agentleFS
sitetillersitetiller/ai-visibility-skills/skills/content-brief/SKILL.md

content-brief

Skill0 starsChanged 2 days agoMITView on GitHub

Build a brief for a new page from real data: Search Console queries for the topic (gsc --dims query,page), the live results page the user pastes in, and quotability signals of the competing pages (cite). Produces intent, must-answer questions, an information-gain plan from Google's helpful content guidance, outline, internal links and a measurement plan, with no invented search volumes. Use when the user says 'content brief', 'write a brief for', 'what should this page cover', 'new article outline', 'SERP analysis', 'what are competitors doing'.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use competitor-gap, serp-analysis and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • DarynaRodriguezSkill

    competitor-gap

    Finds the terms rivals rank for and the site does not, confirms who the real organic competitors are, and returns a gap table split into terms to win, terms underperforming, and terms to concede.

    Also in 4 projects that use this

  • opencueSkill

    serp-analysis

    Use when the user asks to "analyze SERPs"; reviews ranking factors, features, intent, AI Overviews, and snippets. SERP分析/搜索结果

    Also in 3 projects that use this

  • indranilbanerjeeSkill

    client-proposal

    Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. \"respond to this RFP\"

    Also in 3 projects that use this

  • akii-technologies-ltdSkill

    internal-linking

    Analyze and improve internal linking strategy. Use when the user asks about "internal links", "link structure", "site architecture", "link strategy", "orphan pages", "link equity", "page authority distribution", "anchor text", "topical clusters", "siloing", or wants to improve how pages connect.

    Also in 3 projects that use this

  • akii-technologies-ltdSkill

    keyword-clustering

    Cluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "group keywords", "organize keywords", "keyword mapping", "topic clusters", "keyword grouping", "build a content plan", "pillar pages", "topical authority", "semantic clustering", or pastes a list of keywords.

    Also in 3 projects that use this

  • silvainfmSkill

    schema-markup

    When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If an existing page already receives these queries, decide with cannibalization whether to extend it instead of creating a new one.

    line 28
  2. Distinctive:

    Write the intent in one sentence from query wording, not from guesses: "template" wants a file, "vs" wants a decision, "how to" wants steps.

    line 35
  3. Very specific:

    Add internal links in both directions (internal-links) and the measurement plan (measure-rollback).

    line 37
  4. Distinctive:

    Never invent search volume, difficulty or traffic forecasts.

    line 65
  5. Distinctive:

    Do not copy competitor wording or structure.

    line 66
  6. Distinctive:

    Do not set a word count. Set the questions to be answered.

    line 67
  7. Very specific:

    Do not brief a second page for a query another page of the same site already ranks for before checking cannibalization.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “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 brief from evidence

Goal: a brief a writer can follow, where every requirement traces to a query the site already gets, a result the user observed, or a line in Google's guidance. Search volume is never invented. Search Console shows impressions for the user's own site, and that is the only demand number used. If the user has a third-party volume figure, they supply it and the brief labels it with its source.

Inputs

  • The topic, and Search Console access (see gsc-bing) or a Queries/Pages export.
  • The live results page for the main query, pasted by the user with the date: titles, URLs, features seen (AI overview, video, forum threads). The CLI does not scrape Google results and this skill does not either.
  • Whether the page is new or replaces an existing one (run cannibalization first).

Steps

  1. Pull the site's own data, 90 days if available:
    npx sitetiller gsc example.com --start 2026-08-12 --end 2026-11-09 --dims query,page --out qp.csv
    npx sitetiller gsc example.com --start 2026-08-12 --end 2026-11-09 --dims query --out queries.csv
    Filter rows to the topic by text match and group them by meaning (topic-clusters). Note which page each query lands on today and at what position. Related queries at positions 4-20 show relevance the site already has:
    npx sitetiller striking queries.csv --json
  2. If an existing page already receives these queries, decide with cannibalization whether to extend it instead of creating a new one.
  3. For each competing page the user listed:
    npx sitetiller page https://competitor.example/post --json
    npx sitetiller cite https://competitor.example/post --json
    From page: title, h1, headings, words, tables, schemaTypes. From cite: per-section heading, numbers, hasTable, hasList, links, and the summary shares (answer-first, specific, structured, sourced). Then read the text and record what the page does not answer.
  4. Write the intent in one sentence from query wording, not from guesses: "template" wants a file, "vs" wants a decision, "how to" wants steps.
  5. Fill the brief (format below). The information-gain section is mandatory.
  6. Add internal links in both directions (internal-links) and the measurement plan (measure-rollback).

Information-gain checklist

From Google's helpful content guidance. A page with none of these restates what Google already shows:

  • Original information, reporting, research or analysis: own data, a test, a benchmark, a survey, screenshots, a worked example with real numbers.
  • Insight beyond the obvious: a decision rule, a pitfall, a counter-example.
  • Value over the sources it draws on. If it summarises others, say what is added.
  • First-hand experience where the topic calls for it, with author and background shown.
  • A complete answer: the reader does not need to search again.
  • Honest dates: no refresh without substantive change; no word-count target. For each item the brief names the asset, who creates it and where it sits on the page.

Brief format

  1. Target: main query and the 3-8 closest queries from the site's data, each with impressions and position.
  2. Intent: one sentence, and the page type (guide, template, comparison, tool, data).
  3. Reader and next step.
  4. Must answer: questions from the queries and from gaps in competing pages, each tagged query or gap.
  5. Information gain: the assets above.
  6. Outline: headings phrased as the questions answered, answer first in each section.
  7. Evidence and sources: each fact to be used with a source, or "to be tested".
  8. Elements: title and description options (titles-meta), schema types (schema), tables or tools.
  9. Links: pages to link to, pages that should link in.
  10. Measure: publish date, queries to watch, window of at least 28 days.

Output to the user

The filled brief and a short list of unknowns, such as "no data for query X; volume not assumed".

Guardrails

  • Never invent search volume, difficulty or traffic forecasts.
  • Do not copy competitor wording or structure. Use them to find gaps.
  • Do not set a word count. Set the questions to be answered.
  • Do not brief a second page for a query another page of the same site already ranks for before checking cannibalization.
  • Content created from the brief must have a person accountable for its facts; Google lists mass-produced, lightly cared-for pages as a quality warning sign.

References

  • references/sources.md

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.