SkillAtlasSkill 详情

antfu-create-pr

A curated collection of Agent Skills reflecting Anthony Fu's preferences, experience, and best p...

审核状态:已审核Quality 72Security 90

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年9月30日

Anthony Fu's Skills

A curated collection of Agent Skills reflecting Anthony Fu's preferences, experience, and best practices, along with usage documentation for the tools.

[!IMPORTANT] This is a proof-of-concept project for generating agent skills from source documentation and keeping them in sync. I haven't fully tested how well the skills perform in practice, so feedback and contributions are greatly welcome.

Installation

pnpx skills add antfu/skills --skill='*'

or to install all of them globally:

pnpx skills add antfu/skills --skill='*' -g

Learn more about the CLI usage at skills.

Skills

This collection is aim to be a one-stop collection of you are mainly working on Vite/Nuxt. It includes skills from different sources with different scopes.

Hand-maintained Skills

Opinionated

Manually maintained by Anthony Fu with his preferred tools, setup conventions, and best practices.

SkillDescription
antfuAnthony Fu's preferences and best practices for app/library projects (eslint, pnpm, vitest, vue, etc.)
antfu-create-prOpen reviewable PRs: Conventional Commits title, evidence-based body, before/after screenshots via gh --attach (adapted from moeru-ai/airi)

[!TIP] For design, see antfu/design, which ships the antfu-design skill alongside the @antfu/design package.

Skills Generated from Official Documentation

Unopinionated but with tilted focus (e.g. TypeScript, ESM, Composition API, and other modern stacks)

Generated from official documentation and fine-tuned by Anthony.

SkillDescriptionSource
vueVue.js core - reactivity, components, composition APIvuejs/docs
nuxtNuxt framework - file-based routing, server routes, modulesnuxt/nuxt
piniaPinia - intuitive, type-safe state management for Vuevuejs/pinia
viteVite build tool - config, plugins, SSR, library modevitejs/vite
vitepressVitePress - static site generator powered by Vitevuejs/vitepress
vitestVitest - unit testing framework powered by Vitevitest-dev/vitest
unocssUnoCSS - atomic CSS engine, presets, transformersunocss/unocss
pnpmpnpm - fast, disk space efficient package managerpnpm/pnpm.io

FAQ

What Makes This Collection Different?

This collection is opinionated, but the key difference is that it uses git submodules to directly reference source documentation. This provides more reliable context and allows the skills to stay up-to-date with upstream changes over time. If you primarily work with Vue/Vite/Nuxt, this aims to be a comprehensive one-stop collection.

The project is also designed to be flexible - you can use it as a template to generate your own skills collection.

Skills vs llms.txt vs AGENTS.md

To me, the value of skills lies in being shareable and on-demand.

Being shareable makes prompts easier to manage and reuse across projects. Being on-demand means skills can be pulled in as needed, scaling far beyond what any agent's context window could fit at once.

You might hear people say "AGENTS.md outperforms skills". I think that's true — AGENTS.md loads everything upfront, so agents always respect it, whereas skills can have false negatives where agents don't pull them in when you'd expect. That said, I see this more as a gap in tooling and integration that will improve over time. Skills are really just a standardized format for agents to consume—plain markdown files at the end of the day. Think of them as a knowledge base for agents. If you want certain skills to always apply, you can reference them directly in your AGENTS.md.

Generate Your Own Skills

Fork this project to create your own customized skill collection.

  1. Fork or clone this repository
  2. Install dependencies: pnpm install
  3. Update meta.ts with your own projects and skill sources
  4. Run pnpm start cleanup to remove existing submodules and skills
  5. Run pnpm start init to clone the submodules
  6. Run pnpm start sync to pull the latest source docs
  7. Ask your agent to Generate skills for \<project\> (recommended one at a time to manage token usage)

See AGENTS.md for detailed generation guidelines.

Sponsors

Sponsors

License

Skills and the scripts in this repository are MIT licensed.

其他

低风险

  • 来源需自行核对维护者身份。
  • 未检测到明显脚本安装指令。
  • 可能需要外部 token、网络权限或第三方服务。
  • 未检测到高风险命令。
  • 扫描发现:0 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/antfu/skills.git
  3. 将 "skills/antfu-create-pr" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/antfu/skills.git
  3. 将 "skills/antfu-create-pr" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/antfu/skills.git
  3. 将 "skills/antfu-create-pr" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/antfu/skills.git
  3. 将 "skills/antfu-create-pr" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/antfu/skills.git
  3. 将 "skills/antfu-create-pr" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: antfu-create-pr
description: Create a reviewable GitHub pull request from the current branch with a Conventional Commits title, a concise evidence-based body, and before/after screenshots for UI changes. Use when asked to open, create, publish, or prepare a PR.
metadata:
  author: Anthony Fu
  version: "2026.09.30"

Create Pull Request

Open a PR that a reviewer can understand from the body alone. Explain the changed behavior and why, not the list of changed files. Keep the body proportional to the change: a one-line fix gets a few sentences, a cross-module feature gets tables and diagrams.

Workflow

  1. Inspect the repo: git status, current branch, remotes, default branch, .github/PULL_REQUEST_TEMPLATE*, and AGENTS.md / CONTRIBUTING.md for PR rules.
  2. Compute the merge base against the target branch and record the exact base...head range the PR publishes. If the branch is stacked on another unmerged branch, target that branch and describe only this PR's own changes.
  3. Read the full diff. Separate runtime code from generated files, lockfiles, and snapshots. Trace changed code to its entry points, callers, and external boundaries so architecture claims are backed by file paths or symbols.
  4. Classify the PR (feature, fix, refactor, chore, docs) and decide which optional body sections earn their place. See pr-body.
  5. Run the checks that match the changed surfaces (focused tests, typecheck, lint). Record the exact commands and results.
  6. If the diff changes user-visible UI, capture before/after evidence. See visual-evidence.
  7. Write the body to a temporary file. Push the branch. Create the PR with gh pr create --title ... --body-file ... (add --attach for each screenshot). Use --draft when checks are still running or the work is not review-ready.
  8. Open the created PR and verify title, base, head, rendered tables, diagrams, and images.
  9. Address review comments: fix each confirmed issue, run focused checks, push, reply with evidence, and resolve the thread.

Title

Use Conventional Commits, matching how the repo already writes commit messages:

feat(scope): add retry to upload client
fix(scope): avoid double submit on enter
refactor: extract diff parsing from cli
chore(deps): update vite to v8
docs: clarify worktree setup
  • Lowercase, imperative, no trailing period, under ~70 characters.
  • Scope is the package, module, or feature name the repo already uses. Omit it when the change is repo-wide.
  • Squash-merge repos turn the title into the commit message; write it as the commit you want in history.

Body

Required in every PR:

  • ## Summary: the problem or capability first, then what changed and why this approach. Mention if the PR is stacked and on what.
  • Linked issues: closes #123 / fixes #123 / refs #123 so GitHub links and auto-closes.
  • ## Verification: exact commands run and their results, plus anything left unverified.

Optional, only when it helps the reviewer:

  • ## Change map: table of module, before, after, reason. Use for changes across several modules or ownership boundaries. Never a raw file list.
  • ## Architecture and behavior: a Mermaid flow, sequence, or state diagram when ordering, async work, or state transitions changed. For a fix, pair a Before and After diagram at the same abstraction level.
  • ## Boundaries and risks: table of invariant, failure mode, protection, evidence. Use when there are real failure modes, migrations, or external effects.
  • ## Visual changes: before/after image table for UI changes.
  • ## Rollout and follow-up: migrations, feature flags, known gaps. State whether a gap blocks merge.

If the repo has a PR template, keep its headings and fill them; add sections above only where the template leaves room.

Rules

  • Say what is verified, what is assumed, and what is not verified. Do not write "safe", "fixed", or "backward compatible" without pointing at the evidence.
  • Green CI proves only the checks CI runs. Focused tests prove only the behavior they cover.
  • Do not describe inherited changes from a parent branch as this PR's changes.
  • Use plain hyphens; never em dashes (U+2014) or en dashes (U+2013).
  • No filler ("This PR aims to...", "comprehensive", "robust"). Start sentences with the fact.
  • Do not paste tokens, secrets, user records, or full payloads into the body.
  • Do not commit screenshots or other PR-only artifacts to the repo; attach them with gh --attach.
  • If the PR was written with the help of an agent, say so in one line at the end of the body.

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!