agentleFS
robdasirobdasi/skills/content-preflight/SKILL.md

content-preflight

Skill0 starsChanged 5 months agoMITView on GitHub

Run the 12-point pre-write checklist before writing any SEO article or page. Turns a target keyword into a research-backed content brief: search intent, content gaps, real People Also Ask, semantic terms, entities to cite, internal links, the EEAT angle, and an outline. Use this BEFORE writing any piece of SEO content so the page is built on what actually ranks, not a guess. It stops at the brief. Writing to the brief is the next step (yours, or your writer's).

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ShangBoyang0130/dsh-rules★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Live SERP: Search the keyword. List the top 8-10 ranking URLs, the dominant format (guide / listicle / comparison / tool / product), and …

    line 28
  2. Distinctive:

    Content gaps: Read what those pages cover.

    line 29
  3. Distinctive:

    The AI Overview: Check whether an AI Overview answers the query outright.

    line 31
  4. Distinctive:

    Use web search for checks 1-7 if you have no SEO API.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Content Pre-Flight

Most AI content is written straight from a keyword and a prompt. That is why it reads like slop: the model never looked up from the keyword. This skill runs the research a good SEO does first, then hands you a brief to write to.

Twelve checks, in order. Fill the brief as you go. Do not skip ahead to writing.

Inputs (ask for whatever is missing)

  • Target keyword / topic (required)
  • The site's domain and what the business sells + who for (for intent + EEAT)
  • Optional, makes it sharper: a Search Console export, a Google Analytics view, and any keyword-tool read (volume / difficulty) the user already has. Work without them if absent.

The 12 checks

  1. Live SERP. Search the keyword. List the top 8-10 ranking URLs, the dominant format (guide / listicle / comparison / tool / product), and rough word count. This is the bar to clear.
  2. Content gaps. Read what those pages cover. Note what NONE of them cover, and what only one or two do. The gap is usually where the new page wins.
  3. Real People Also Ask. Pull the actual PAA / "related questions" Google shows for the term. Never invent these. They become H2s and the FAQ schema.
  4. The AI Overview. Check whether an AI Overview answers the query outright. If it fully satisfies the user, flag it: this keyword may not be worth writing for (the click no longer happens). Prefer queries where the user still has to act, go, or book.
  5. Search intent. Classify it: informational, comparison, transactional, or local. The intent dictates the format. Comparison -> tables. How-to -> numbered steps. Informational -> definition first.
  6. Semantic terms. From the ranking pages, extract the 8-12 topic/entity terms they all share. Set a target count for each (1-3 mentions). Covering these is how you signal topic coverage, not just keyword repetition.
  7. Entities. List every tool, company, product, and stat the competitors cite. Research each one up front so the draft references real things, not invented ones.
  8. Search Console (if provided). What does the site already rank for near this topic, and what is slipping? Reinforce existing momentum instead of starting cold.
  9. Analytics (if provided). What actually converts on this site? Bias the topic toward pages that earn, not just pages that get traffic.
  10. Authority / difficulty read. Honestly assess whether this site can realistically rank for this term given its current authority. If not, pick the winnable adjacent term instead.
  11. Internal links. Identify which existing pages this one should link to and which should link back to it. Place it in a cluster, not on an island.
  12. EEAT angle. Define the first-person experience or proprietary data the author can add that a competitor cannot. Generic authority does not rank; specific experience does.

Output: the brief

Produce a single brief with:

  • Verdict — write it / do not write it (and why), based on checks 4 and 10.
  • Primary keyword + intent + target format
  • Angle — the gap this page fills (from check 2)
  • Must-answer questions — the real PAA (check 3)
  • Semantic terms + target counts (check 6)
  • Entities to cite with a one-line fact each (check 7)
  • Internal links in and out (check 11)
  • EEAT hook — the specific experience to weave in (check 12)
  • Outline — H2s matched to intent and built to fill the gap, with a rough word count per section

What this skill does NOT do

It stops at the brief. It does not write the article. That is deliberate. A brief this good makes the writing the easy 10%. Write to it by hand, with your own model, or with your own pipeline.

Notes

  • Use web search for checks 1-7 if you have no SEO API. Paste-in exports cover 8-9.
  • Front-load answers in the eventual draft (answer-first passages, declarative sentences, dated numbers) so both Google and AI summaries can extract cleanly.
  • Built by Robin Laires / Laires Labs. laireslabs.com

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.