About blog-writer
A blog-writing skill for creating posts about Lightfast capabilities and industry trends, aimed at developer content teams. It emphasizes verified claims, transparent limitations, and category-specific structure and voice.
Key features
- 01Verifies facts and product claims
- 02Matches style to post category
- 03Adds TL;DR and FAQ elements
- 04Follows required post metadata
- 05Includes code examples in engineering posts
Use cases
- 01Writing engineering deep dives
- 02Preparing product update posts
- 03Creating tutorials or research articles
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ lightfastai/ lightfast --skill blog-writerAfter installing, type/blog-writerin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
resources/aeo-requirements.mdchecklist.mdtemplates.mdresources/categories/company.mdproduct.mdtechnology.mdDetails
From the project READMEBlog Writer
Create clear, accurate blog posts that help developers understand Lightfast capabilities and industry trends.
Critical: Accuracy Over Marketing
Before writing anything:
-
Verify every claim:
- If you cite a number, confirm the source
- If you mention a feature, confirm it exists in production
- When uncertain, ask for clarification
-
Never oversell:
- Disclose limitations: "Currently supports X; Y coming in vZ"
- Be honest about beta status and rollout timelines
-
Match category voice:
- Engineering: Technical authority, data-driven
- Company: Visionary, category-defining
- Product: Problem-solver, benefit-oriented
- Tutorial: Step-by-step, practical
- Research: Data-driven, methodology-first
Writing Guidelines
- Concise & scannable: Match category word counts
- Lead with value: Start with what readers gain
- Be transparent: Mention beta status, limitations
- Active voice: "You can now..." not "Users are able to..."
- No emoji: Professional tone
- Include TL;DR: 20-300 chars for AI citation (in frontmatter
tldrfield) - FAQ section: 3-5 questions matching search queries (in frontmatter
faq[]) - Code examples: Required for Engineering posts
Workflow
- Detect category from input or ask if unclear
- Load category style from
resources/categories/{category}.md - Research topic using web-search-researcher agent
- Draft following category template and templates
- Add AEO elements per aeo-requirements
- Review with checklist
Quick Reference
Category Selection
| Category | Use When | Audience |
|---|---|---|
| Engineering | Technical deep-dives, architecture, research | Developers, engineers |
| Company | Funding, partnerships, events, hiring | Executives, investors |
| Product | Feature launches, updates, tutorials | Customers, prospects |
| Tutorial | Step-by-step how-tos, guides | Developers learning |
| Research | Data analysis, findings, benchmarks | Engineering leaders |
Do
- Include code examples (Engineering/Tutorial)
- Use "shift from/to" narratives (Company)
- Lead with pain point (Product)
- Link to 3-5 related docs
Don't
- Marketing buzzwords without substance
- Claims without verification
- Long paragraphs (keep sections scannable)
- Generic corporate speak
Output
Save drafts to: thoughts/blog/{YYYY-MM-DD-slug}.md
Required Frontmatter Fields
Every draft MUST include (maps to BlogPostSchema in apps/www/src/lib/content-schemas.ts):
title(core)description(150-160 chars — this is the meta description)keywords[](min 3 — first entry is primary keyword)ogTitle,ogDescription,ogImage(social/OG)authors[](structured array with name, url, twitterHandle)publishedAt,updatedAt(ISO datetimes)category(engineering | product | company | tutorial | research)readingTimeMinutes(integer)featured(boolean)tldr(20-300 chars)faq[](min 1 entry)_draft: true(traceability)
See resources/templates.md for complete frontmatter template.