SKILL·A13304

Getting Started with Skills

obra
更新于 Today
35 次查看
751
169
751
在 GitHub 上查看
元aiautomation

关于

This skill establishes mandatory workflows for developers using Claude Code, requiring skills to be checked and read before any task. It emphasizes using the Read tool on full skill files and following brainstorming triggers before coding. Key features include mandatory skill usage, todo creation for tracking, and the find-skills command for discovery.

快速安装

Claude Code

推荐
主要方式
npx skills add obra/superpowers-skills -a claude-code
插件命令备选方式
/plugin add https://github.com/obra/superpowers-skills
Git 克隆备选方式
git clone https://github.com/obra/superpowers-skills.git ~/.claude/skills/Getting Started with Skills

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Getting Started with Skills

Critical Rules

  1. Use Read tool before announcing skill usage. The session-start hook does NOT read skills for you. Announcing without calling Read = lying.

  2. Follow mandatory workflows. Brainstorming before coding. Check for skills before ANY task.

  3. Create TodoWrite todos for checklists. Mental tracking = steps get skipped. Every time.

Mandatory Workflow: Before ANY Task

1. Check skills list at session start, or run find-skills [PATTERN] to filter.

2. If relevant skill exists, YOU MUST use it:

  • Use Read tool with full path: ${SUPERPOWERS_SKILLS_ROOT}/skills/category/skill-name/SKILL.md
  • Read ENTIRE file, not just frontmatter
  • Announce: "I've read [Skill Name] skill and I'm using it to [purpose]"
  • Follow it exactly

Don't rationalize:

  • "I remember this skill" - Skills evolve. Read the current version.
  • "Session-start showed it to me" - That was using-skills/SKILL.md only. Read the actual skill.
  • "This doesn't count as a task" - It counts. Find and read skills.

Why: Skills document proven techniques that save time and prevent mistakes. Not using available skills means repeating solved problems and making known errors.

If a skill for your task exists, you must use it or you will fail at your task.

Skills with Checklists

If a skill has a checklist, YOU MUST create TodoWrite todos for EACH item.

Don't:

  • Work through checklist mentally
  • Skip creating todos "to save time"
  • Batch multiple items into one todo
  • Mark complete without doing them

Why: Checklists without TodoWrite tracking = steps get skipped. Every time. The overhead of TodoWrite is tiny compared to the cost of missing steps.

Examples: skills/testing/test-driven-development/SKILL.md, skills/debugging/systematic-debugging/SKILL.md, skills/meta/writing-skills/SKILL.md

Announcing Skill Usage

After you've read a skill with Read tool, announce you're using it:

"I've read the [Skill Name] skill and I'm using it to [what you're doing]."

Examples:

  • "I've read the Brainstorming skill and I'm using it to refine your idea into a design."
  • "I've read the Test-Driven Development skill and I'm using it to implement this feature."
  • "I've read the Systematic Debugging skill and I'm using it to find the root cause."

Why: Transparency helps your human partner understand your process and catch errors early. It also confirms you actually read the skill.

How to Read a Skill

Every skill has the same structure:

  1. Frontmatter - when_to_use tells you if this skill matches your situation
  2. Overview - Core principle in 1-2 sentences
  3. Quick Reference - Scan for your specific pattern
  4. Implementation - Full details and examples
  5. Supporting files - Load only when implementing

Many skills contain rigid rules (TDD, debugging, verification). Follow them exactly. Don't adapt away the discipline.

Some skills are flexible patterns (architecture, naming). Adapt core principles to your context.

The skill itself tells you which type it is.

Instructions ≠ Permission to Skip Workflows

Your human partner's specific instructions describe WHAT to do, not HOW.

"Add X", "Fix Y" = the goal, NOT permission to skip brainstorming, TDD, or RED-GREEN-REFACTOR.

Red flags: "Instruction was specific" • "Seems simple" • "Workflow is overkill"

Why: Specific instructions mean clear requirements, which is when workflows matter MOST. Skipping process on "simple" tasks is how simple tasks become complex problems.

Summary

Starting any task:

  1. Run find-skills to check for relevant skills
  2. If relevant skill exists → Use Read tool with full path (includes /SKILL.md)
  3. Announce you're using it
  4. Follow what it says

Skill has checklist? TodoWrite for every item.

Finding a relevant skill = mandatory to read and use it. Not optional.

GitHub 仓库

obra/superpowers-skills
路径: skills/using-skills
0
FAQ

常见问题

什么是 Getting Started with Skills Skill?

Getting Started with Skills 是一个 Claude Skill,作者为 obra。Skill 将 Claude 按需加载的说明和资源打包,让 Claude 无需额外提示即可执行与 Getting Started with Skills 相关的任务。

如何安装 Getting Started with Skills?

使用本页的安装命令:将 Getting Started with Skills 作为插件添加到 Claude Code,或将其仓库克隆到 skills 目录,然后重启 Claude 以加载该 Skill。

Getting Started with Skills 属于哪个分类?

Getting Started with Skills 属于元分类。

Getting Started with Skills 可以免费使用吗?

可以。Getting Started with Skills 已收录在 AIMCP,可免费安装。

相关推荐技能

content-collections
元

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能
polymarket
元

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能
creating-opencode-plugins
元

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能
sglang
元

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能