Token导航 LogoToken导航

Agent Skill · 前端设计

skills-skills(技能技能)

skills-skills 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

skills-skills 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在前端设计类的 10,216 个 Skill 里排第 6,576。

总安装 489周安装 21GitHub Stars 12,017下载 171核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:skills-skills(技能技能)
来源仓库:https://github.com/tukuaiai/vibe-coding-cn
仓库路径:skills/skills-skills
安装命令:
npx skills add https://github.com/tukuaiai/vibe-coding-cn --skill skills-skills
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/tukuaiai/vibe-coding-cn --skill skills-skills

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。通过 npx skills add 命令从指定仓库安装,需结合原始 README 核验具体用法。

安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。skills-skills 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/skills-skills

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/tukuaiai/vibe-coding-cn --skill skills-skills;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

skills-skills 怎么安装?

在终端执行 npx skills add https://github.com/tukuaiai/vibe-coding-cn --skill skills-skills。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

skills-skills 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

skills-skills 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

skills-skills 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

skills-skills 用的人多吗?

公开数据是累计安装 489 次,近一周安装 21 次,下载 171 次,GitHub 12,017 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

skills-skills 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 来源仓库有 12,017 星,维护活跃度相对可查。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
skills-skills

技能技能 · 本页

48912,017需要联网未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Claude Skills Meta-Skill

Turn scattered domain material into a Skill that is reusable, maintainable, and reliably activatable:

  • SKILL.md as the entrypoint (triggers, constraints, patterns, examples)
  • references/ for long-form evidence and navigation
  • optional scripts/ and assets/ for scaffolding and templates

When to Use This Skill

Trigger this meta-skill when you need to:

  • Create a new Skill from scratch from docs/specs/repos
  • Refactor an existing Skill (too long, unclear, inconsistent, misfires)
  • Design reliable activation (frontmatter + triggers + boundaries)
  • Extract a clean Quick Reference from large material
  • Split long content into navigable references/
  • Add a quality gate and a validator

Not For / Boundaries

This meta-skill is NOT:

  • A domain Skill by itself (it builds domain Skills)
  • A license to invent external facts (if the material does not prove it, say so and add a verification path)
  • A substitute for required inputs (if inputs are missing, ask 1-3 questions before proceeding)

Quick Reference

Deliverables (What You Must Produce)

Your output MUST include:

  1. A concrete directory layout (typically assets/skills/<skill-name>/)
  2. An actionable SKILL.md with decidable triggers, boundaries, and reproducible examples
  3. Long-form docs moved to references/ with a references/index.md
  4. A pre-delivery checklist (Quality Gate)

Built-in Tool (Mandatory): Skill Seekers (Vendored)

This repo vendors the Skill Seekers source code inside this meta-skill so you can generate a first-draft Skill from:

  • Documentation websites
  • GitHub repositories
  • PDFs

Bootstrap dependencies (once):

./assets/skills/skills-skills/scripts/skill-seekers-bootstrap.sh

Run Skill Seekers (from vendored source):

./assets/skills/skills-skills/scripts/skill-seekers.sh -- --version
./assets/skills/skills-skills/scripts/skill-seekers.sh -- scrape --config ./assets/skills/skills-skills/scripts/Skill_Seekers-development/configs/react.json
./assets/skills/skills-skills/scripts/skill-seekers.sh -- github --repo facebook/react --name react

Import the generated skill into this repo's canonical assets/skills/ tree:

./assets/skills/skills-skills/scripts/skill-seekers-import.sh react
./assets/skills/skills-skills/scripts/skill-seekers-import.sh react --force

Update the vendored source snapshot (optional, network required):

./assets/skills/skills-skills/scripts/skill-seekers-update.sh
./assets/skills/skills-skills/scripts/skill-seekers-update.sh --ref main

Recommended Layout (Minimal -> Full)

skill-name/
|-- SKILL.md              # Required: entrypoint with YAML frontmatter
|-- references/           # Optional: long-form docs/evidence/index
|   `-- index.md          # Recommended: navigation index
|-- scripts/              # Optional: helpers/automation
`-- assets/               # Optional: templates/configs/static assets

The truly minimal version is just SKILL.md (you can add references/ later).

YAML Frontmatter (Required)

---
name: skill-name
description: "What it does + when to use (activation triggers)."
---

Frontmatter rules:

  • name MUST match ^[a-z][a-z0-9-]*$ and SHOULD match the directory name
  • description MUST be decidable (not "helps with X") and include concrete trigger keywords

Minimal SKILL.md Skeleton (Copy/Paste)

---
name: my-skill
description: "[Domain] capability: includes [capability 1], [capability 2]. Use when [decidable triggers]."
---

# my-skill Skill

One sentence that states the boundary and the deliverable.

## When to Use This Skill

Trigger when any of these applies:
- [Trigger 1: concrete task/keyword]
- [Trigger 2]
- [Trigger 3]

## Not For / Boundaries

- What this skill will not do (prevents misfires and over-promising)
- Required inputs; ask 1-3 questions if missing

## Quick Reference

### Common Patterns

**Pattern 1:** one-line explanation

[command/snippet you can paste and run]


## Examples

### Example 1

- Input:
- Steps:
- Expected output / acceptance:

### Example 2

### Example 3

## References

- `references/index.md`: navigation
- `references/...`: long-form docs split by topic

## Maintenance

- Sources: docs/repos/specs (do not invent)
- Last updated: YYYY-MM-DD
- Known limits: what is explicitly out of scope

Authoring Rules (Non-negotiable)

  1. Quick Reference is for short, directly usable patterns

- Keep it <= 20 patterns when possible. - Anything that needs paragraphs of explanation goes to references/.

  1. Activation must be decidable

- Frontmatter description should say "what + when" with concrete keywords. - "When to Use" must list specific tasks/inputs/goals, not vague help text. - "Not For / Boundaries" is mandatory for reliability.

  1. No bluffing on external details

- If the material does not prove it, say so and include a verification path.

Workflow (Material -> Skill)

Do not skip steps:

  1. If your source material is a docs site / GitHub repo / PDF: generate a first draft with the vendored Skill Seekers tool, then import into assets/skills/<skill-name>/
  2. Scope: write MUST/SHOULD/NEVER (three sentences total is fine)
  3. Extract patterns: pick 10-20 high-frequency patterns (commands/snippets/flows)
  4. Add examples: >= 3 end-to-end examples (input -> steps -> acceptance)
  5. Define boundaries: what is out-of-scope + required inputs
  6. Split references: move long text into references/ + write references/index.md
  7. Apply the gate: run the checklist and the validator

Quality Gate (Pre-delivery Checklist)

Minimum checks (see references/quality-checklist.md for the full version):

  1. name matches ^[a-z][a-z0-9-]*$ and matches the directory name
  2. description states "what + when" with concrete trigger keywords
  3. Has "When to Use This Skill" with decidable triggers
  4. Has "Not For / Boundaries" to reduce misfires
  5. Quick Reference is <= 20 patterns and each is directly usable
  6. Has >= 3 reproducible examples
  7. Long content is in references/ and references/index.md is navigable
  8. Uncertain claims include a verification path (no bluffing)
  9. Reads like an operator's manual, not a documentation dump

Validate locally:

# From repo root (basic validation)
./assets/skills/skills-skills/scripts/validate-skill.sh assets/skills/<skill-name>

# From repo root (strict validation)
./assets/skills/skills-skills/scripts/validate-skill.sh assets/skills/<skill-name> --strict

# From assets/skills/skills-skills/ (basic validation)
./scripts/validate-skill.sh ../<skill-name>

# From assets/skills/skills-skills/ (strict validation)
./scripts/validate-skill.sh ../<skill-name> --strict

Tools & Templates

Generate a new Skill skeleton:

# From repo root (generate into ./assets/skills/)
./assets/skills/skills-skills/scripts/create-skill.sh my-skill --full --output assets/skills

# From skills-skills/ (generate into ../ i.e. ./assets/skills/)
./scripts/create-skill.sh my-skill --full --output ..

# Minimal skeleton
./assets/skills/skills-skills/scripts/create-skill.sh my-skill --minimal --output assets/skills

Templates:

  • assets/template-minimal.md
  • assets/template-complete.md

Examples

Example 1: Create a Skill from Docs

  • Input: an official doc/spec + 2-3 real code samples + common failure modes
  • Steps:

1. Run create-skill.sh to scaffold assets/skills/<skill-name>/ 2. Write frontmatter description as "what + when" 3. Extract 10-20 high-frequency patterns into Quick Reference 4. Add >= 3 end-to-end examples with acceptance criteria 5. Put long content into references/ and wire references/index.md 6. Run validate-skill.sh --strict and iterate

Example 2: Refactor a "Doc Dump" Skill

  • Input: an existing SKILL.md with long pasted documentation
  • Steps:

1. Identify which parts are patterns vs. long-form explanation 2. Move long-form text into references/ (split by topic) 3. Rewrite Quick Reference as short copy/paste patterns 4. Add or fix Examples until they are reproducible 5. Add "Not For / Boundaries" to reduce misfires

Example 3: Validate and Gate a Skill

  • Input: assets/skills/<skill-name>/
  • Steps:

1. Run validate-skill.sh (non-strict) to get warnings 2. Fix frontmatter/name mismatches and missing sections 3. Run validate-skill.sh --strict to enforce the spec 4. Run the scoring rubric in references/quality-checklist.md before shipping

References

Local docs:

  • references/index.md
  • references/skill-spec.md
  • references/quality-checklist.md
  • references/anti-patterns.md
  • references/README.md (upstream official reference)
  • references/skill-seekers.md (vendored tool integration + workflow)

External (official):

Maintenance

  • Sources: local spec files in assets/skills/skills-skills/references/ + upstream official docs in references/README.md
  • Last updated: 2025-12-14
  • Known limits: validate-skill.sh is heuristic; strict mode assumes the recommended section headings

平台分布

Codex

34.56%
按下载量换算59

Claude

29.27%
按下载量换算50

Cursor

19.79%
按下载量换算34

Gemini CLI

9.9%
按下载量换算17

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills