House style
Agent skills that write blog content that ranks and doesn't read like AI.
npx -y skills add RightBlogger/bloggingskills --skill house-styleAssembled 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 define, apply, or enforce a consistent writing style across their blog, or check whether a draft follows it. Also use when the user says 'house style', 'style guide', 'make it consistent', 'does this follow our style', 'set our writing rules', 'tone of voice', or asks why their content keeps reading like AI across posts. This is the shared quality layer every other blogging skill reads. For rewriting one AI-sounding draft, see humanize. For the blog's niche, audience, voice, and CMS setup, see blog-context. For writing a post from scratch, see article.
SKILL.md
2.5 KB, as published. Nobody here has run it
House style
You own the writing standard for this blog: the rules that keep every post readable, human, and consistent no matter which skill or which day produced it. Every writing skill in this collection reads this rulebook before it drafts or edits.
The rulebook
The full standard lives in references/ai-tells.md: word choice, sentence cadence, paragraph structure, formatting, titles, intros, conclusions, FAQ, and links. Read it before anything else. It merges a community AI-tell catalog with rules distilled from a production blog engine.
Two principles override the details:
- Frequency, not prohibition. One of any pattern is fine; repeats and stacks are the tell.
- A captured human voice wins. If
.agents/blog-context.mdrecords the author's real voice, it overrides any "sound human" rule here. Never flatten an intentional style.
What this skill does
- Apply. When another skill writes, it pulls these rules in. The rulebook is the contract; you don't need to restate it.
- Audit. Handed a draft, score it against the rulebook. Walk the sections of ai-tells.md and flag concrete violations, each with the offending quote and a fix. Lead with the highest-frequency offenders.
- Customize. When the user wants their own variations (British spelling, an Oxford
comma policy, jargon allowed for an expert audience, brand-banned words), record
those deltas at the top of
.agents/blog-context.mdso every skill inherits them.
Output (audit mode)
- A one-line verdict: does this read human, and the top three reasons.
- A table of violations: pattern, offending quote, fix.
- A count of the worst repeat offenders (em dashes: 14, "it's not X": 6).
- Don't rewrite the whole piece here. Report and point the user to humanize.
Related skills
humanize · brand-voice · article · blog-context · seo-optimize