — 不会处理 如果你没有已有标签体系，建议直接用默认值。 你要： 1. 使用默认标签（推荐） 2. 自定义部分或全部标签名 ✻ Churned for 4s ❯ 1 ⏺ 好的，Triage labels 选择：使用默认标签。 Section C — Domain docs（领域文档布局） 一些技能（例如 improve-codebase-architecture、diagnose、tdd）会读取： - CONTEXT.md：项目的领域语言、业务规则、重要概念 - docs/adr/：架构决策记录（ADR） 它们需要知道这是一个单上下文项目，还是 monorepo 那种多上下文项目。 当前目录是空的，所以我建议使用 Single-context：根目录一个 CONTEXT.md，根目录一个 docs/adr/。 请选择： 1. Single-context（推荐） — 根目录 CONTEXT.md + docs/adr/ 2. Multi-context — 根目录 CONTEXT-MAP.md 指向多个子项目/子领域的 CONTEXT.md ✻ Crunched for 3s ❯ 1 Read 3 files (ctrl+o to expand) ⏺ 确认：Domain docs 选择 Single-context。 因为当前目录里既没有 CLAUDE.md，也没有 AGENTS.md，我需要你决定要创建哪一个配置文件。 我会写入以下草稿： 将创建的 Agent skills 区块 ## Agent skills ### Issue tracker Issues are tracked as local markdown files under `.scratch/<feature-slug>/`. See `docs/agents/issue-tracker.md`. ### Triage labels This repo uses the default triage label vocabulary: `needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, and `wontfix`. See `docs/agents/triage-labels.md`. ### Domain docs This repo uses a single-context domain docs layout. See `docs/agents/domain.md`. 将创建的文件 - docs/agents/issue-tracker.md：使用 local markdown issue tracker 约定 - docs/agents/triage-labels.md：使用默认五个 triage label - docs/agents/domain.md：使用 single-context domain docs 规则 请选择要创建哪个主配置文件： 1. CLAUDE.md（推荐） — Claude Code 会直接读取 2. AGENTS.md — 更通用的 agent 说明文件 ✻ Crunched for 7s ❯ 1 ⏺ Bash(mkdir -p docs/agents) ⎿ Done ⏺ Write(CLAUDE.md) ⎿ Wrote 13 lines to CLAUDE.md 1 ## Agent skills 2 3 ### Issue tracker 4 5 Issues are tracked as local markdown files under `.scratch/<feature-slug>/`. See `docs/agents/issue-tracker.md`. 6 7 ### Triage labels 8 9 This repo uses the default triage label vocabulary: `needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, and `won tfix`. See `docs/agents/triage-labels.md`. … +4 lines (ctrl+o to expand) ⏺ Write(docs/agents/issue-tracker.md) ⎿ Wrote 19 lines to docs/agents/issue-tracker.md 1 # Issue tracker: Local Markdown 2 3 Issues and PRDs for this repo live as markdown files in `.scratch/`. 4 5 ## Conventions 6 7 - One feature per directory: `.scratch/<feature-slug>/` 8 - The PRD is `.scratch/<feature-slug>/PRD.md` 9 - Implementation issues are `.scratch/<feature-slug>/issues/<NN>-<slug>.md`, numbered from `01` 10 - Triage state is recorded as a `Status:` line near the top of each issue file (see `triage-labels.md` for the role strings) … +9 lines (ctrl+o to expand) ⏺ Write(docs/agents/triage-labels.md) ⎿ Wrote 15 lines to docs/agents/triage-labels.md 2 # Triage Labels 3 The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this r epo's issue tracker. 4 5 | Label in mattpocock/skills | Label in our tracker | Meaning | 6 | -------------------------- | -------------------- | ---------------------------------------- | 7 | `needs-triage` | `needs-triage` | Maintainer needs to evaluate this issue | 8 | `needs-info` | `needs-info` | Waiting on reporter for more information | 9 | `ready-for-agent` | `ready-for-agent` | Fully specified, ready for an AFK agent | 10 | `ready-for-human` | `ready-for-human` | Requires human implementation | … +6 lines (ctrl+o to expand) ⏺ Write(docs/agents/domain.md) ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── Create file docs/agents/domain.md ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌ 1 # Domain Docs 2 3 How the engineering skills should consume this repo's domain documentation when exploring the codebase. 4 5 ## Before exploring, read these 6 7 - **`CONTEXT.md`** at the repo root, or 8 - **`CONTEXT-MAP.md`** at the repo root if it exists — it points at one `CONTEXT.md` per context. Read each one relevant to the topic. 9 - **`docs/adr/`** — read ADRs that touch the area you're about to work in. In multi-context repos, also check `src/<context>/docs/adr/` for context-scoped decisions. 10 11 If any of these files don't exist, **proceed silently**. Don't flag their absence; don't suggest creating them upfront. The producer sk ill (`/grill-with-docs`) creates them lazily when terms or decisions actually get resolved. 12 13 ## File structure 14 15 Single-context repo (most repos): 4 5 Issues are tracked as local markdown files under `.scratch/<feature-slug>/`. See `docs/agents/issue-tracker.md`. 6 7 ### Triage labels 8 9 This repo uses the default triage label vocabulary: `needs-triage`, `needs-info`, `ready-for-agent`, `ready-for-human`, and `won tfix`. See `docs/agents/triage-labels.md`. … +4 lines (ctrl+o to expand) ⏺ Write(docs/agents/issue-tracker.md) ⎿ Wrote 19 lines to docs/agents/issue-tracker.md 1 # Issue tracker: Local Markdown 2 3 Issues and PRDs for this repo live as markdown files in `.scratch/`. 4 5 ## Conventions 6 7 - One feature per directory: `.scratch/<feature-slug>/` 8 - The PRD is `.scratch/<feature-slug>/PRD.md` 9 - Implementation issues are `.scratch/<feature-slug>/issues/<NN>-<slug>.md`, numbered from `01` 10 - Triage state is recorded as a `Status:` line near the top of each issue file (see `triage-labels.md` for the role strings) … +9 lines (ctrl+o to expand) ⏺ Write(docs/agents/triage-labels.md) ⎿ Wrote 15 lines to docs/agents/triage-labels.md 2 # Triage Labels 3 The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this r epo's issue tracker. 4 5 | Label in mattpocock/skills | Label in our tracker | Meaning | 6 | -------------------------- | -------------------- | ---------------------------------------- | 7 | `needs-triage` | `needs-triage` | Maintainer needs to evaluate this issue | 8 | `needs-info` | `needs-info` | Waiting on reporter for more information | 9 | `ready-for-agent` | `ready-for-agent` | Fully specified, ready for an AFK agent | 10 | `ready-for-human` | `ready-for-human` | Requires human implementation | … +6 lines (ctrl+o to expand) ⏺ Write(docs/agents/domain.md) ⎿ Wrote 51 lines to docs/agents/domain.md 2 # Domain Docs 3 How the engineering skills should consume this repo's domain documentation when exploring the codebase. 4 5 ## Before exploring, read these 6 7 - **`CONTEXT.md`** at the repo root, or 8 - **`CONTEXT-MAP.md`** at the repo root if it exists — it points at one `CONTEXT.md` per context. Read each one relevant to the topic. 9 - **`docs/adr/`** — read ADRs that touch the area you're about to work in. In multi-context repos, also check `src/<context>/doc s/adr/` for context-scoped decisions. … +46 lines (ctrl+o to expand) ⏺ 设置完成。 已创建： - CLAUDE.md - docs/agents/issue-tracker.md - docs/agents/triage-labels.md - docs/agents/domain.md 当前配置为： - Issue tracker：本地 markdown，位于 .scratch/<feature-slug>/ - Triage labels：使用默认五个状态标签 - Domain docs：single-context 布局 之后这些技能会读取这些文件： - to-issues - triage - to-prd - diagnose - tdd - improve-codebase-architecture 以后如果只是微调规则，可以直接编辑 docs/agents/*.md。只有在你想切换 issue tracker 或重新初始化时，才需要重新运行这个 setup。 ✻ Crunched for 16s ※ recap: 目标是为当前空项目配置 Matt Pocock 工程技能，已完成本地 markdown issue、默认 triage 标签、single-context 文档布局，并创建 CLAUDE.md 与 docs/agents 文件。下一步可直接开始使用这些技能或继续初始化项目代码。 (disable recaps in /config)

学AI大模型的正确顺序，千万不要搞错了

🤔2026年AI风口已来！各行各业的AI渗透肉眼可见，超多公司要么转型做AI相关产品，要么高薪挖AI技术人才，机遇直接摆在眼前！

有往AI方向发展，或者本身有后端编程基础的朋友，直接冲AI大模型应用开发转岗超合适！

就算暂时不打算转岗，了解大模型、RAG、Prompt、Agent这些热门概念，能上手做简单项目，也绝对是求职加分王🔋

📝给大家整理了超全最新的AI大模型应用开发学习清单和资料，手把手帮你快速入门！👇👇

学习路线:

✅大模型基础认知—大模型核心原理、发展历程、主流模型（GPT、文心一言等）特点解析
✅核心技术模块—RAG检索增强生成、Prompt工程实战、Agent智能体开发逻辑
✅开发基础能力—Python进阶、API接口调用、大模型开发框架（LangChain等）实操
✅应用场景开发—智能问答系统、企业知识库、AIGC内容生成工具、行业定制化大模型应用
✅项目落地流程—需求拆解、技术选型、模型调优、测试上线、运维迭代
✅面试求职冲刺—岗位JD解析、简历AI项目包装、高频面试题汇总、模拟面经

以上6大模块，看似清晰好上手，实则每个部分都有扎实的核心内容需要吃透！

我把大模型的学习全流程已经整理📚好了！抓住AI时代风口，轻松解锁职业新可能，希望大家都能把握机遇，实现薪资/职业跃迁～