Founder Content

SKILL.md

---
name: founder-content
description: Complete content creation and multiplication system for solo founders and indie hackers. Use for any content task including writing social posts, repurposing content, creating threads, build-in-public updates, or content planning. Triggers on "write a post", "create content", "repurpose this", "thread", "build in public", "ship update", "content calendar", "turn this into posts", or any content creation request.
homepage: https://canlah.ai
metadata: {"category": "content-creation", "platforms": ["twitter-x", "linkedin", "xiaohongshu"], "features": ["build-in-public", "repurposing", "multi-platform", "voice-guide"]}
---

# Founder Content System

Everything for creating and multiplying content as a solo founder or indie hacker.

---

## Master Content Creation Workflow (Must Follow)

**Core Principle: Research → Extract → Adapt → Write**

Every piece of content must go through this workflow:

### Step 1: Research Hot Content (REQUIRED)

Before writing ANY content, research what is working:

```
1. Search for viral/high-engagement posts on target platform
2. Find 3-5 top-performing posts on similar topic
3. Note: hook structure, format, engagement type, tone
4. Identify what makes them work (specifics, emotion, contrarian angle)
```

**Search patterns:**
- `[platform] [topic] viral`
- `site:[platform].com [topic] lessons learned`
- `[topic] founder thread high engagement`

### Step 2: Extract Winning Patterns

| What to Extract | Why |
|-----------------|-----|
| **Hook formula** | First line determines if people read |
| **Number usage** | Specifics add credibility ($400 → $180) |
| **Emotion triggers** | What makes people react (cringe, saved, wasted) |
| **Story arc** | How tension and payoff are structured |
| **CTA design** | What drives comments vs likes |

### Step 3: Adapt with Founder Voice

**Brand Voice Principles:**
- 真实 (authentic) — real stories, not theory
- 硬 (sharp) — specific numbers, direct claims
- 带点自嘲 (self-deprecating) — own failures openly
- 不鸡汤 (no fluff) — substance over motivation

**Adaptation Rules:**
1. Keep the winning hook structure
2. Replace content with real stories from the user
3. Add specific numbers (e.g. $3,000 wasted, saved $1,000+)
4. Include genuine emotion (still cringe, learned the hard way)
5. Avoid: vague claims, motivational fluff, humblebrags

### Step 4: Platform-Specific Polish

| Platform | Key Adaptation |
|----------|---------------|
| **Twitter/X** | Punchy, <280 chars, threads for depth |
| **LinkedIn** | Longer, professional vulnerability, spaced lines |
| **小红书** | 口语化, 情绪词 (亏麻了/稳了), search-optimized titles |

---

## Quick Reference

| Task | Section |
|------|---------|
| Write posts from scratch | [Build-in-Public Workflow](#build-in-public-workflow) |
| Multiply existing content | [Repurposing Framework](#repurposing-framework) |
| Thread formula | [Thread Formula](#thread-formula) |
| Voice rules | [Voice Rules](#voice-rules) |
| Platform defaults | [Platform Defaults](#platform-defaults) |

---

## Build-in-Public Workflow

### Step 1: Gather Context

**From version control (auto mode):**
- Recent commits since last post
- PR titles and descriptions
- Release notes if tagged

**From user input (manual mode):**
- What shipped (feature/fix/improvement)
- Who it helps
- Why now
- One metric (optional)
- One lesson learned

### Step 2: Extract the Story

Every post answers 5 questions:
1. **What changed?** (the ship)
2. **Who benefits?** (the user)
3. **Why it matters now?** (the context)
4. **One proof** (metric, example, before/after)
5. **One takeaway** (lesson or insight)

### Step 3: Render for Each Platform

**Twitter/X:** Under 280 chars, concise, slightly spicy, one insight + one proof

**LinkedIn:** 8-20 lines with spacing, narrative + framework + takeaway

**小红书:** Chinese-first, structure: 背景→步骤→结果→踩坑→总结

### Step 4: Quality Check

- [ ] No identical cross-posts
- [ ] Each post has a takeaway
- [ ] No banned patterns (see Voice Rules below)
- [ ] 小红书 passes sensitivity check
- [ ] Metrics/proof included where possible

---

## Repurposing Framework

**Core Principle:** One Excellent Piece → 7-10 Platform-Native Derivatives

### Step 1: Evaluate Source

**High-Value (prioritize):** Evergreen topics, top performers, content with data/frameworks, long-form (>1000 words)

**Skip:** Trend-based, low performers, thin content

### Step 2: Extract Atomic Units

| Element | What to Extract |
|---------|----------------|
| Hook | Opening line, attention-grabber |
| Stats | Numbers, percentages, metrics |
| Frameworks | Step processes, models |
| Quotes | Memorable phrases |
| Stories | Anecdotes, case studies |
| Takeaways | Key lessons, actionable tips |

### Step 3: Apply STEPPS (from Contagious)

Every derivative needs at least one:
1. **Social Currency** — Makes sharer look smart
2. **Triggers** — Connected to daily habits
3. **Emotion** — Evokes awe, surprise, anger
4. **Public** — Visible behavior
5. **Practical Value** — Useful, saves time/money
6. **Stories** — Narrative that carries message

### Step 4: Make It Stick (SUCCESs)

- **Simple** — One core idea
- **Unexpected** — Break patterns
- **Concrete** — Specific details
- **Credible** — Proof points
- **Emotional** — Care about individual
- **Stories** — People remember stories

### Step 5: Schedule Distribution

```
Day 0:    Original published
Day 1-2:  Tease/announcement
Day 3-7:  First wave derivatives
Week 2-3: Second wave
Week 4+:  Evergreen rotation
```

---

## Content Pillars

Suggested pillar mix for technical founders:

1. **Technical Build** — AI, tools, architecture decisions, tech comparisons
2. **Building in Public** — Process over results, real learnings, metrics
3. **Cross-Cultural Founder** — Unique perspective from background/geography
4. **Systems Thinking** — Workflows, optimization, productivity

**Weekly mix:** 2-3 posts from pillars 1-2, 1 post from pillars 3-4

---

## Voice Rules

**Always:**
- Include one takeaway per post
- Adapt content per platform
- Use metrics when available
- Keep 小红书 titles search-optimized

**Never:**
- Motivational fluff ("believe in yourself")
- Humblebragging / name-dropping
- Vague claims ("game-changing", "revolutionary")
- Thought-leader cringe
- Dunking on competitors by name

**Voice Summary:**
- 真实 (authentic, not performative)
- 硬 (direct, earned confidence)
- 带点自嘲 (self-deprecating humor)
- 细节感强 (specific details)
- 不鸡汤 (no inspirational soup)

---

## Platform Defaults

| Platform | Language | Cadence | Format |
|----------|----------|---------|--------|
| Twitter/X | English | 3-5/week | <280 chars, threads rare |
| LinkedIn | English | 1-2/week | 8-20 lines, spaced |
| 小红书 | Chinese primary | 2/week | 干货 + 踩坑 mix |

---

## Thread Formula

```
Tweet 1 (Hook): Surprising stat or contrarian take
Tweet 2-5:      One key point per tweet with proof
Tweet 6:        Common mistake / "what most get wrong"
Tweet 7:        The solution/framework
Tweet 8:        CTA + callback to original
```

Write **10-15 versions of hook** before publishing.

---

## Example Transformation

**Input (commit message):**
```
feat: connect database MCP to content scheduler
- Added automatic content storage
- Triggers on push
- Posts to 3 platforms
```

**Output:**

**Twitter/X:**
```
Just wired up Claude → database → auto-posting pipeline.
Push to repo now triggers content across 3 platforms.
The surprising part: 80% of the work was tone adaptation, not infra.
```

**LinkedIn:**
```
Shipped: automated "build in public" pipeline

What it does: commits → AI-adapted posts → 3 platforms

What I learned: The hard part isn't automation—it's maintaining authentic voice at scale.

Next: adding human-in-the-loop approval.
```

**小红书:**
```
标题：用 Claude + 数据库搭了个自动发帖系统

背景：每次提交都想分享，但手动发三个平台太累

做法：Claude 读 commit → 生成三版本 → 数据库存储 → 自动发

踩坑：以为难点是技术，其实是语气适配

总结：自动化不是复制粘贴，是让机器学会"变脸"
```

---

## Input/Output Examples

### Example 1: Build-in-Public Update

**User Input:**
> "We just shipped a feature that lets users generate brand-consistent ad creative in one click."

**Expected Output:**

**Twitter/X:**
```
Shipped: One-click brand-consistent ad creative.

Before: 3 rounds of "make it more on-brand" feedback.
After: 90% first-pass approval rate.

The hard part wasn't the AI. It was teaching it what "on-brand" actually means.
```

**LinkedIn:**
```
We just shipped one-click brand-consistent ad creative.

Here's what changed:

Before:
• Designer creates ad
• Brand team reviews
• "Can you make it more on-brand?"
• 3 rounds of revision
• Finally approved

After:
• AI generates with brand memory
• 90% first-pass approval
• Designer focuses on strategy, not iteration

The insight: "On-brand" isn't subjective. It's computable.

We spent 6 months building the math behind brand consistency. Now it takes one click.

What's the most frustrating feedback loop in your creative process?
```

### Example 2: Content Repurposing

**User Input:**
> "Turn this blog post into social content: [paste 1000-word article]"

**Response Pattern:**
1. Extract atomic units: hooks, stats, frameworks, quotes, stories, takeaways
2. Apply STEPPS framework to select the most shareable elements
3. Generate platform-native content for each platform

**Example Output Structure:**
```
## Extracted Atomic Units:
- Hook: [most contrarian/surprising claim]
- Stat: [most specific number]
- Framework: [step-by-step model]
- Quote: [most memorable phrase]
- Takeaway: [core lesson]

## Derivatives:

**Twitter Thread (7 tweets):**
1/ [Hook tweet]
2/ [Supporting data]
[continues...]

**LinkedIn Post:**
[Full expanded version]

**小红书:**
标题：[search-optimized Chinese title]
[Full Chinese adaptation]

## Distribution Schedule:
- Day 1: Twitter thread (9 AM local)
- Day 2: LinkedIn (8 AM local)
- Day 3: 小红书 (8 PM local)
```

### Example 3: Cross-Platform Adaptation

**User Input:**
> "This tweet performed well — adapt it for LinkedIn and 小红书."

**Expected Output:**
```
## Original Tweet Analysis:
- Hook type: Contrarian ("Everyone thinks X, but Y")
- Key element: Specific number ($3,000 wasted)
- Engagement driver: Relatable failure story

## LinkedIn Version:
[Expanded with more context, spaced lines, professional framing, ends with question]

## 小红书 Version:
[Chinese adaptation with 口语化 tone, 情绪词, structured as 背景→经过→结果→教训]

## Adaptation Notes:
- LinkedIn: Added "Here's what I learned" framework
- 小红书: Localized dollar amounts to local currency context
- Both: Kept the core contrarian insight
```

---

## Author

**[Canlah AI](https://canlah.ai)** — Run performance marketing without breaking your brand.

- GitHub: [github.com/PHY041](https://github.com/PHY041)
- All Skills: [clawhub.ai/PHY041](https://clawhub.ai/PHY041)