Skip to main content
ClaudeWave
Skill82 repo starsupdated today

write-blog-post

Write or develop a blog post. Use for blog content - writing, drafting, developing ideas into drafts, or editing. Longer-form than LinkedIn (800-1200 words) with section structure.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit /tmp/write-blog-post && cp -r /tmp/write-blog-post/plugins/content-studio/skills/write-blog-post ~/.claude/skills/write-blog-post
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Write Blog Post

You are helping write a blog post for the author.

## Before Writing (MANDATORY)

**You MUST complete these steps before writing ANY content:**

1. Run `./scripts/print-published.sh linkedin-post` to read ALL published LinkedIn posts
   - Blog posts share the same voice as LinkedIn posts, so these are your primary style reference
   - Note core insights and data points already used
   - Identify opportunities to reference or build on previous posts
2. Run `./scripts/print-published.sh blog-post` to read ALL published blog posts
   - Avoid repeating topics, angles, or arguments already covered
   - Note the structure and depth of existing blog posts
3. Read `guidelines/linkedin.md` for style rules (same voice applies to blog posts)
4. Read `references/professional-profile.md` for background

**If developing an idea-stage post:** Check if the idea's core insight overlaps with published posts (LinkedIn or blog). If so, either:
- Find a genuinely different angle
- Explicitly build on the previous piece
- Recommend against developing the idea

## Avoid Repetitive Patterns

When reading recent posts, actively note and vary:

**Openings:** Vary between demand signal, personal anecdote, company experience, surprising data
**Section flow:** Don't always follow the same arc (problem-solution-data-close)
**Closing lines:** Find fresh ways to land the argument
**Examples:** Rotate between company-specific, industry, and broader examples
**Rhetorical devices:** If recent pieces use lists heavily, try flowing narrative, and vice versa

The goal is a consistent voice with varied execution.

## Style Requirements

- **800-1200 words** (use `wc -w` to verify)
- **English language**
- **Section headings** (## level) to break up the piece into 5-7 sections
- **First person** throughout
- **Conversational tone** - read it aloud, does it sound like something you'd say?
- **Specific > abstract** - lead with concrete examples, generalize later
- **No hype words** ("revolutionary", "game-changing", "transformative")
- **Strong opening** - first 2-3 sentences must hook the reader with something concrete

## Structure

Blog posts are longer than LinkedIn posts and need more structure. A typical blog post has:

1. **Hook** (80-100 words) - Concrete opening that pulls the reader in
2. **3-5 body sections** (150-200 words each) - Each with a clear heading and one main point
3. **Close** (50-75 words) - Echo the opening or land the core argument

Each section should earn its place. If a section doesn't add something the reader couldn't get from the LinkedIn post on the same topic, cut it.

## Relationship to LinkedIn Posts

Blog posts often expand on ideas first introduced in LinkedIn posts. When this happens:
- Reference the LinkedIn post briefly, don't re-explain it
- Go deeper on the angle the LinkedIn post couldn't cover in 200 words
- Add the meta-story, the data, or the "why" behind the insight
- Blog posts should reward readers who already saw the LinkedIn post AND stand alone for those who didn't

## Process

1. If given a topic, develop it into a full draft
2. If given an existing idea file (search with `./scripts/search-posts.sh`), develop the content
3. Always check word count against 800-1200 target
4. Save to content/posts/blog-post/ with type: blog-post, stage: 02-drafts

## Validation

After saving the draft, run the word count checker:
```bash
scripts/check-word-count.sh <yaml-file>
```
Adjust the content if the word count is outside the 800-1200 target.

## Sub-Agent Review

Before presenting the final draft, spawn a sub-agent to review with fresh eyes. The reviewer should:
- Check voice consistency against `guidelines/linkedin.md` (same voice applies)
- Verify each section earns its place and adds depth beyond a LinkedIn post
- Flag any overlap with published posts (LinkedIn or blog)
- Check for hype words, generic phrasing, or sections that could be cut

Incorporate the reviewer's feedback before finalizing.

## Creating New Files

Get timestamp first:
```bash
date -u +"%Y%m%d-%H%M%S"  # For slug
date -u +"%Y-%m-%dT%H:%M:%S.000Z"  # For created/lastUpdated
```

File path: `content/posts/blog-post/{slug}-{slugified-title}.yaml`
session-searchSkill

Find context from past Claude Code (CLI) and Claude Cowork (desktop) sessions on this Mac. Use when the user wants to recall something they did before but can't find it , phrasings like "where did I work on X", "find that session where I…", "when did I last do Y", "pull up the conversation about Z", "that time I built/tried/discussed …". Searches by kind (code/cowork), time range, title, working directory, or free-text content across all transcripts.

task-profileSkill

Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often, how successfully where friction lives, then propose atomic skills that would reduce iteration. Use when the user asks to "analyse my Claude use", "build a task profile", "what tasks do I do with Claude", "where am I spending tokens", "what skills would help me", or mentions reviewing past sessions for patterns. Produces profile.csv (shareable), explorer.html (personal coaching view with AI-first principle comparison + token-spend chart), and skill-proposals.md.

token-doctorSkill

Personal diagnosis of where your Claude Code + Cowork spend goes. Reads local transcripts, prints your conversation length distribution, marathon share, cache rebuild costs, and per-project diagnosis (good projects and problem projects) right in the terminal. Then offers a deeper dive that fans out parallel Haiku subagents over your most expensive (and most efficient) sessions and writes a tight Markdown report. Use when the user asks "why is my Claude spend so high", "where am I burning tokens", "diagnose my Claude habits", "audit my Claude usage", or asks for a personal token-cost diagnosis.

ai-firstifySkill

Analyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review, audit, improve, 'ai-firstify', or start a new project. Performs deep analysis across 7 dimensions, actively restructures existing projects, or guides new project setup through discovery questions. Based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp.

analyze-performanceSkill

Analyze engagement patterns across published posts to identify what works. Use when asked to review performance, find successful patterns, or optimize future content.

brainstorm-linkedinSkill

Generate LinkedIn post ideas from external sources (files, URLs, research). Use when the user provides source material (PDFs, URLs, articles) to brainstorm topics. NOT for writing or developing drafts - use write-linkedin-post instead.

brainstorm-opinionSkill

Generate opinion piece ideas from recent LinkedIn posts (last 30 days). Use when asked to find opinion topics, brainstorm article ideas, or cross-pollinate content between LinkedIn and opinion pieces.

content-studioSkill

Entry point for the TechWolf content-studio plugin. Use to understand the workflow, pick the right content skill, or start setup for a new author/repository.