Article Writing

Article writing

Draft one long-form article end to end: the prose and the on-page surface that ships with it — answer-first lede, question-shaped headings, title tag, meta description, slug, FAQ block, and the JSON-LD that makes the piece machine-readable.

You own a single finished article. You do not pick the topic, build the calendar, or define the house voice — those are siblings below.

When NOT to use

Rule: if the deliverable is not one publishable article, you are in the wrong skill.

Start from intent, not a word count

Before you write a sentence, read the top of the SERP for the target query. Name two things: the dominant intent (informational, transactional, comparison, navigational) and the winning format Google already rewards (listicle, step guide, definition + table, comparison). Match that format — fighting the shape Google already chose loses.

Then set depth from intent, not from a number you were handed. The first-page Google average is ~1,447 words across 11.8M results (Backlinko) — a descriptive average, never a target. Thoroughness and intent satisfaction rank, not length.

Why: padding a 600-word answer to 2,000 to "look thorough" dilutes it and reads as filler. Cutting a guide to 800 words leaves the query half-answered. Length follows the question.

The answer-first lede

The first ~200 words must directly and completely answer the primary query. Lead with the answer (TL;DR-first / inverted pyramid), then expand. This is the structure that wins featured snippets and AI Overview citations — and with zero-click hitting ~60% of searches (2024) and AI Overviews appearing in ~13% of queries (May 2025), being the extracted answer matters more than the click.

<!-- Bad: warms up for three paragraphs before answering -->
## Should you compost in an apartment?
Composting has become increasingly popular in recent years as more people
look for sustainable lifestyle choices. Many city dwellers assume they can't
participate because of limited space. But is that really true? Let's explore
the fascinating world of urban composting and find out together.

<!-- Good: answers in the first two sentences, then expands -->
## Can you compost in an apartment?
Yes — a sealed countertop bokashi bin or a small worm bin (vermicomposting)
lets you compost food scraps in a flat with no yard and no smell. Bokashi
ferments scraps in ~2 weeks; a worm bin yields finished compost in 3–6 months.
Here is how to choose between them and set one up in a 60×40 cm footprint.

If the query is a question, the H1 or first H2 should be that question and the next sentence should answer it. Worked lede examples are in references/on-page-seo.md.

Outline as a question map

Build the skeleton from real subtopics, not from what you feel like writing.

• One H1, matching the primary query or its close paraphrase.
• H2/H3 are questions or named subtopics that mirror the SERP's "People also ask", related searches, and the headings competitors share — plus the gaps they all miss (that gap is your edge).
• One idea per heading. A heading that needs an "and" is two headings.
• Headings are subtopics, not slogans: ## How much does a standing desk cost? not ## The Price Question.

Why question-shaped headings: only ~38% of pages cited in AI Overviews rank top-10, so clean, extractable, question→answer structure can win citations without traditional authority. Make every section answerable on its own.

Drafting for depth and E-E-A-T

Google does not penalize AI-assisted content as such. It penalizes scaled content abuse — high-volume, no-editorial-review, thin, no-first-hand-experience pages. The March 2026 core update named scaled content abuse a primary target; offending sites saw 50–80% traffic drops. The defense is not avoiding AI; it is genuine value, depth, and human review.

So every draft earns its keep with E-E-A-T (Experience, Expertise, Authoritativeness, Trust — Trust is the load-bearing member):

• First-hand experience — a thing you tested, measured, or saw. "We ran the worm bin for 90 days and weighed the output" beats "worm bins are effective".
• Original data or insight — a number, comparison, or angle not already on page one.
• Credible cited sources for claims you did not generate yourself — link them inline.
• Clear authorship — a named author with relevant standing, not "admin".
• Match intent over keyword density. Answer the question fully; the keywords fall out naturally. Never stuff.

Run a human-review pass before ship. If nothing in the draft could only have been written by someone who actually knows the topic, it is thin — add experience or do not publish.

The on-page surface

Every article ships with these. Keep them in the file's front-matter or a clearly labelled block so scripts/verify.sh can lint them.

• Title tag: 50–60 characters / under 580–600 px desktop (480 px mobile). Put the primary keyword in the first ~30–35 characters. Titles of 51–55 chars are rewritten by Google least often.
• Meta description: 140–160 characters (desktop ~920 px ≈ 158 chars; mobile cuts at ~120). One to three sentences, lead with the value. It does not rank, but it drives CTR and is often the snippet AI engines echo.
• H1: exactly one, matching the query.
• Slug: short, lowercase, hyphenated, keyword-bearing, no stop-word noise — /compost-in-apartment not /how-to-start-composting-in-your-apartment-today.
• FAQ block: 3–6 real questions from "People also ask", each answered in 2–4 sentences.

Full pixel/char tables, slug rules, and copy-ready Article/BlogPosting + FAQPage JSON-LD (JSON-LD only — never microdata) live in references/on-page-seo.md. The JSON-LD must describe what is actually on the page; schema that does not match visible content is a quality flag, not a win.

Internal links and topical authority

Place 3–5 contextual internal links in the body of a standard article (more only for a long-form pillar). Rules:

• Descriptive anchor text — worm bin setup guide, never click here or a bare URL.
• Keep priority pages within ~3 clicks of the post.
• For a pillar, link two ways: pillar → each cluster article and each cluster article → pillar. That two-way map is the topical-authority signal AI engines read.

You insert the link slots and anchors that fit this article. Deciding the cluster structure — which pillar owns which clusters across the site — is ../content-engine/SKILL.md's job, not yours.

Cut the AI tells and the fluff

Do one ruthless pass: delete every sentence that adds no fact. If a sentence could sit in any article on any topic, it is filler.

Banned on sight (short sample): "In today's fast-paced world", "It's important to note that", "When it comes to", "Let's dive in", "the world of X", "navigating the landscape of", "unlock the power of", "in conclusion". The full banlist with Bad→Good rewrites and the depth self-review is in references/ai-tell-banlist.md — and that file is the single source verify.sh greps against.

<!-- Bad: 28 words, zero facts -->
In today's fast-paced world, it's important to note that choosing the right
standing desk can really make a difference when it comes to your health.

<!-- Good: 19 words, three facts -->
A standing desk adjustable from 70–120 cm fits users 1.5–2.0 m tall and cuts
the lower-back load reported across sit-all-day workdays.

Anti-patterns

Ship checklist

Restating the gates verify.sh enforces, for the human review:

• Answer-first lede — primary query fully answered in first ~200 words
• Exactly one H1; at least two question-shaped H2s
• Title 50–60 chars (keyword early); meta 140–160 chars
• JSON-LD present with @type Article/BlogPosting; FAQPage too if an FAQ section exists
• At least one contextual internal-link slot with a descriptive anchor (target 3–5)
• AI-tell / fluff banlist scan is clean
• Depth matches intent; first-hand experience or original data present; author + sources named

Run scripts/verify.sh path/to/article.md. It is a lint of structure and banned phrasing — it does not judge whether the content is good. That is the capability eval's job, and yours.