For the complete documentation index, see llms.txt. Markdown variants are available by appending .md to any URL or sending an Accept: text/markdown header. An agent skill is available at /.well-known/agent-skills/site-skill.md.
255
Sponsor

AI SEO Audit

PreviousNext

Fetches a page through context.dev and scores its readability to AI answer engines, returning failing checks and an agent-ready fix prompt.

EveFlue

Output will stream here when you run the agent.

Summary

The AI SEO Audit Agent evaluates a page for how readable it is to AI answer engines — ChatGPT, Claude, and Perplexity — rather than classic blue-link search. It fetches the page through context.dev (never touching the site directly), scores six categories to a 0–100 total, lists the failing checks by impact, and returns an agent-ready fix prompt you can paste straight into a coding agent. Reach for it when you want a page to get cited by AI assistants.

Installation

$ pnpm dlx shadcn@latest add @agentcn/eve/ai-seo-audit

Composition

agent/
├── agent.ts              # Agent definition (model + config)
├── instructions.md       # Audit-and-report instructions
├── tools/
│   └── fetch_page.ts     # Page Markdown + HTML via the context.dev SDK
└── skills/
    └── seo-audit/
        └── SKILL.md      # Six-category rubric and scoring bands

Customization

  • Fetching. The page is fetched through context.dev — the recipe never hits the audited site directly. Set CONTEXT_DEV_API_KEY.
  • Tune the rubric. Edit agent/skills/seo-audit/SKILL.md to add checks, reweight categories, or change the scoring bands.
  • Reshape the output. Edit agent/instructions.md to emit JSON, a shorter summary, or a different fix-prompt format.
  • Swap the model. Edit agent/agent.ts — anthropic/claude-sonnet-4-6 for deeper analysis, anthropic/claude-haiku-4-5 for speed.