# LinkedIn Content Memory

This file is the reinforcement learning database for the LinkedIn Content Skill.
It is automatically read by every generator script to personalise your content.
Use `/feedback` to update it. Use `/show-memory` to review it.

---

## 🧠 Core Identity & Tone
- **Primary Niche:** (Update this — e.g. "AI & Technology", "Marketing", "SaaS")
- **Tone:** Professional, insightful, concise, and story-driven.
- **Voice:** First-person. Confident but humble. Write to one person, not an audience.
- **Formatting Preference:** Short paragraphs (1-2 sentences). Aggressive line breaks. Bullet points over dense paragraphs.
- **Emojis:** Use sparingly — 2-3 max per post, only where they genuinely add value.
- **CTA Style:** Specific and value-driven. Never "like and share" — always give a reason.

---

## 🎯 Successful Hooks
> Add hooks that received high engagement here.
- (Empty — use `/feedback` to add your first successful hook)

---

## 📈 Top Performing Formats
> Note which content formats get the best reactions.
- (Empty — use `/feedback` to log your best performing format)

---

## 🔑 High-Performing Topics
> Track which topics resonate most with your audience.
- (Empty — use `/feedback` to log topics that hit well)

---

## 🚫 What to Avoid
> Patterns, phrases, or formats that underperformed.
- Avoid cliché openers like "In today's fast-paced world..."
- Avoid posting without a clear CTA
- Avoid hashtag stuffing (max 5)

---

## 📝 Positive Feedback Log

### [2026-06-01 21:58] — test-01
- **What worked:** Great hook!
- **Tags:** `hook`