Agent skill

Write Blog

by OpenClaudia in OpenClaudia/openclaudia-skills

Generate a full SEO-optimized blog post. An agent skill from OpenClaudia/openclaudia-skills.

MITAuto-check passedWriting & Content

Install Write Blog

skills CLI
$ npx skills add OpenClaudia/openclaudia-skills --skill write-blog -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenClaudia/openclaudia-skills write-blog --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/write-blog .claude/skills/write-blog && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
write-blog
GitHub stars
713
Token cost
~3.7k tokens
SKILL.md length
1,413 words
Files
1
Skills in repo
74
Repo updated
First seen
Licence
MIT

At a glance

Generate a full SEO-optimized blog post. An agent skill from OpenClaudia/openclaudia-skills.

  • Works in 7 steps: Research & Briefing → Create the Outline → Write the Content → …
  • The user says write a blog post
  • SKILL.md covers Blog Writing Process, Output Format and Important Notes
  • Calls curl and jq; reaches api.unsplash.com and unsplash.com; needs SEMRUSH_API_KEY

What it does

Write Blog is an agent skill from OpenClaudia/openclaudia-skills. Generate a full SEO-optimized blog post. Use when the user says "write a blog post", "blog article", "write about", "create content for", "SEO article", "blog content", "write a post about", or provides a keyword and asks for a written article.

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Blog and article writing. The repository describes itself as: 77 open-source marketing skills for Claude Code, Codex, and other AI coding agents. SEO, content, email, ads, analytics, and growth. The licence is MIT.

When your agent uses it

  • The user says write a blog post
  • Create content for
  • Write a post about
  • Provides a keyword and asks for a written article

Example prompts

  • “write a blog post”
  • “blog article”
  • “write about”
  • “/write-blog”

Requirements

  • A credential in SEMRUSH_API_KEY

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Research & Briefing
  2. Create the Outline
  3. Write the Content
  4. Optimize for Featured Snippets
  5. Add Supporting Elements
  6. FAQ Section
  7. Final Quality Check

What it can do on your machine

Read from SKILL.md and the folder at commit 28bf209. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.unsplash.com
    • unsplash.com
    • api.semrush.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • SEMRUSH_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Write Blog loads about 3.7k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 1,413 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OpenClaudia/openclaudia-skills at commit 28bf209, republished under its MIT licence (© OpenClaudia). 1,413 words, ~3,719 tokens.

Download SKILL.mdSave it as .claude/skills/write-blog/SKILL.md (or your agent's skills folder).
name
write-blog
description
Generate a full SEO-optimized blog post. Use when the user says "write a blog post", "blog article", "write about", "create content for", "SEO article", "blog content", "write a post about", or provides a keyword and asks for a written article.

Write Blog Post Skill

You are an expert SEO content writer. Create comprehensive, well-researched blog posts optimized for both search engines and readers. Follow the E-E-A-T framework (Experience, Expertise, Authoritativeness, Trustworthiness).

Blog Writing Process

Step 1: Research & Briefing

Before writing a single word, gather intelligence:

1A. Understand the keyword Ask or infer:

  • Target keyword: Primary keyword to rank for
  • Secondary keywords: 3-5 related terms to include naturally
  • Search intent: What does the searcher want? (Answer, comparison, tutorial, list)
  • Target audience: Who is reading this? (Beginner/intermediate/expert, role, industry)
  • Business goal: What should the reader do after? (Sign up, buy, share, learn)

1B. Get Keyword Data (if SemRush API available)

If SEMRUSH_API_KEY is set, pull real keyword metrics to inform the content strategy:

bash
# Get keyword data for the target keyword
curl -s "https://api.semrush.com/?type=phrase_all&key=${SEMRUSH_API_KEY}&phrase={keyword}&database=us&export_columns=Ph,Nq,Cp,Co,Nr"

The response is semicolon-delimited with columns:

  • Ph - Keyword phrase
  • Nq - Monthly search volume (use this to gauge content depth: higher volume = more comprehensive article)
  • Cp - CPC in dollars (high CPC signals strong commercial intent - emphasize CTAs and product mentions)
  • Co - Competition index 0-1 (high competition means you need stronger E-E-A-T signals)
  • Nr - Number of organic results (more results = more competitive SERP)

Use these insights to:

  • Calibrate word count: Keywords with volume >5,000 typically need 2,500+ word articles
  • Adjust commercial angle: CPC > $5 means readers have buying intent - include product recommendations, comparisons, or pricing info
  • Identify difficulty: Competition > 0.8 means you need more external links, original research, and expert quotes to compete

1C. Analyze the SERP (if tools available) Use WebSearch to check what currently ranks:

  • What content type dominates? (Listicle, how-to, guide, comparison)
  • What's the average word count of top 5?
  • What topics do all top results cover?
  • What's missing from existing content?

1D. Build the outline from SERP intelligence Your outline should cover everything the top results cover, plus unique sections they miss.

Step 2: Create the Outline

Build a detailed outline before writing. Every blog post follows this master structure:

markdown
# [H1: Title - includes primary keyword, compelling, 50-60 chars for title tag]

Meta Title: [50-60 characters, primary keyword front-loaded]
Meta Description: [150-160 characters, includes keyword, has CTA, creates curiosity]
URL Slug: [primary-keyword-short-descriptive]

## Introduction (100-150 words)
- Hook: Open with a surprising stat, question, or relatable problem
- Context: Why this topic matters RIGHT NOW
- Promise: What the reader will learn/gain
- Primary keyword appears in first 100 words

## [H2: First major section - includes secondary keyword]
### [H3: Subsection if needed]
- Key points to cover
- Data or examples to include

## [H2: Second major section]
### [H3: Subsection]
...

## [H2: Practical/Actionable Section]
(How-to steps, templates, checklists, frameworks)

## [H2: Expert Tips / Advanced Section]
(Differentiator content - what competitors don't cover)

## [H2: Common Mistakes / What to Avoid]
(Addresses "People Also Ask" questions)

## [H2: FAQ]
### [H3: Question 1?]
Answer (2-4 sentences, targets featured snippet)
### [H3: Question 2?]
...

## Conclusion (100-150 words)
- Summarize key takeaways (3-5 bullet points)
- Restate the main value delivered
- Clear CTA: what should the reader do next?

## Internal Links Plan
- Link TO: [3-5 related pages on the site]
- Link FROM: [Pages that should link to this post]
Step 3: Write the Content

Follow these writing rules strictly:

Title Tag Formula (50-60 characters)

Choose the best pattern for the intent:

IntentFormulaExample
How-to"How to {Action} ({Qualifier})""How to Start a Blog (Step-by-Step Guide)"
Listicle"{Number} {Adjective} {Topic} for {Year/Audience}""15 Best SEO Tools for Small Business (2025)"
Guide"{Topic}: The {Adjective} Guide for {Year}""Email Marketing: The Complete Guide for 2025"
Comparison"{A} vs {B}: {Differentiator}""Notion vs Obsidian: Which Is Better for Teams?"
Question"{Question}? {Promise}""Is SEO Dead? What the Data Actually Shows"

Title rules:

  • Primary keyword within first 30 characters
  • Add a power word: Ultimate, Complete, Proven, Essential, Definitive
  • Include year if the topic is time-sensitive
  • Use numbers for listicles (odd numbers outperform: 7, 9, 11, 13)
  • Never exceed 60 characters (Google truncates at ~580px)
Meta Description Formula (150-160 characters)
{What the article covers} + {Unique value prop} + {CTA or curiosity hook}

Examples:

  • "Learn how to start a blog in 2025 with our step-by-step guide. Covers hosting, design, content, and monetization. Free checklist included."
  • "We tested 15 SEO tools and ranked them by features, pricing, and ease of use. See which tool is best for your budget and goals."

Meta description rules:

  • Include primary keyword naturally
  • Include a CTA or curiosity element
  • Use active voice
  • Mention a specific deliverable (checklist, template, comparison, steps)
  • Stay between 150-160 characters
Writing Style Rules

Readability:

  • Paragraphs: 2-4 sentences max
  • Sentences: 15-20 words average
  • Use short sentences for emphasis. Like this.
  • Reading level: Grade 7-9 (Flesch-Kincaid)
  • Use "you" and "your" - write TO the reader
  • Active voice > passive voice (aim for 90%+ active)

Structure & Scannability:

  • H2 every 200-300 words
  • H3 for subsections within H2s
  • Bullet points for lists of 3+ items
  • Numbered lists for sequential steps
  • Bold key terms and takeaways
  • Pull quotes or callout boxes for key insights
  • Tables for comparisons (Google loves tables for featured snippets)

SEO Integration (natural, not forced):

  • Primary keyword in: H1, first 100 words, 1-2 H2s, conclusion, alt text
  • Primary keyword density: 0.5-1.5% (roughly every 200 words in a 2000-word post)
  • Secondary keywords: each appears 2-3 times throughout
  • LSI/related terms: sprinkle naturally throughout
  • Never keyword stuff - if it sounds unnatural, rewrite it

E-E-A-T Signals:

  • Experience: Include first-hand observations, "In my experience...", "When I tested..."
  • Expertise: Reference specific methodologies, use precise terminology, show deep knowledge
  • Authoritativeness: Cite authoritative sources (studies, official docs, industry leaders)
  • Trustworthiness: Acknowledge limitations, present balanced views, link to sources
Content Depth Targets
Article TypeTarget WordsSections (H2)ImagesInternal LinksExternal Links
How-to Guide2000-30006-105-105-83-5
Listicle2500-40001 per item + intro/conclusion1 per item5-103-5
Ultimate Guide3000-50008-158-158-125-8
Comparison1500-25005-83-53-52-4
Opinion/Thought1000-15004-62-33-52-3
News/Update800-12003-51-33-53-5

Target featured snippets with these patterns:

Paragraph snippet (definition/what is):

markdown
## What Is {Topic}?

{Topic} is {clear 40-60 word definition that directly answers the question}.
{Additional context in 1-2 more sentences}.

List snippet (how-to/best of):

markdown
## How to {Action}

1. **{Step 1 title}** - Brief description
2. **{Step 2 title}** - Brief description
3. **{Step 3 title}** - Brief description
...

Table snippet (comparison/data):

markdown
## {Comparison Topic}

| {Column 1} | {Column 2} | {Column 3} |
|------------|------------|------------|
| {Data} | {Data} | {Data} |
Show full SKILL.md (633 more words)Show less
Step 5: Add Supporting Elements

Image suggestions: For each major section, suggest an image:

markdown
[IMAGE: {Description of what the image should show}]
Alt text: "{Descriptive alt text with keyword where natural}"

Image types to suggest:

  • Hero image (featured image for social sharing)
  • Screenshots (for tutorials)
  • Comparison tables (as images for Pinterest)
  • Infographics (for key data points)
  • Process diagrams (for step-by-step content)
  • Charts/graphs (for data-driven claims)

Sourcing Featured Images from Unsplash (if UNSPLASH_CLIENT_ID available):

Use the Unsplash API to find high-quality, royalty-free featured images for the blog post:

bash
# Search Unsplash for a relevant featured image
curl -s "https://api.unsplash.com/search/photos?query={topic}&per_page=5&orientation=landscape" \
  -H "Authorization: Client-ID ${UNSPLASH_CLIENT_ID}"

Parsing the response:

The JSON response contains a results array. For each photo, extract:

bash
# Parse with jq to get image URLs, photographer info, and download links
curl -s "https://api.unsplash.com/search/photos?query={topic}&per_page=5&orientation=landscape" \
  -H "Authorization: Client-ID ${UNSPLASH_CLIENT_ID}" | \
  jq -r '.results[] | {
    id: .id,
    description: .description,
    image_url: .urls.regular,
    full_url: .urls.full,
    download_link: .links.download,
    photographer_name: .user.name,
    photographer_url: .user.links.html,
    unsplash_url: .links.html
  }'

Key fields from the response:

  • .urls.regular - Optimized image (1080px wide, good for blog featured images)
  • .urls.full - Full resolution image
  • .urls.small - Thumbnail (400px wide, good for social sharing previews)
  • .links.download - Trigger a download (Unsplash tracks this for photographer stats)
  • .user.name - Photographer's name (required for attribution)
  • .user.links.html - Photographer's Unsplash profile URL

Unsplash attribution requirement:

Unsplash requires attribution whenever you use a photo. Include this in the blog post:

markdown
Photo by [Photographer Name](https://unsplash.com/@username?utm_source=your_app&utm_medium=referral) on [Unsplash](https://unsplash.com/?utm_source=your_app&utm_medium=referral)

Place the attribution either:

  • In the image caption directly below the featured image
  • In an image credits section at the bottom of the post
  • In the alt text or title attribute of the image tag

Tip: Search with specific, descriptive queries rather than broad terms. For example, use "remote team video call" instead of "business" for better results. You can also filter by color, content_filter (low/high), and order_by (relevant/latest).

Internal link placement:

  • Contextual links within body paragraphs (most valuable)
  • "Related reading" callout boxes between sections
  • "Further reading" section at the end
  • Anchor text should be descriptive, not "click here"

External link rules:

  • Link to authoritative sources (studies, official docs, .edu, .gov)
  • Open external links in new tab
  • No-follow affiliate links and sponsored content
  • Cite statistics with linked sources
Step 6: FAQ Section

Every blog post should end with a FAQ section targeting "People Also Ask":

markdown
## Frequently Asked Questions

### {Question matching PAA or long-tail keyword}?

{Direct answer in 2-4 sentences. Front-load the answer.
Provide additional context after the direct answer.
This format optimizes for both featured snippets and FAQ rich results.}

### {Second question}?

{Answer}

FAQ rules:

  • 4-6 questions
  • Questions should use natural language (how, what, why, when, can, does)
  • Answer the question in the first sentence
  • Keep each answer under 100 words
  • Include schema markup (see schema-markup skill)
Step 7: Final Quality Check

Before delivering the post, verify:

SEO Checklist:

  • Title tag: 50-60 characters, keyword front-loaded
  • Meta description: 150-160 characters, includes keyword, has CTA
  • URL slug: Short, includes keyword, hyphenated
  • H1: One per page, includes primary keyword
  • H2s: Include secondary keywords where natural
  • Primary keyword in first 100 words
  • Keyword density: 0.5-1.5%
  • Internal links: 5+ contextual links
  • External links: 3+ authoritative sources
  • Images: Alt text on all, keyword in at least one
  • FAQ section with 4-6 questions
  • Word count meets target for content type
  • No duplicate content or thin sections

Readability Checklist:

  • Average paragraph: 2-4 sentences
  • Average sentence: under 20 words
  • Grade level: 7-9
  • Active voice: 90%+
  • Power words in subheadings
  • Bullet points or numbered lists every 300 words
  • Bold text highlights key points

E-E-A-T Checklist:

  • Author byline with credentials suggested
  • Sources cited and linked
  • First-hand experience or expertise demonstrated
  • Balanced perspective (pros and cons, not just hype)
  • Date published and "last updated" date included
  • Factual accuracy verified (no made-up statistics)

Output Format

Deliver the blog post in this format:

markdown
---
title: "{Meta title - 50-60 chars}"
description: "{Meta description - 150-160 chars}"
slug: "{url-slug}"
keywords: ["{primary}", "{secondary1}", "{secondary2}"]
date: "{YYYY-MM-DD}"
author: "{Author name}"
---

# {H1 Headline}

{Full article content with all formatting, links, and image placeholders}

After the article, provide:

  1. SEO metadata summary (title, description, slug, word count)
  2. Internal linking recommendations (which pages to link to/from)
  3. Schema markup (Article or BlogPosting JSON-LD)
  4. Social sharing (suggested OG title, description, and image concept)
  5. Content promotion ideas (2-3 distribution channels and angles)

Important Notes

  • Never fabricate statistics. If citing a number, include the source or note "[Source needed]".
  • Write for humans first, search engines second. If an SEO tactic makes the content worse for readers, skip it.
  • Every section must provide value. No filler paragraphs. If a section doesn't teach, convince, or entertain, cut it.
  • Match the user's brand voice if they specify one. Ask if not clear.
  • If the topic is YMYL (health, finance, legal), be extra careful with claims and heavily cite authoritative sources.

© OpenClaudia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/write-blog of OpenClaudia/openclaudia-skills.

Open the folder on GitHubat commit 28bf209

Compare with similar skills

Write Blog next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Write Blog compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Write Blog this skillOpenClaudia/openclaudia-skills713—~3.7kAutomated safety check: PassMIT
Khazix WeChat Article WriterKKKKhazix/khazix-skills21k1 repos~2.9kAutomated safety check: PassMIT
Figurevectorize-io/hindsight47k—~1.9kAutomated safety check: PassMIT
SepiaNanako0129/sepia3k—~3.6kAutomated safety check: PassMIT
Blog Post Draftingluongnv89/claude-howto42k—~2.1kAutomated safety check: PassMIT
Notion To Blogwasp-lang/wasp19k—~922Automated safety check: PassMIT

Similar skills

  • Khazix WeChat Article Writer

    KKKKhazix/khazix-skills

    Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.

    21k GitHub starsUsed in 1 repo~2.9k tokens
    Writing & ContentAuto-check passed
  • Figure

    vectorize-io/hindsight

    Draw an animated figure (boxes, arrows, moving data) as one self-contained SVG for a GitHub README, PR, issue or blog post.

    47k GitHub stars~1.9k tokensUpdated today
    Writing & ContentAuto-check passed
  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3k GitHub stars~3.6k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Blog Post Drafting

    luongnv89/claude-howto

    Guides drafting a blog post from an idea and optional source material: research, brainstorming, outlining and version-tracked drafts, with user approval at each step.

    42k GitHub stars~2.1k tokensUpdated 8 days ago
    Writing & ContentAuto-check passed
  • Notion To Blog

    wasp-lang/wasp

    Transfer a blog post from Notion to the Wasp blog. An agent skill from wasp-lang/wasp.

    19k GitHub stars~922 tokensUpdated today
    Writing & ContentAuto-check passed
  • Blog Post

    nteract/semiotic

    Author a new entry for the Semiotic blog. An agent skill from nteract/semiotic.

    2.7k GitHub stars~3.4k tokensUpdated today
    Writing & ContentAuto-check passed

More from OpenClaudia/openclaudia-skills

All 74 skills in this repo
  • Competitor Traffic Report

    OpenClaudia/openclaudia-skills

    Build an interactive competitive-traffic report for any company and its rivals — monthly visits (SimilarWeb), organic search traffic and Domain Rating (Ahrefs) — as one self-contained HTML page with…

    713 GitHub stars~1.2k tokensUpdated 21 days ago
    Auto-check passed
  • Geo Difficulty

    OpenClaudia/openclaudia-skills

    Score how hard a keyword is to rank for in the AI-search era — page-level URL Rating of real competitors (not just domain DR), Ahrefs keyword difficulty, and whether a given site already ranks or is…

    713 GitHub stars~694 tokensUpdated 21 days ago
    Auto-check passed
  • Gsc Portfolio Audit

    OpenClaudia/openclaudia-skills

    Audit EVERY Google Search Console property at once — rank all sites by clicks and impressions with period-over-period deltas, then diff keywords per site to surface what is newly ranking, rising…

    713 GitHub stars~1k tokensUpdated 21 days ago
    Auto-check passed
  • Similarweb Traffic

    OpenClaudia/openclaudia-skills

    Fetch website traffic estimates (monthly visits, traffic sources, top countries, keywords, engagement, ranks) for any domain from SimilarWeb.

    713 GitHub stars~882 tokensUpdated 21 days ago
    Auto-check passed
  • Ahrefs Python

    OpenClaudia/openclaudia-skills

    Manages Ahrefs API usage in Python using ahrefs-python library.

    713 GitHub stars~1.9k tokensUpdated 21 days ago
    Auto-check passed
  • Ab Test Setup

    OpenClaudia/openclaudia-skills

    Design, plan, and analyze A/B tests with statistical rigor. An agent skill from OpenClaudia/openclaudia-skills.

    713 GitHub stars~1.7k tokensUpdated 21 days ago
    Auto-check passed

Questions about Write Blog

What does Write Blog do?

Generate a full SEO-optimized blog post. An agent skill from OpenClaudia/openclaudia-skills. Write Blog is an agent skill from OpenClaudia/openclaudia-skills. Generate a full SEO-optimized blog post.

When should I use Write Blog?

Write Blog fits situations like: the user says write a blog post; create content for; write a post about; provides a keyword and asks for a written article.

How do I install Write Blog in Claude Code?

Run `npx skills add OpenClaudia/openclaudia-skills --skill write-blog -a claude-code`. Or copy the skill folder (skills/write-blog in OpenClaudia/openclaudia-skills) into .claude/skills/write-blog in your project. Claude Code loads it when a task matches its description.

How do I install Write Blog in Codex?

Run `npx skills add OpenClaudia/openclaudia-skills --skill write-blog -a codex`. Or copy the skill folder (skills/write-blog in OpenClaudia/openclaudia-skills) into .agents/skills/write-blog in your project. Codex loads it when a task matches its description.

Can I use Write Blog in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenClaudia/openclaudia-skills --skill write-blog -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/write-blog, .gemini/skills/write-blog, .github/skills/write-blog and .opencode/skills/write-blog in your project.

What does Write Blog need to run?

Going by SKILL.md and its folder, Write Blog needs the command-line tools its instructions call (curl and jq) and credentials named SEMRUSH_API_KEY. Our summary lists: A credential in SEMRUSH_API_KEY.

Does Write Blog access the network?

SKILL.md names 3 domains. In commands or code: api.unsplash.com, unsplash.com and api.semrush.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Write Blog safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Write Blog use?

Write Blog is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Write Blog use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Write Blog?

Skills that share tags, products or a category with Write Blog: Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars), Figure (vectorize-io/hindsight, 47k stars), Sepia (Nanako0129/sepia, 3k stars) and Blog Post Drafting (luongnv89/claude-howto, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Write Blog?

OpenClaudia (a GitHub organization) maintains it in OpenClaudia/openclaudia-skills, which has 713 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on September 18, 2026.

Source: OpenClaudia/openclaudia-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.