content-brief-factory

content-brief-factory is a skill for Claude Code, Codex from gooseworks-ai/goose-skills. It costs 76 tokens per session (3,138 once invoked), scanned A, original, MIT.

A content-brief tool that researches search results, competing pages, customer language, internal links, and search-result features to guide writers.

In plain words
What is it for?
It helps plan search-focused articles, programmatic SEO pages, and content calendars.
Why use it?
It replaces vague keyword lists with a clearer explanation of what already ranks, what competitors miss, and how a new page could differ. Batch mode helps prepare many briefs from a keyword list.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 skills/site-content-catalog/scripts/catalog_content.py \.

Good fit It helps plan search-focused articles, programmatic SEO pages, and content calendars.

Compare 6 skills from other repositories ↓
About the project

Goose Skills is a library of workflows and data APIs that lets coding agents handle growth and go-to-market work such as advertising, social media, content, SEO, lead generation, and customer research. It is intended for teams using Claude Code, Cursor, Codex, and similar agents. The catalogue entries are its reusable skills.

gooseworks-ai/goose-skills · 1,202 stars · on GitHub · gooseworks.ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/gooseworks-ai/goose-skills
agentmods
npx agentmods add skills/gooseworks-ai/goose-skills/content-brief-factory

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for content-brief-factory

README.md
[![agentmods](https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/content-brief-factory/github.svg)](https://agentmods.dev/skills/gooseworks-ai/goose-skills/content-brief-factory)
Your own site
<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/content-brief-factory"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/content-brief-factory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for content-brief-factory

Your own site · 80×15
<a href="https://agentmods.dev/skills/gooseworks-ai/goose-skills/content-brief-factory"><img src="https://agentmods.dev/badge/skills/gooseworks-ai/goose-skills/content-brief-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.03138
Opus 5 $0.00038 $0.01569
Sonnet 5 $0.00015 $0.00628
Haiku 4.5 $0.00008 $0.00314

Measured 9d ago against content hash dfbe1b423e7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

content-brief-factory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/content/composites/content-brief-factory/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Brief Factory

Most content briefs are garbage. They tell you "mention these keywords 7 times" and call it a strategy. This skill produces briefs that include competitive analysis, unique angles mined from what real customers say, SERP feature targeting, and a differentiated outline — so your writer knows exactly what to create and why it'll rank.

Core principle: A great brief doesn't just say "write about X." It says "here's what's already ranking, here's why it's winning, here's the gap they missed, here's the customer language that proves the gap matters, and here's exactly how to structure a page that beats them."

Batch mode: Process 10-50 keywords in a single run. Each brief takes ~30 seconds in enhanced mode, ~60 seconds in baseline.

When to Use

  • "Create content briefs for these keywords"
  • "I need briefs for our Q2 content calendar"
  • "Write briefs for our pSEO templates"
  • "Generate 20 briefs from this keyword list"
  • "What should we write about [topic]? Give me a full brief."

Tool Enhancement (Optional)

Briefs are significantly better with real SERP data (what's actually ranking, what SERP features appear) rather than inferred analysis.

Agent Prompt to User

"I can create strong content briefs using competitive research and customer language mining. For the best results — especially accurate SERP analysis and keyword metrics — I'd recommend connecting a SERP data API."

Recommended: SerpAPI (100 free searches/month, $50/month for 5,000)

  • Sign up at serpapi.com → get API key
  • Set SERPAPI_KEY env var

Alternatives that also work:

  • Serper.dev (2,500 free searches, then $50/month for 50K) → set SERPER_API_KEY
  • DataForSEO SERP (pay-per-use, ~$0.01/search) → set DATAFORSEO_LOGIN + DATAFORSEO_PASSWORD
  • ValueSERP (free tier available) → set VALUESERP_API_KEY

"Want to use one of these, or should I proceed with baseline mode? Baseline uses web search to analyze competing pages — still produces great briefs, just with less precise SERP feature and volume data."

Read the full file on GitHub · 333 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 333 lines · 76 tokens per session scan A dfbe1b423e7e

Subscribe to this mod's changes

content-brief-factory is a skill published in the GitHub repository gooseworks-ai/goose-skills (1,202 stars, last pushed 11d ago), licensed MIT. It adds 76 tokens to every session and 3,138 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.