Blog context
Agent skills that write blog content that ranks and doesn't read like AI.
npx -y skills add RightBlogger/bloggingskills --skill blog-contextAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
When the user wants to set up or update the foundational context for their blog — niche, audience, topic pillars, CMS, and writing voice — so every other skill stops re-asking. Also use when the user says 'set up my blog', 'blog context', 'who is my audience', 'connect my site', 'my writing voice', or is starting with this collection for the first time. Creates .agents/blog-context.md, which every other blogging skill reads first. For a one-off keyword list, see keyword-research. For capturing a voice from writing samples, see brand-voice.
SKILL.md
2.5 KB, as published. Nobody here has run it
Blog context
You create and maintain the foundation file every other skill depends on:
.agents/blog-context.md. It records what this blog is, who it's for, and how it
sounds, so no skill ever has to re-interview the user.
Before anything
Check whether .agents/blog-context.md already exists. If it does, read it and ask
only what's missing or stale. Don't start over on top of existing context.
What to capture
Interview the user, or infer from their site if they give a URL, and write these sections:
- Blog. Name, URL, primary niche, and the goal (rank for X, drive signups, build authority).
- Audience. Who reads this, their level (beginner vs practitioner), the problems they arrive with, and the words they actually use for them.
- Pillars. The three to six core topic clusters this blog owns. New posts should ladder up to one of these.
- Voice. Tone (conversational, editorial, technical), reading level, point of view (first / second / third person), and any house-style deltas (spelling, allowed jargon, banned words). If the user has writing samples, summarize the voice in four to six concrete traits, and record them in the Voice section so every skill writes in them. For a deeper capture from real writing samples, run brand-voice.
- CMS and tools. WordPress, Ghost, or Webflow, plus which data sources exist (Search Console, analytics, a knowledge base).
- Constraints. Anything off-limits, required disclaimers, or competitor domains to avoid linking.
Output
Write .agents/blog-context.md with those sections, short and scannable.
references/template.md is a fillable starting point. Confirm
the path, summarize what you captured in three lines, and tell the user which skills
will now read it automatically.
Related skills
brand-voice · keyword-research · serp-analysis · house-style · article