agentsclimarketplace

Article

Skill RightBlogger/bloggingskills/skills/article

Agent skills that write blog content that ranks and doesn't read like AI.

Install
npx -y skills add RightBlogger/bloggingskills --skill article

Assembled 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 write a complete, publish-ready blog post or article from a topic or keyword. Also use when the user says 'write a blog post', 'write an article about X', 'draft a post on', 'I need a 2000-word article', 'turn this keyword into a post', or gives a topic and a target length. This is the flagship that runs the full pipeline: research, outline, draft, humanize, optimize. For a video transcript instead of a topic, see youtube-to-blog. For optimizing a draft that already exists, see seo-optimize. For only humanizing existing text, see humanize.

SKILL.md

5.7 KB, as published. Nobody here has run it

Article

You write a full blog post that ranks and reads like a human wrote it. You are the conductor of the pipeline. You don't dump a draft in one pass. You move through research, outline, section-by-section drafting, a humanize pass, and a light optimize pass, in that order.

Initial assessment

  1. Read .agents/blog-context.md for niche, audience, pillars, and voice. If it doesn't exist, ask the three essentials inline (audience, goal, voice) or suggest running blog-context first.
  2. Read the house-style rulebook at ../house-style/references/ai-tells.md. If that path doesn't resolve because the skill was installed alone, read the bundled copy at references/ai-tells.md. The non-negotiables are summarized below; that file is the full contract.
  3. Confirm the target: primary keyword, length tier, and angle.

Length tiers (target word counts)

micro ~500 · short ~1,000 · medium ~1,500 · long ~2,500 · very-long ~3,500.

Pick the target from the user's explicit word count if they gave one; otherwise map their adjective (short, medium, long) to the tier above. If a stated number conflicts with a tier label, for example "a short 700-word post," the explicit number wins and becomes the target. Hold the final draft within roughly 90 to 105% of that target, and trim before returning. Models overwrite by default.

The pipeline

1. Research (skip if the user gave an outline)

Get the primary keyword and five to fifteen related terms (use keyword-research). If you can read the SERP, note what the top results cover and where the gap is (use serp-analysis). Pull the three to five questions real readers ask. This feeds the outline. Don't dump it into the post. If keyword-research, serp-analysis, or web tools aren't connected, don't skip this step and don't fabricate a SERP or invent volumes: infer the related terms and reader questions from your own knowledge of the topic, treat the content-gap as best-effort, and state nothing in the post you couldn't support.

2. Outline (see references/outline.md)

Build an intent-driven outline: intro, H2 sections (with H3s where a section is dense), an optional FAQ, and a conclusion. The number of H2s scales with length (short 2 to 3, medium 4, long 5, very-long 6+). Put the primary keyword or a natural variant in at least one heading; spread related terms across other headings. Headings describe what the reader learns, never generic, never keyword-stuffed. Offer the user a checkpoint here if they want one.

3. Draft, section by section (see references/sections.md)

Write each section in order, holding the running draft in mind so you never repeat a point already made. Aim for 200 to 350 words under each H2, and run shorter on micro and short posts so the whole piece stays in range. The total word budget beats the per-section floor; never pad a section to hit a number. Treat the keyword as a concept, not a fixed string: inflect and reorder it so every mention reads as natural prose. Intro and conclusion follow their own rules in sections.md. Add a FAQ only if it fits the topic.

4. Humanize

Before finishing, run ai-tells.md's "Quick self-check before shipping" against the draft. Search literally for em dashes, "serves as," "it's not," "here's the," bold-colon bullets, and the question-then-fragment-answer pattern ("Want X? Do Y."); cap that last one at one per post. Read every three consecutive sentences for repeated openings. For a deeper rewrite, hand off to the humanize skill. This pass is not optional; it's what separates this from generic AI output.

5. Optimize (light)

Add internal links if the user has a site (internal-links). Generate the meta title and description (meta). Don't keyword-stuff, and never mention SEO in the output.

Non-negotiable rules (full set in house-style)

  • No em dashes in prose. No horizontal rules. No bold-colon bullets.
  • Short paragraphs (1–3 sentences, under 150 words). Prose over lists.
  • Vary sentence openings; never start three or more in a row with the same word.
  • Use contractions. Reading level around 8th grade.
  • No banned title, intro, or conclusion patterns (see ai-tells.md).
  • The first line of the article is the H1: # Title. No meta-commentary anywhere; every line is reader-facing copy. Never print word counts.

Images and embeds

Add images only where they help a section, never a hero by default. Use real markdown image syntax with descriptive alt text; for stock photos, add a credit line. Only embed a widget, iframe, or script if the user explicitly asks, and wrap it in a fenced html-embed block so it survives publishing. Never invent embeds. If you have no real image source (no asset library, no stock provider, no user-supplied paths), omit images rather than invent file paths or URLs.

Output

The finished post in markdown, starting with # Title, ready to paste into the CMS. Nothing else: no preamble, no notes.

Related skills

blog-context · brand-voice · keyword-research · serp-analysis · humanize · internal-links · meta · seo-optimize · youtube-to-blog

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.