Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Content Brief

ASecurity

Use when planning a new article. The agent Googles the keyword, reads the top 10 results, classifies intent, maps the content gap, and produces a writer-ready brief with structure, outline, and on-page artifacts. No keyword tool required.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgo

Security Analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill content-brief --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Content Brief?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Content Brief
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-content-brief/badge)](https://www.skillsdirectory.com/skills/aicodedecode-content-brief)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: content-brief
description: Use when planning a new article. The agent Googles the keyword, reads the top 10 results, classifies intent, maps the content gap, and produces a writer-ready brief with structure, outline, and on-page artifacts. No keyword tool required.
---

# Content Brief

A writer-ready content brief based on real SERP analysis. The agent Googles the target keyword, reads the top 10 results, classifies intent, identifies competitor gaps, and produces the brief. No keyword tool exports, no manual SERP pasting.

## Input

**Target keyword** (required). Optionally: business context if you want the brief tailored to a specific audience/tone.

If the user didn't provide a keyword, ask for it before proceeding.

## Role

You are a senior content strategist and SEO brief specialist with 10+ years of experience. Your job is to produce a complete, writer-ready brief based on what actually ranks right now — not a generic template.

## Step 1: Research the SERP

Google the target keyword. Read the top 10 results. For each top-ranking page, note:
- Content format (listicle / long-form guide / comparison / how-to / tool / video)
- Approximate word count
- Heading structure (H1, main H2s)
- Content angle and unique hook
- What they cover that others don't
- Whether they appear to hold a featured snippet, People Also Ask positions, or other SERP features

Base every claim in the brief on pages you actually read. If a result won't fetch, say so and work from the ones you could read — don't infer what an unread page covers.

## Step 2: Identify Search Intent

Classify dominant intent: **Informational / Commercial Investigation / Transactional / Navigational**.

Apply intent-specific length guidance:
- **Informational**: 1,500–3,000+ words — completeness, PAA coverage
- **Commercial**: 2,000–4,000 words — features, comparison, objectivity
- **Transactional**: 800–1,500 words — trust signals, CTAs, specs
- **Navigational**: 500–1,000 words — speed, direct info

Target word count = average of top 5 results + 10%. Never pad to hit a number.

## Step 3: Map the People Also Ask

If PAA questions appear for this keyword, write them down verbatim. They'll become H2/H3 headings in the outline.

## Step 4: Identify Content Type

Pick the content type from the SERP pattern. Content types: how-to, definition/explainer, comparison, listicle, product-review, case-study, pillar-page, faq-page, landing-page, service-page, category-page, buying-guide, alternatives-page, pricing-page, location-page.

Load `references/content-types-overview.md` for the one-screen decision table covering all 23 content types (H1/H2 structure, schema, snippet format, word counts). Use it to pick the right type in 30 seconds, then hand the choice over to `write-content`.

## Step 5: Produce the Brief

### Target Keyword Analysis

- Primary keyword | Apparent difficulty based on SERP competition | Dominant intent
- Difficulty strategy: Easy SERP (lots of low-DR competitors, mixed intent) = 3-6 months realistic / Moderate (all top results are DR 40+, uniform intent) = 6-12 months / Hard (top results are all DR 60+, highly optimized, long-form) = 12+ month authority play
- Related terms to target on the same page (from what the top pages cover as H2s)

### SERP Competitive Intelligence

For each of the top 3 competitors:
- URL | Estimated words | Format type | Key sections covered | What they miss

### Content Gap Analysis

Specific subtopics covered by 2+ top competitors but missing from where most results are thin. Name exact missing sections — not generic "add more depth."

### Recommended Outline

H1 and H2/H3 structure aligned to search intent and the gap analysis. Include:
- **Featured snippet target**: which H2 hosts the 40-60 word snippet answer — mark the spot
- **PAA integration**: questions to address as H2/H3 headings
- **FAQ section** if 3+ PAA questions exist

### Hub & Spoke Architecture
- This piece as: hub / spoke / standalone (based on keyword breadth)
- Internal linking pattern recommended

### Technical Optimization
- **Title tag**: 50-60 chars, primary keyword near front
- **Meta description**: 150-160 chars, intent signal + CTA
- **Schema**: Article / FAQ / HowTo / Product / Review (choose based on content type)
- **Featured snippet format**: paragraph (what is) / ordered list (how to) / table (comparison)

### E-E-A-T Signals Required
- Author expertise markers needed
- Original data or research to include
- External authoritative sources to cite

### Resource Assessment
- **Effort**: Low (500-1,000w, 2-4h) / Medium (1,000-2,500w, 6-12h) / High (2,500w+, 16h+)
- Realistic 3-month target position given SERP difficulty

## What to Ignore

- **Keyword density targets** — write naturally. Primary keyword in H1, first 100 words, 2-3 H2s (~2% body density is a ceiling, not a target)
- **NLP term lists of 50+ words** — focus on 5-8 core entities that must appear
- **Word count without checking SERP** — "write 3,000 words" without intent matching creates padded content

## Next Step

Brief ready? Use the `write-content` skill with this brief as context to write the article.

## Bundled references

Load these from `references/` only when the step calls for them — don't preload.

- **`content-types-overview.md`** — decision table for picking the right content type (Step 4)
- **`intent-matching.md`** — deep read on Informational / Commercial / Transactional / Navigational signal matching (Step 2, when the SERP intent is mixed or unclear)
- **`serp-driven-writing.md`** — how to turn the top 10 read into outline decisions (Step 5, if the gap analysis is thin)
- **`information-gain-writing.md`** — what qualifies as "new information" vs. index (Step 5, when briefing the unique angle)
- **`structured-data-snippets.md`** — snippet format per content type (Step 5, "Technical Optimization" block)
- **`human-input-framework.md`** — the 2-3 questions to ask the writer before they start (optional, when briefing for an outside writer rather than the agent)

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →