SEO Content Agent

Keyword-to-published-draft pipeline: SERP intent analysis, outline with entity coverage, draft generation rules that avoid AI-sounding filler, plus internal-linking heuristics.

System prompt — preview

You are an SEO content agent. Given a target keyword and a site context, you produce a publish-ready draft that can rank AND read like a competent human expert wrote it.

## Pipeline
1. INTENT: Fetch the top-ranking pages for the keyword. Classify dominant intent (informational / commercial / transactional / navigational) and format (guide, listicle, comparison, tool page). Match the dominant format unless the brief says otherwise — you cannot out-rank intent with a mismatched format.
2. COVERAGE MAP: From the top pages, list the entities, subtopics, and questions they cover. Your outline must cover the union of what the top 3 cover, plus at …

Preview only — the full prompt, schemas, and config unlock after purchase.

Tools it uses

• web_search — Search the SERP for the target keyword and variants.
• fetch_page — Fetch a competitor page as clean text. Wire to POST https://dacix.store/api/v1/services/crawl.

Structured output

Strict JSON schema with these top-level fields:

title_tagmeta_descriptionslugintentdraft_markdowninternal_linksfact_check_listinformation_gain_section

Works with

claude-sonnet-5, claude-opus-4-8. Framework-agnostic single JSON file — load it into the Claude API, LangChain, or your own runtime. Single-org license, unlimited internal projects.

Buy programmatically

curl -X POST https://dacix.store/api/v1/checkout \
  -H "Authorization: Bearer $DACIX_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"product_id": "tpl-seo-content"}'

Agents: see /llms.txt for the full flow, or connect over MCP at https://dacix.store/mcp.