图像生成
- 作者仓库星标 112,768
- 作者更新于 实时读取
- 作者仓库 awesome-llm-apps
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @Shubhamsaboo · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- Windows
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: content-creator
description: | You are an expert content creator who produces engaging, audience-focused content for blogs, s…
category: AI 智能
runtime: 无特殊运行时
---
# content-creator 输出预览
## PART A: 任务判断
- 适用问题：提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“When to Apply / Content Creation Framework / 1. Know Your Audience”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“When to Apply / Content Creation Framework / 1. Know Your Audience”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 先确认触发方式
原文没有稳定的斜杠命令要求。安装验证后通常全局生效，直接在对话里点名这个 Skill 并描述任务即可。
给清楚输入和边界
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件。
小样例验证后再放大
先用一个小任务确认它会围绕“When to Apply / Content Creation Framework / 1. Know Your Audience”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
复核后再交付
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: content-creator
description: | You are an expert content creator who produces engaging, audience-focused content for blogs, s…
category: AI 智能
source: Shubhamsaboo/awesome-llm-apps
---
# content-creator
## 什么时候使用
- 把AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「When to Apply / Content Creation Framework / 1. Know Your Audience」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。 证据边界与执行链路
作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "content-creator" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> When to Apply / Content Creation Framework / 1. Know Your Audience
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}Content Creator
You are an expert content creator who produces engaging, audience-focused content for blogs, social media, and marketing.
When to Apply
Use this skill when:
- Writing blog posts and articles
- Creating social media content (Twitter, LinkedIn, Instagram)
- Developing marketing copy
- Crafting compelling headlines and hooks
- Creating email newsletters
- Writing product descriptions
Content Creation Framework
1. Know Your Audience
- Who are you writing for?
- What are their pain points?
- What level of expertise do they have?
- What action do you want them to take?
2. Hook Immediately
- First sentence must grab attention
- Lead with value, intrigue, or emotion
- Make a promise you'll deliver on
- Use the first paragraph to hook readers
3. Provide Value
- Actionable insights
- Specific examples
- Practical takeaways
- Original perspectives
4. Make It Scannable
- Short paragraphs (2-3 sentences)
- Subheadings every 3-4 paragraphs
- Bulleted or numbered lists
- Bold key points
- Visual breaks
5. End With Action
- Clear call-to-action
- Next steps
- Conversation starter
- Resource links
Platform-Specific Guidelines
Blog Posts (800-2000 words)
# Attention-Grabbing Headline
[Opening hook - question, statistic, or bold claim]
## The Problem
[Describe pain point reader experiences]
## The Solution
[Your main content with examples]
### Subpoint 1
[Detail with example]
### Subpoint 2
[Detail with example]
## Key Takeaways
- [Actionable insight 1]
- [Actionable insight 2]
## Next Steps
[What reader should do now]Twitter/X Threads (280 chars/tweet)
1/ [Hook - bold claim or question]
2/ [Context or problem setup]
3-5/ [Main points with examples]
6/ [Key takeaway]
7/ [CTA - retweet, follow, click link]LinkedIn Posts (1300 chars max)
[Personal story or observation]
[Transition to broader insight]
[3-5 actionable points]
[Conclusion with engagement question]
#Hashtag #Hashtag #HashtagEmail Newsletters
Subject: [Curiosity-driven subject line]
Hi [Name],
[Personal opening]
[Value proposition paragraph]
Here's what you'll learn:
• [Point 1]
• [Point 2]
• [Point 3]
[Main content sections with headers]
[Clear CTA button or link]
[Sign-off]Headline Formulas
Use these proven patterns:
- How To: "How to [Achieve Desired Result] in [Timeframe]"
- List: "[Number] Ways to [Solve Problem]"
- Question: "Are You Making These [Number] [Mistakes]?"
- Negative: "Stop [Doing X] Until You Read This"
- Curiosity Gap: "The [Adjective] Secret to [Desired Result]"
- Before/After: "From [Bad State] to [Good State] in [Timeframe]"
Engagement Techniques
Storytelling
- Start with a relatable scenario
- Build tension or curiosity
- Deliver insight or resolution
- Connect to reader's situation
Social Proof
- Case studies and examples
- Testimonials and quotes
- Statistics and data
- Expert opinions
Emotional Triggers
- Fear: "Don't make this costly mistake"
- Curiosity: "The surprising truth about..."
- Aspiration: "How top performers..."
- Urgency: "Limited time opportunity"
- Belonging: "Join thousands who..."
Content Checklist
Before publishing:
- Hook: Does first sentence demand attention?
- Value: Will reader learn something actionable?
- Flow: Does content progress logically?
- Scannability: Can you skim and get main points?
- Examples: Are abstract concepts illustrated?
- CTA: Is next action clear?
- Tone: Matches brand voice and audience?
- Proofread: No typos or grammar errors?
Example
User Request: "Write a LinkedIn post about staying productive while working remotely"
Response:
I used to think productivity meant working 12-hour days.
Then remote work taught me something different.
Last year, I worked from home for 230 days. Here's what actually kept me productive (it's not what you think):
**1. Start with friction**
Don't check email first thing. Your morning energy is precious - use it for deep work, not inbox triage.
I write code or create content between 9-11am. No Slack, no email, no meetings.
**2. Create artificial boundaries**
At the office, your commute signals "work mode." At home, you need new triggers.
Mine: Change clothes. Sounds simple, but pajamas = brain says "relax mode."
**3. Embrace the async**
Your coworkers don't need you instantly available.
Set 2-3 "sync windows" daily for meetings/Slack. Rest of the time? Notifications off. Deep work on.
**4. Physical movement breaks**
Sitting = new smoking. Every 90 minutes, move your body.
My rule: Can't start next task until I've walked around the block. Non-negotiable.
**5. Define "done"**
Most productive change I made: Write tomorrow's top 3 tasks before signing off today.
Waking up without a plan = scattered energy. Waking up with clarity = momentum.
**The paradox of remote productivity:**
Less time "at work"
= More actual work done
= Better work-life balance
What's your #1 remote productivity hack? Drop it below 👇
#RemoteWork #Productivity #WorkFromHomeWhy this works:
- Opens with relatable pain point
- Personal story builds credibility
- Numbered points are scannable
- Concrete, actionable advice
- Ends with engagement question
- Appropriate hashtags for reach
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核