write-blog-post

$npx mdskill add techwolf-ai/ai-first-toolkit/write-blog-post

Write or develop a blog post with section structure and voice consistency.

  • Drafts or edits long-form blog content from ideas or outlines.
  • Depends on scripts to read published LinkedIn posts and blog posts.
  • Checks published content and style guidelines to avoid repetition.
  • Produces a complete blog post draft with varied openings and flow.

SKILL.md

.github/skills/write-blog-postView on GitHub ↗
---
name: write-blog-post
description: 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.
---

# 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`

More from techwolf-ai/ai-first-toolkit

SkillDescription
ai-firstifyAnalyze, 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.
brainstorm-linkedinGenerate 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-opinionGenerate 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.
build-mcpBuild an MCP server end to end, tailored to how it will be used. Use when asked to build an MCP, create an MCP server, wrap an API as a tool, make a tool for Claude, expose a service to an agent, build a Claude connector, or turn a service into MCP tools. Asks up front who the server is for (just me, my org, or public) and what it wraps, then walks through analyze, build, deploy, scale, and distribute with steps tailored to that answer. Builds on the example-skills:mcp-builder skill for implementation depth.
content-studioEntry 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.
customer-statusSynthesised view of account health and activity for managers overseeing customer-facing teams (Sales, CS, Professional Services, Presales). Scans project channels, email threads, and Notion pages to surface status, risks, and upcoming milestones, without requiring the manager to trawl through individual channels. Supports proactive account management.
goal-promptTurn a task, plan, or feature request into a ready-to-paste Claude Code /goal command — a single completion condition with a measurable end state, a demonstrable proof, and the constraints that must not drift. Use when the user says "give me a goal", "goal prompt", "make this a /goal", "turn this into a goal", or wants an autonomous long-running objective for Claude Code.
kb-answer|
kb-import|
kb-refresh|