More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    SEO Content Writer

    1

    Write blog posts, guides, and comparisons that rank and convert: intent first, a SERP brief, titles that win the click, checkable claims, one clear next step.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    SEO Content Writer

    SEO Content Writer

    Example session with this skill installed

    Plan an article for our kitchen blog targeting "best budget espresso machine". We sell nothing ourselves; the post earns from affiliate links. What should the article look like?

    • Read your context and instructions
    • Compiled the seo content writer

    Intent sentence. The searcher wants a shortlist of espresso machines under $300 they can trust, so they can buy one this month without a research project. SERP check: the top results are all tested roundups — commercial intent, comparison format. A how-to or a buying-guide essay would lose to that shape.

    Recon brief. The top three run 2,100–3,400 words and all cover the same six machines. None of them tests how the machines suit a small kitchen — counter depth, heat-up time, noise at 6 a.m. That is the wedge: a "small kitchen, early morning" testing angle.

    Title options. 1) Best Budget Espresso Machines: 6 Tested Under $300 (2026). 2) 6 Espresso Machines Under $300, Tested in a Small Kitchen. 3) Budget Espresso Machines: What $150–$300 Actually Gets You. Pick: option 2 — the keyword sits early and the title promises the wedge, not a seventh copy of the same roundup.

    Meta description. "We tested 6 espresso machines under $300 for taste, heat-up time, noise, and counter space. One clear winner for small kitchens — see which, and why."

    Structure. H1 mirrors the title. First 100 words give the verdict up front: the winner named, two runners-up, prices. Then one section per machine (taste, heat-up, noise, footprint), a comparison table, the wedge section ("Tested at 6 a.m. on a 40 cm counter"), a descaling-and-care section the top three skip, and exactly one CTA — the winner's product page. FAQ seeds from real search questions: "Is a $200 espresso machine worth it?", "How long do budget machines take to heat up?", "What size machine fits a small counter?" — each answered in 40–60 words, direct answer first, so any one can travel alone into a snippet.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Most SEO content fails quietly. It targets the wrong intent, or loses the click to a better title, or gets eight seconds before the reader bounces, or makes claims nobody can check. This skill treats a search article as a journey with six stages — intent, research, click, scan, trust, action — and gives each stage a job, a test, and the mechanics that serve it.

    It starts before the draft: you name the intent in one sentence ("the searcher wants X so they can Y") and recon the results page for format, depth bar, and the wedge — the question the top three results all dodge, which becomes the reason your page deserves to exist. Then it builds the click (three title options under the promise rule, a meta description that ends on the reason to click), the scan (an H1 that mirrors the promise, the core answer in the first 100 words, headings that tell the story alone), and the depth that holds a reader: one idea per section, specifics over adjectives, your own evidence on the page.

    A claim triage table sorts every statistic, comparison, and superlative before shipping, so nothing fabricated or stale survives. The close follows the intent sentence to exactly one call to action, and the FAQ block is written as self-contained answers built to travel into featured snippets and AI answers. The skill includes the brief template, a complete worked example (a freelancer invoicing guide, stage by stage), edge cases for product pages and regulated topics, and a pre-delivery quality gate with five checks a page must pass before it ships.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Writing & Content.

    • It cannot run live keyword tools; volume and difficulty calls come from reading the results page, which is honest recon but not a metrics dashboard.
    • Rankings are never guaranteed — the method raises the odds at every stage of the journey, but search outcomes also depend on your site's authority and history.
    • The evidence standard cuts both ways: if you have no first-hand tests, data, or screenshots, Stage 5 will be thin and the draft will say what it could not verify.
    • Written for search-led articles in English; other languages and video-first content need adaptation.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    Permissions

    No special permissions declared or detected

    Listed24 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    The generic ask skips the two stages that decide everything: intent and recon. This skill forces an intent sentence checked against the live results, a brief with a wedge the top pages miss, a promise rule for titles, and a claim triage pass — the draft is the last step, not the first.

    Yes — that is usually a Stage 0 or Stage 6 problem: the page attracts a learn-intent reader and then asks them to buy, or it closes with four competing calls to action. The skill re-reads the page against its intent sentence and fixes the close to one next step matched to that intent.

    No. The recon stage works from the results page itself — formats ranking, the depth bar of the top three, the phrases those pages use, and the questions searchers ask. Tools can add volume numbers if you have them, but the method does not depend on them.

    New in Writing & Content