skills/blog-post/SKILL.md
Generates engaging long-form blog posts from source materials or a topic brief. Supports listicles, tutorials, how-to guides, 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 a tutorial", "draft a thought leadership piece", or "write a how-to guide". 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.
npx skillsauth add mblode/agent-skills blog-postInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
copywriting), slide decks (use presentation-creator), or technical reference docs and API pages (use docs-writing).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
Pick the format before writing a word; the format dictates the template in Step 4. If the request is ambiguous, ask one question rather than guessing.
| Format | Best for | Spine | |--------|----------|-------| | Listicle | Surprising takeaways from sources | Numbered insights, each with analysis | | Tutorial / how-to | Teaching a process step by step | Problem, steps, result | | Narrative | Personal experience or journey | Scene, tension, resolution | | Thought leadership | Industry opinion or commentary | Thesis, evidence, implications |
Also lock the angle in one sentence: what does the reader believe or do differently after reading? A post without an angle becomes a summary, the most common failure mode.
Read files, fetch URLs, or accept pasted text. Read each source end to end before outlining; skimming produces posts that miss the buried lede.
If the user gives a topic with no sources, research it first. Accept messy input (scattered notes, bullet dumps, half-formed observations). The mess is the input; structure is the output.
Write a section outline, one line of purpose per section, before drafting. If a section has no purpose beyond "more detail," cut it.
Load only the matching format block from references/format-templates.md. Do not load all four. Follow its structure, then write through.
Walk this list and fix any failing item before declaring the post done. A post that fails any check is not finished.
- [ ] Hook lands in the first 1-2 sentences
- [ ] Headline is specific, under 60 chars, and the body delivers on it
- [ ] Every paragraph is 2-4 sentences
- [ ] Each section adds analysis or insight, not just restated source
- [ ] Blockquotes total 2-4, no more
- [ ] Conclusion looks forward (question, CTA, or provocation), not a recap
- [ ] Voice is conversational throughout, no academic register
- [ ] Meta description present, 150-160 chars
- [ ] Markdown renders: headings nest, blockquotes/bold/code are well-formed
These cut against Claude's defaults, which trend toward neutral, hedged, summary prose:
| When | Run |
|------|-----|
| Audit the finished prose against documentation/style rules | docs-writing |
| Turn the post into a slide deck | presentation-creator |
| Sharpen marketing hooks, CTAs, or strip AI writing tells | copywriting |
| Deepen on-page SEO beyond the basics here | optimise-seo |
development
Designs and builds UI end to end, from visual direction (palettes, type scales, design tokens, layout systems, landing-page CRO strategy, brand kits) to Tailwind implementation with the ui.sh design guideline system, including multiple variants with an in-browser picker, semantic markup scaffolds from screenshots, retrofitting dark mode or responsive behavior, and componentizing or canonicalizing Tailwind code. Use when asked to "build a landing page", "create a dashboard", "make this look good", "make this look premium", "pick a visual style", "design the UI for", "show me 3 hero options", "improve conversions", "create a brand kit", "turn this screenshot into markup", "add dark mode", "make a dark version of this image", "make this responsive", "fix this on mobile", "componentize this page", "clean up the Tailwind", or any prompt that designs, creates, or refines UI code. For auditing existing UI use ui-audit; for motion use ui-animation; for landing page copy use copywriting.
development
Collaborative interrogation that produces an implementation plan before any code is written. Explores the codebase and relevant docs first, asks one question at a time with a concrete recommended answer, grills the rationale behind documented decisions, flags fuzzy terminology, and walks a decision tree until shared understanding is reached, then writes a plan file. First step of the shipping pipeline; it creates plans, plan-reviewer stress-tests them, pr-creator opens the PR. Use when asked to "create a plan", "help me think through this", "plan this feature", "I want to build X", "grill me", "grill with docs", "understand the docs", "unpack the decisions", "brainstorm a spec", "what should the plan be", "think this through with me", or before starting any non-trivial implementation.
development
--- name: pr-reviewer description: Reviews the current local diff or branch and returns a read-only, severity-tiered findings report. It never edits files. Four modes: standard bug and compliance review, structural quality, AI slop detection, and whole-codebase security audit. Use when asked to run /pr-reviewer, "review my changes", or "code review" before commit, push, or handoff. "Thermo-nuclear review", "structural review", "deep code quality audit", "harsh maintainability review", and "code
development
--- name: ux-audit description: Feature-level UX audit for React/Next.js code, diff-aware by default. Catches what Lighthouse, axe, ESLint, and Storybook miss: state-coverage gaps (missing loading/empty/error), form data loss on validation, double-submit, broken focus management, optimistic UI without rollback, stale async responses, skeleton-induced layout shift, and vague microcopy. 33 modern failure-mode rules plus 30 Laws of UX rules across 12 feature playbooks. Produces a 3-tier ship-readin