FREE TEMPLATE + CLAUDE SKILL · CONTENT BRIEFS
Most briefs are a keyword and a word count, so the writer makes fifty decisions you never see until the draft comes back wrong. This template specifies all of them: the sub-queries each section answers, word counts per section, the sources to cite, the internal links, and what not to do. Take the template free, or install the Claude skill that fills it in with real keyword data.
Copy the template straight off this page · Skill runs in Claude · Connects to Ahrefs and Exa if you have them · No card required
Why briefs fail
Every ambiguity you leave in a brief becomes a judgement call made by someone with less context than you. You find out three days later, when the draft comes back on a different angle, at the wrong length, citing a source you would not have approved.
The test for a finished brief is simple. Could a competent writer who has never spoken to you produce a publishable first draft from this alone? If they would need to ask a question, the brief is not finished.
sub-queries an answer engine fires for one complex question.
A brief that specifies one keyword produces a page matching a fraction of what gets retrieved. Pages covering the fan-out see roughly a 161% lift in citation likelihood (Surfer SEO, 2026, directional).
The template
Copy it. Use it. Change it. It is the same structure the skill generates.
CONTENT BRIEF TEMPLATE ====================== THE ASK Topic / working title: Primary keyword: Monthly searches (global): [ enter ] Keyword difficulty: [ enter ] Format: [ blog post / comparison / how-to / guide ] Total word count: [ n ] (per-section breakdown below) Deadline: Published at: [ URL or /new-path ] TARGET KEYWORD DATA --- Primary keyword [ enter ] Monthly searches (global) [ enter ] Keyword difficulty [ enter ] SERP format [ list / comparison / Q&A / editorial ] Existing pages on this topic [ n — list any that overlap ] AUDIENCE Who: [ job title or buyer segment ] Trigger: [ what event made them search today ] Prior knowledge: [ what they already know ] Must answer: [ the single question this page resolves ] ANGLE What this piece says that page one does not: [ one sentence. If you cannot write it, the piece is redundant. ] Why we can say it: [ source, data, or first-hand experience that earns the claim ] STRUCTURE --- H1: [ exact H1 text ] Opening capsule (150 words max) Front-load the direct answer: problem, solution, one-sentence proof. Do not throat-clear or restate the headline. Sections: H2 text Sub-query it answers Words Format ---------------------------------------------------------------------- [ H2 text ] [ question this section answers ] [ n ] [ prose / bullets / table ] [ H2 text ] [ question this section answers ] [ n ] [ prose / bullets / table ] [ H2 text ] [ question this section answers ] [ n ] [ prose / bullets / table ] [ H2 text ] [ question this section answers ] [ n ] [ prose / bullets / table ] [ H2 text ] [ question this section answers ] [ n ] [ prose / bullets / table ] Must include in [ section ]: [ specific data point, table, or example required ] FAQ Include as FAQPage schema at the end of the post. State questions as plain questions. 3 to 5 items. Q: Q: Q: SOURCES TO CITE --- Source URL Claim it supports Section [ author/org, yr ] [ https:// ] [ specific claim ] [ H2 ] [ author/org, yr ] [ https:// ] [ specific claim ] [ H2 ] INTERNAL LINKS Outbound (from this page to site): - [ anchor text ] to [ /path ] -- reason it belongs here Inbound (existing pages to update): - [ /existing-page ] -- add link using [ anchor text ] CTA Destination: [ URL or section anchor ] Trigger: [ what the reader should want after the final section ] Button text: [ exact copy ] DO NOT - [ claim we cannot support with a named source ] - [ competitor or brand name to avoid ] - [ positioning that conflicts with existing messaging ] - [ topic already covered by an existing page ] OPEN ITEMS # Question Owner 1 [ question to resolve before writing starts ] [ name ]
That is the whole thing. The hard part is not the structure, it is filling in the target keyword data, mapping the sub-queries, and finding the sources. That is what the skill does.
What most briefs are missing
Word counts per section, not just a total
A total invites 800 words of preamble and 200 of substance. Per-section counts make the shape of the piece non-negotiable.
Real source URLs
A writer told to find supporting data either will not, or will find something you would never have approved. Give them the links and say what each one supports.
The angle, stated
What this piece says that page one does not. If the brief cannot articulate it, the piece is redundant before anyone starts writing.
A do-not section
Unsupportable claims, competitors not to name, positioning to avoid. This prevents more rework than any other field in the brief.
Fan-out mapping
Answer engines split a question into sub-queries and retrieve passages for each. The brief job is to make sure the article covers the ones that matter. The skill maps them across seven types, then filters to the ones that earn a section.
Six to ten surviving sub-queries is usually the right article. More than fifteen and the topic is a cluster, not a page. The skill says so rather than specifying a 6,000-word piece nobody finishes.
See it run
What makes it different
Researches before it specifies
Pulls volume, difficulty, and SERP format from Ahrefs so the brief targets something real rather than something plausible.
Checks your cluster first
Looks for pages you already have on the topic. Two pages targeting one sub-query compete with each other in retrieval, not just in rank.
Gives the writer the sources
Real URLs mapped to the specific claims they support.
Never invents a statistic
Gaps come back marked, not filled. A fabricated figure in a brief becomes a fabricated figure in a published article with your name on it.
Specifies what not to do
The field that prevents the most rework, and the one almost every brief template omits.
Feeds the next skill
Hands straight to the AEO blog post skill, which writes the draft from it. Brief, draft, audit. Three skills, one chain.
How it works
Install the skill
Download the file and save it into Claude. It triggers whenever you ask for a brief, an outline, or a content spec.
Give it a topic and an audience
It runs keyword and SERP research, checks your existing cluster, maps the fan-out, and finds real sources.
Get the brief as a file
Markdown, ready to paste into Notion, Docs, or a ticket. Hand it to a writer, or hand it to the AEO blog post skill.
Who it's for
Want us to run the content programme instead? That is the Lil Big Things GEO programme. Book a GEO strategy call
What's in the file
content-brief.skill The installable skill. Save once, run on demand.
content-brief/
SKILL.md Workflow, ten rules, brief types, self-check.
references/
fan-out.md Mapping sub-queries, sizing sections,
format by engine.
assets/
brief-template.md The template on this page, as a file.Honest note
A brief cannot rescue a topic that should not be written. The skill will tell you when an existing page should be expanded instead, and when a topic is really a cluster rather than a single piece. Both of those answers are more useful than a brief, and both are answers people commissioning content rarely want to hear.
More free skills
SEO + AEO Audit
Checks whether engines can crawl, render, and cite your site.
Homepage Build + Audit
Grades your homepage against six buyer questions and rewrites what is broken.
AEO Blog Post
Writes content engineered to get cited.
Content Brief (this)
Builds a brief a writer can execute without a follow-up call.
Meta Description Optimizer
Rewrites title tags and descriptions against the live top 10.
GET THE SKILL
Drop your email and we will send the skill file plus the template as a document. We will also send the occasional GEO Times update. Unsubscribe anytime.
FAQ