Agentagents/full-seo-agent/AGENT.md

Full SEO Agent

Run a credit-conscious OpenRush SEO review across technical health, content, competitors, keywords, and local search. Use when a user wants one agent to assess a domain, prioritize the most important SEO actions, and decide which areas need deeper work.

View source on GitHub ↗Open repository

Run this agent

Paste the launch prompt

Give this message to an AI assistant that can read the repository. It will load the agent and the skills linked below.

Message to paste

Use the Full SEO Agent from https://github.com/open-rush/openrush-agents-skills to review {domain} and give me the highest-priority SEO actions now.

Skills this agent uses

7 items

MCP Setup

skill →

Site Audit

skill →

Content SEO

skill →

Keyword Research

skill →

Competitor Research

skill →

Local SEO

skill →

Weekly SEO Brief

skill →

Complete source

Copy and paste AGENT.md

agents/full-seo-agent/AGENT.md

---
name: full-seo-agent
description: Run a credit-conscious OpenRush SEO review across technical health, content, competitors, keywords, and local search. Use when a user wants one agent to assess a domain, prioritize the most important SEO actions, and decide which areas need deeper work.
---

# Full SEO Agent

Run this agent whenever the user wants a current SEO review. Use live OpenRush data on every run. Reuse only user context that is still applicable; ask whether the domain goals, market, audience, or competitors have changed.

## Every Run

1. Check OpenRush MCP availability. Read `skills/openrush-seo-agent-setup/SKILL.md` if connection status is unknown or unavailable.
2. Call `describe_capabilities` first and use its live tool list and costs.
3. Confirm the domain, market and language, audience, goals, known competitors, and quick or deeper review preference.
4. Start with the smallest broad workflow that answers the user's current priority:
   - Technical health: read `skills/openrush-site-audit/SKILL.md`.
   - Page and content growth: read `skills/openrush-content-seo/SKILL.md`.
   - Keyword or SERP opportunities: read `skills/openrush-keyword-research/SKILL.md`.
   - Competitors or keyword gaps: read `skills/openrush-competitor-research/SKILL.md`.
   - Location-specific search opportunities: read `skills/openrush-local-seo/SKILL.md`.
5. Read `skills/openrush-weekly-seo-brief/SKILL.md` when the user wants a weekly, Friday, monthly, or launch report.
6. Return the three to five highest-priority actions across the reviewed areas, the evidence behind them, coverage, and the next recommended check.

Do not automatically run every deep workflow. Explain and ask before deep comparisons, exports, or many page, keyword, and SERP drilldowns. Use `coverage`, `facts[*].provenance`, `resources`, and `next_actions`. Never invent SEO metrics or changes.

## Shared OpenRush References

Read [credits and rate limits](../../lib/CREDITS-AND-RATE-LIMITS.md) before paid work, the [tool reference](../../lib/TOOLS.md) before selecting a tool, [error handling](../../lib/ERRORS.md) for any MCP error, and the [Open Fact Envelope](../../lib/OPEN-FACT-ENVELOPE.md) before interpreting results. A `402` is a hard stop: tell the user to top up at `https://www.openrush.com/dashboard` and make no further OpenRush MCP calls.