メニュー
Create LinkedIn posts, bios, comments, and articles that sound authentically human. This skill should be used when the user wants to write LinkedIn content, says "write a post", "update my bio", "comment on this", or "draft an article".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Integrate better-auth into Next.js 16 apps. Use for email/password, social OAuth, magic links, passkeys, 2FA setup. Covers database adapters (Prisma/Drizzle), session management, and route protection.
Build AI chat applications with OpenAI ChatKit SDK. Use when creating chat UIs, multi-session systems, integrating AI agents (OpenAI, Gemini, Claude, Ollama), adding tools with MCP, widgets, or building conversational apps. Covers server setup, Store implementations, frontend integration (@openai/chatkit-react), function tools, MCP servers, multi-user sessions, and streaming responses.
Create production-grade frontend interfaces with systematic UI/UX design. Use when building web components, pages, or applications. Covers design systems, component states, accessibility (WCAG 2.2), responsive design, and industry conventions. Evaluates existing UI against best practices. Forces design thinking before implementation. Generates distinctive code avoiding generic AI aesthetics while following UX principles.
Draft professional replies to received messages across platforms (LinkedIn, Fiverr, Upwork, Interview, Email, WhatsApp). This skill should be used when the user pastes a received message and needs a reply draft, or says "reply to this", "draft a response", "help me respond to".
This skill conducts discovery conversations to understand user intent and agree on approach before taking action. It should be used when the user explicitly calls /interview, asks for recommendations, needs brainstorming, wants to clarify, or when the request could be misunderstood. Prevents building the wrong thing by uncovering WHY behind WHAT.
Write winning Upwork proposals that stand out from AI-generated spam. This skill should be used when the user pastes an Upwork job description and wants to bid, or says "write proposal", "apply for this job", "bid on this".
| name | linkedin-content |
| description | Create LinkedIn posts, bios, comments, and articles that sound authentically human. This skill should be used when the user wants to write LinkedIn content, says "write a post", "update my bio", "comment on this", or "draft an article". |
Generate LinkedIn content that sounds human, builds credibility, and drives engagement.
54% of LinkedIn long-form posts are now AI-generated. AI content gets 45% less engagement because readers detect it instinctively. This skill creates content that sounds like YOU, not like ChatGPT.
| Metric | Value |
|---|---|
| AI content penalty | 30% less reach, 55% less engagement |
| Optimal post frequency | 3-4 times per week |
| Golden hour | First 60-90 minutes critical |
| Hashtag limit | Max 5 (more = 35% reach drop) |
| Comments importance | #1 algorithm factor |
| Link penalty | Up to 70% if in main post |
User describes topic → Identify content type → Apply anti-AI rules → Generate + shorter version
| Type | Trigger | Length |
|---|---|---|
| Post | "write a post about..." | 50-150 words |
| Bio/Headline | "update my bio" | 1-4 lines |
| Comment | "comment on this" | 2-4 sentences |
| Article | "write an article" | 800-1500 words |
Always provide TWO versions:
## LinkedIn Post
[Primary version - ready to post]
---
## Shorter Version
[Condensed alternative]
---
## Hashtags (add at bottom)
#tag1 #tag2 #tag3
## Notes
- [Link placement suggestion]
- [Best time to post]
See references/anti-ai-patterns.md for full list.
These scream "AI-generated" - avoid completely:
delve, tapestry, realm, embark, unlock, unleash, harness,
leverage, cutting-edge, robust, vital, crucial, paramount,
in today's digital age, it's important to note, game changer,
landscape, testament, moreover, furthermore, additionally,
in the realm of, navigate, elevate, revolutionize, foster
| AI Pattern | Human Alternative |
|---|---|
| Perfect grammar throughout | Natural imperfections okay |
| Uniform sentence length | Vary short and long |
| "I'm excited to announce" | Direct statement |
| Generic statements | Specific examples |
| Repetitive structure | Varied formatting |
| Overly polished | Conversational |
Critical - this shows before "See more". Must stop the scroll.
Good hooks:
Bad hooks:
See references/algorithm-insights.md. Quick reference:
| Do | Don't |
|---|---|
| Post 3-4x per week | Post multiple times per day |
| Engage in first 60 mins | Post and disappear |
| Put links in comments | Put links in post body |
| Use 3-5 hashtags | Use 9+ hashtags |
| Native video (under 90s) | YouTube/external links |
| Ask questions | Engagement bait |
| Share real experiences | Generic advice |
[What you built - direct statement, no "excited to announce"]
[1-2 sentences on what it does/solves]
What I learned building this:
- [Specific insight 1]
- [Specific insight 2]
[Link in first comment]
Would love to hear your thoughts.
[What you achieved - specific]
[Why it matters to you personally]
The biggest takeaway: [One specific insight]
Next: [What you're doing with this]
[Question or bold statement about the tech]
[Simple explanation - like explaining to a friend]
Why this matters: [Practical application]
Have you tried this? What's your experience?
Headline format: [Role] | [Specialty] | [Differentiator]
Example for user:
AI Automation Engineer | n8n & Python Workflows | Building Agentic AI Systems
Bio structure:
Template:
[Agree/expand on specific point they made]
[Add your perspective or related experience]
[Optional: thoughtful question]
Name: Muhammad Umer Razzaq Niche: AI Automation & n8n Workflows Certified: PIAIC Agentic AI Engineer
Topics to post about:
Voice characteristics: