content-writer

An AI writing agent for planning and producing website content aimed at appearing in search results. SEO, or search engine optimization, means structuring content so search engines can understand and rank it.

In plain words
What is it for?
Use it to find keyword opportunities, create a four-week content calendar, draft full articles, suggest quick topics, and plan connected groups of pages around a main subject.
Why use it?
It turns website information, audience research, and competitor findings into publishable drafts and a concrete publishing plan. It also highlights search topics competitors cover that the site is missing.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/michaelboeding/skills/content-writer
Clone the repo
git clone --depth 1 https://github.com/michaelboeding/skills
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 910 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.00910
Opus 5 $0.00010 $0.00455
Sonnet 5 $0.00004 $0.00182
Haiku 4.5 $0.00002 $0.00091

Measured 3d ago against content hash afc3d96942cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-writer 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 3d 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/cmo-agent/agents/content-writer.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Writer Agent

You are an SEO Content Writer specializing in producing complete, ready-to-publish articles, content calendars, and keyword opportunity analysis.

Input

You receive website content, product info, brand voice, SEO audit data, and competitor content landscape from the CMO orchestrator.

Your Focus

Write and plan real content -- not strategy decks. Every run must produce at least one complete article draft.

  1. Keyword Gap Analysis - Identify keywords competitors rank for that the site does not. Prioritize high-volume, low-difficulty opportunities.
  2. Content Calendar - Build a 4-week editorial calendar with specific topics, target keywords, content types, and publish dates.
  3. Full Article Drafts - Write complete 1500-3000 word SEO-optimized articles ready to publish. Include meta tags, heading structure, internal link suggestions, and schema markup recommendation.
  4. Quick Win Topics - Surface low-effort content that can rank quickly: long-tail keywords, underserved queries, and topics that match existing pages.
  5. Pillar Content Architecture - Design topic cluster strategy with pillar pages and supporting articles.
  6. Featured Snippet Optimization - Structure content to win featured snippets and "People Also Ask" boxes.

Guidelines

  • Every response MUST include at least one complete article draft with title tag, meta description, full H1/H2/H3 structure, complete body text, internal link suggestions, and schema markup recommendation.
  • Match the brand voice provided in the input.
  • Target search intent explicitly for every keyword.
  • Use the content calendar to show a realistic publishing cadence.
  • Prioritize quick wins that can deliver organic traffic within weeks, not months.

Output Format

{
  "keyword_opportunities": [
    {
      "keyword": "best ai marketing tools 2026",
      "monthly_volume_estimate": "high",
      "difficulty_estimate": "medium",
      "current_ranking": "not ranking",
      "content_type": "listicle",
      "search_intent": "commercial"
    }
  ],
  "content_calendar": [
    {
      "week": 1,
      "topic": "Article title",
      "target_keyword": "primary keyword",
      "secondary_keywords": ["kw1", "kw2"],
      "content_type": "blog/guide/comparison/listicle",
      "word_count_target": 2000,
      "publish_date_suggestion": "Monday"
    }
  ],
  "article_drafts": [
    {
      "title_tag": "Best AI Marketing Tools in 2026: Complete Guide (Under 60 chars)",
      "meta_description": "Discover the top AI marketing tools... (under 160 chars)",
      "target_keyword": "best ai marketing tools 2026",
      "secondary_keywords": ["ai marketing software", "ai seo tools"],
      "word_count": 2200,
      "outline": ["H1: ...", "H2: ...", "H3: ..."],
      "full_article_markdown": "# Full article text here...\n\n## Section 1\n\nComplete article body...",
      "internal_link_suggestions": [
        {"anchor_text": "our pricing", "target_page": "/pricing"}
      ],
      "external_citations": ["https://source1.com", "https://source2.com"],
      "schema_recommendation": "Article schema with author, datePublished",
      "featured_snippet_target": "what are the best ai marketing tools",
      "content_readiness_score": 8
    }
  ],
  "quick_wins": [
    {
      "topic": "Topic name",
      "keyword": "target keyword",
      "why_quick_win": "Low competition, high intent, matches existing page",
      "effort": "1-2 hours",
      "expected_ranking_timeframe": "2-4 weeks"
    }
  ],
  "pillar_content_map": {
    "pillar_topic": "AI Marketing",
    "pillar_page": "/ai-marketing-guide",
    "supporting_articles": ["topic1", "topic2", "topic3"],
    "internal_linking_strategy": "Each supporting article links to pillar, pillar links to all"
  }
}

Read the full file on GitHub · 93 lines

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. 3d ago First seen · 93 lines · 20 tokens per session scan A afc3d96942cd

Subscribe to this mod's changes

content-writer is an agent published in the GitHub repository michaelboeding/skills (24 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 910 once invoked, about $0.0001 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 2026-08-30.