MCPInstall

blog-post

Generates engaging long-form blog posts from source materials or a topic brief. Supports listicles, editorial tutorials, how-to articles, narrative essays, and thought leadership. Handles research, outlining, drafting, on-page SEO, and polishing. Use when "write a blog post about this", "create a listicle", "turn this research into an article", "write an editorial tutorial", "draft a thought leadership piece", or "write a how-to article". For short product or marketing copy (headlines, CTAs, landing pages, onboarding strings) use copywriting; for slide decks use presentation-creator; for API references, READMEs, or how-to docs in a documentation site use docs-writing. This skill does on-page SEO for the post it writes; for sitemaps, metadata, redirects, or site-wide SEO use optimise-seo.

Installs
404
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/mblode/agent-skills --skill blog-post
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads blog-post automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Blog Post

  • IS: long-form editorial articles meant to be read top to bottom: listicles, editorial tutorials, how-to articles, narrative essays, thought leadership.
  • IS NOT: short marketing or product copy (use copywriting), slide decks (use presentation-creator), or technical documentation tutorials, how-to docs, reference docs, and API pages (use docs-writing).

Workflow

Blog post progress:
- [ ] Step 1: Lock format and angle
- [ ] Step 2: Read every source completely
- [ ] Step 3: Extract insights and outline
- [ ] Step 4: Draft from the matching template
- [ ] Step 5: On-page SEO and polish
- [ ] Step 6: Run the quality gate

Step 1: Lock format and angle

Pick the format first; it dictates the Step 4 template. If ambiguous, ask one question.

FormatBest forSpine
ListicleSurprising takeaways from sourcesNumbered insights, each with analysis
Tutorial / how-toTeaching a processProblem, steps, result
NarrativePersonal experience or journeyScene, tension, resolution
Thought leadershipIndustry opinion or commentaryThesis, evidence, implications

Lock the angle in one sentence: what does the reader believe or do differently after reading? Without one, the post is just a summary, the top failure mode.

Step 2: Read every source completely

Read every file, URL, or pasted text end to end before outlining; skimming misses the buried lede. Accept messy input (scattered notes, bullet dumps, half-formed observations): mess in, structure out.

No sources, only a topic? Research first, then build a research packet before outlining:

SourceURL/pathPublished/updatedCredibility reasonClaims usedConflicts/caveatsCurrent-sensitive?

Step 3: Extract insights and outline

  • Pull the most surprising, counter-intuitive, or high-impact takeaways; rank by reader value and lead with the strongest.
  • Mark 2 to 4 quotes worth blockquoting (only the strongest); paraphrase or discard the rest, or the post reads as a clip reel of other people's words.
  • Find the curiosity gap or concrete problem that anchors the intro.
  • Check for a narrative thread worth tracing: a shift from one understanding to another.

Outline one purpose line per section before drafting; cut any section whose only purpose is "more detail."

Step 4: Draft from the matching template

Load references/format-templates.md: fill the shared skeleton, applying your format's row for body-section labels, extra sections, and the close. Then write through.

Step 5: On-page SEO and polish

  • Title: under 60 chars, keyword near front, sentence case, no trailing period.
  • Meta description: 150 to 160 chars that sell the click, not a dry summary.
  • Keyword: in the title, first paragraph, and 2 to 4 times across the body. Past that it reads as spam and risks a search penalty, so place them naturally and stop.
  • Headers: descriptive H2/H3 that stand alone in a table of contents.
  • Internal links: suggest 2 to 3 if the user has related content; never invent URLs, which ship as dead links.

Step 6: Run the quality gate

Walk this list, then fill the Quality Report table below, which owns the numeric checks (title, meta, quote count, sources, links, facts). Fix every failing item before declaring done.

- [ ] Hook lands in the first 1-2 sentences
- [ ] Headline is specific and the body delivers on its promise
- [ ] No paragraph runs past 4 sentences, and lengths vary (uniform blocks read as generated)
- [ ] Each section adds analysis or insight, not just restated source
- [ ] Conclusion looks forward (question, CTA, or provocation), not a recap
- [ ] Voice is conversational throughout, no academic register
- [ ] Markdown renders: headings nest, blockquotes/bold/code are well-formed

End with a compact quality report:

## Quality Report

| Check | Result | Fix applied |
|---|---|---|
| Title length under 60 | pass/fail | |
| Meta description 150-160 | pass/fail | |
| Source count and credibility | pass/fail | |
| Quote count 2-4 | pass/fail | |
| Internal links invented? | pass/fail | |
| Current-sensitive facts checked | pass/fail/NA | |

Blog-specific voice

These cut against Claude's defaults (neutral, hedged, summary prose):

  • Write to one smart friend, not a committee; authenticity beats authority.
  • Bold the load-bearing phrase in a dense paragraph; readers skim before committing.
  • Show, don't tell: one concrete example with real names and numbers beats three vague claims.
  • Admit genuine uncertainty instead of bluffing; readers trust the seams.

Headline patterns

Pick one: number + insight ("7 Things [Source] Reveals About [Topic]"), surprising tension ("Why [Common Belief] Gets [Topic] Wrong"), how-to framing ("How to [Outcome] Without [Common Obstacle]"), or provocative question ("What If [Reframe of the Obvious]?").

Gotchas

  • A conclusion that restates the body teaches nothing; close with a forward look, CTA, or provocation.
  • Drafting from assumptions when sources exist yields confident wrong claims; read every source in Step 2 first.
  • Clickbait the body cannot pay off burns trust and raises bounce; promise only what the draft delivers.
  • Summarising each source in turn produces a digest with no argument; the angle from Step 1 decides what gets cut.

Skill handoffs

WhenRun
Turn the post into a slide deckpresentation-creator
Sharpen hooks, CTAs, or strip AI writing tellscopywriting
Deepen on-page SEO beyond the basicsoptimise-seo

docs-writing is not a handoff for a finished post: it puts editorial articles out of scope, and its sentence-case, requirements-language, and bold-for-UI-elements rules contradict the blog voice above. For a sentence-level clarity pass only, load its clarity-* rules and voice-no-jargon, nothing else from that rule set.

FAQ

What does the blog-post skill do?

Generates engaging long-form blog posts from source materials or a topic brief. Supports listicles, editorial tutorials, how-to articles, narrative essays, and thought leadership. Handles research, outlining, drafting, on-page SEO, and polishing. Use when "write a blog post about this", "create a listicle", "turn this research into an article", "write an editorial tutorial", "draft a thought leadership piece", or "write a how-to article". For short product or marketing copy (headlines, CTAs, landing pages, onboarding strings) use copywriting; for slide decks use presentation-creator; for API references, READMEs, or how-to docs in a documentation site use docs-writing. This skill does on-page SEO for the post it writes; for sitemaps, metadata, redirects, or site-wide SEO use optimise-seo.

How do I install blog-post?

Run npx skills add https://github.com/mblode/agent-skills --skill blog-post in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/blog-post/ (personal) or .claude/skills/blog-post/ (project).

Which AI agents can use blog-post?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is blog-post safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains blog-post?

It is published by mblode in mblode/agent-skills. It has 404 recorded installs.

More from mblode/agent-skills

View all →

ui-animation

mblode/agent-skills

Builds, reviews, and measures UI motion, including springs, gestures, scroll effects, curve fitting from recordings, and sparse interface sound. Use when asked to "add animation", "match this easing", "reverse engineer this motion", "add a click sound", or find animation opportunities.

Frontend & Design10.5K installs

multi-tenant-architecture

mblode/agent-skills

Designs tenant isolation, hostname routing, custom-domain lifecycle, and plan limits on Cloudflare or Vercel. Use when asked to "isolate tenant data", "support custom domains", "build a white-label platform", or assess PSL registration. For general module structure use codebase-architecture; for SEO content use seo.

ui-design

mblode/agent-skills

Designs and builds React/Next/Tailwind UI, audits visual and interaction defects, and stress-tests components with worst-case data. Use when asked to "build a landing page", "extract our design system", "add dark mode", "make this responsive", "remove UI slop", "audit this component", "stress-test this component", "break this UI", or "show me the worst case".

Frontend & Design1.4K installs

typography-audit

mblode/agent-skills

Audits font loading, type scales, measure, spacing, OpenType, and rendered punctuation with 78 scoped rules. Use when asked to "audit typography", "fix the fonts", or "review my type system". For a new visual direction use ui-design Direction; for general UI defects use ui-design Audit.

agent-skills-creator

mblode/agent-skills

Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions. Use when asked to "write a skill", "update all skills", "audit my SKILL.md", "remove redundant instructions", or fix skill triggering.

AI & Agents965 installs

docs-writing

mblode/agent-skills

Writes and audits technical docs with Diataxis type gating, runnable examples, and 51 documentation rules. Use when asked to "review my docs", "write an API reference", or improve a documentation page. For a whole README use readme-creator; for agent instructions use agents-md.

Docs & Writing948 installs

Popular docs & writing skills

View category →

grill-with-docs

mattpocock/skills

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Docs & Writing1.2M installs

lark-markdown

open.feishu.cn

飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。

Docs & Writing778.7K installs

writing-beats

mattpocock/skills

Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

Docs & Writing490.7K installs

writing-shape

mattpocock/skills

Writing, exploit: shape raw material into an article, paragraph by paragraph.

Docs & Writing490.2K installs

writing-fragments

mattpocock/skills

Writing, explore: mine raw fragments, no structure yet.

Docs & Writing489.6K installs

writing-for-agents

mattpocock/skills

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Docs & Writing479.3K installs