The Agent Skills Directory
npx skills add https://smithery.ai/skills/CaptainCrouton89/output-styles-guide输出风格通过修改系统提示,调整 Claude Code 的行为,使其适用于软件工程之外的用例,从而实现专业化工作流,同时保留核心功能(文件 I/O、脚本执行、TODO 跟踪)。
输出风格是定制的系统提示,用于替换或补充 Claude Code 默认的软件工程焦点。它们:
.claude/settings.local.json)或用户级别(~/.claude/output-styles)持久化。标准的 Claude Code 行为,针对软件工程优化:简洁的输出、代码验证、高效的任务完成。
在任务之间添加 "见解" 部分,以解释实现选择和代码库模式。非常适合理解复杂代码或教学。
协作式、边做边学的模式。分享见解,并通过 TODO(human) 标记请求您对小的代码部分做出贡献。最适合技能培养或入职培训。
交互式菜单:
/output-style
# 或通过 /config 访问
直接命令:
/output-style explanatory
/output-style default
/output-style learning
更改在项目级别应用并保存到 .claude/settings.local.json。
/output-style:new 我想要一个输出风格,它 [描述您的用例]
Claude 将创建并保存一个模板;您可以对其进行完善。
在 ~/.claude/output-styles/<名称>.md(用户级别,跨项目共享)或 .claude/output-styles/<名称>.md(仅项目级别)创建一个 markdown 文件。
结构:
---
name: 我的自定义风格
description: 在 /output-style 菜单中显示的简短描述
---
# 自定义风格指令
您是一个交互式 CLI 工具。[您的指令放在这里...]
## 具体行为
[定义助手的行为方式...]
示例:研究助手风格
---
name: 研究助手
description: 专注于深度优先分析,包含引用和假设跟踪。
---
# 研究助手模式
您是一位专门从事深度调查和综合的研究伙伴。
## 具体行为
- 提出主张时请求来源并引用证据。
- 明确跟踪开放假设。
- 以项目符号格式总结发现,并附置信度。
- 标记不确定性并提出下一步调查建议。
| 用例 | 风格 | 优势 |
|---|---|---|
| 学习代码库 | 解释型 | 理解代码为何如此结构化的原因 |
| 工程师入职 | 学习型 | 积极参与,动手技能培养 |
| 研究/分析 | 自定义 | 深度优先调查,假设跟踪 |
| 技术写作 | 自定义 | 结构化大纲、示例、术语表生成 |
| 产品/用户体验工作 | 自定义 | 专注于人物角色、用户流程、旅程地图绘制 |
| 功能 | 目的 | 范围 |
|---|---|---|
| 输出风格 | 持久化的系统提示修改 | 影响所有主要代理交互 |
| CLAUDE.md | 在系统提示之后添加的项目级指令 | 补充默认行为;不替换它 |
| --append-system-prompt | 运行时系统提示添加 | 每次会话一次性追加 |
| 代理 | 使用自定义工具/模型执行特定任务 | 单一用途委托;不影响主循环 |
| 自定义斜杠命令 | 存储的用户提示(输入模板) | 重复请求的简写形式 |
关键区别: 风格 替换 核心系统指令;其他功能 添加 到它们之上。
.claude/settings.local.json,用户级风格用 ~/.claude/output-styles/。.claude/output-styles/)并提交到 Git。/output-style default 或从 .claude/settings.local.json 中删除。| 操作 | 命令 |
|---|---|
| 查看可用风格 | /output-style |
| 直接切换 | /output-style [风格名称] |
| 创建自定义风格 | /output-style:new [描述] |
| 打开配置 | /config |
| 访问设置 | .claude/settings.local.json(项目)或 ~/.claude/output-styles/(用户) |
每周安装次数
–
来源
首次出现
–
Output styles adapt Claude Code's behavior for use cases beyond software engineering by modifying the system prompt, enabling specialized workflows while retaining core capabilities (file I/O, script execution, TODO tracking).
Output styles are customized system prompts that replace or supplement Claude Code's default software engineering focus. They:
.claude/settings.local.json) or user level (~/.claude/output-styles).Standard Claude Code behavior optimized for software engineering: concise output, code verification, efficient task completion.
Adds "Insights" sections between tasks to explain implementation choices and codebase patterns. Ideal for understanding complex code or teaching.
Collaborative, learn-by-doing mode. Shares insights and requests your contribution on small code sections via TODO(human) markers. Best for skill-building or onboarding.
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
Interactive menu:
/output-style
# or access via /config
Direct command:
/output-style explanatory
/output-style default
/output-style learning
Changes apply at project level and save to .claude/settings.local.json.
/output-style:new I want an output style that [describes your use case]
Claude creates and saves a template; you refine it.
Create a markdown file at ~/.claude/output-styles/<name>.md (user-level, shared across projects) or .claude/output-styles/<name>.md (project-level only).
Structure:
---
name: My Custom Style
description: Brief description shown in /output-style menu
---
# Custom Style Instructions
You are an interactive CLI tool. [Your instructions here...]
## Specific Behaviors
[Define how the assistant behaves...]
Example: Research Assistant Style
---
name: Research Assistant
description: Focused, depth-first analysis with citations and hypothesis tracking.
---
# Research Assistant Mode
You are a research partner specializing in deep investigation and synthesis.
## Specific Behaviors
- Request sources and cite evidence when making claims.
- Track open hypotheses explicitly.
- Summarize findings in bullet-point format with confidence levels.
- Flag uncertainty and propose next investigation steps.
| Use Case | Style | Benefit |
|---|---|---|
| Learning codebase | Explanatory | Understand why code is structured this way |
| Onboarding engineers | Learning | Active participation, hands-on skill building |
| Research/analysis | Custom | Depth-first investigation, hypothesis tracking |
| Technical writing | Custom | Structured outlines, examples, glossary generation |
| Product/UX work | Custom | Personas, user flows, journey mapping focus |
| Feature | Purpose | Scope |
|---|---|---|
| Output Styles | Persistent system prompt modification | Affects all main agent interactions |
| CLAUDE.md | Project-level instructions added after system prompt | Supplements default behavior; doesn't replace it |
| --append-system-prompt | Runtime system prompt additions | One-time append per session |
| Agents | Task-specific execution with custom tools/models | Single-purpose delegation; doesn't affect main loop |
| Custom Slash Commands | Stored user prompts (input templates) | Shorthand for repeated requests |
Key distinction: Styles replace core system instructions; others add to them.
.claude/settings.local.json for project, ~/.claude/output-styles/ for user-level styles..claude/output-styles/) and commit to Git./output-style default or delete from .claude/settings.local.json.| Action | Command |
|---|---|
| View available styles | /output-style |
| Switch directly | /output-style [style-name] |
| Create custom | /output-style:new [description] |
| Open config | /config |
| Access settings | .claude/settings.local.json (project) or ~/.claude/output-styles/ (user) |
Weekly Installs
–
Source
First Seen
–
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
109,600 周安装