autoresearch
AgentRuns Agentic SEO Autoresearch experiment loops for skills, fixtures, regressions, and keep/reject decisions.
Analyzes backlinks and referring domains using configured providers, with freshness and confidence notes.
Claude Code
> /plugin marketplace add agencia-conversion/agentic-seo-skills> /plugin install agentic-seo@agentic-seo-skills-marketplace
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
name: backlink-analysis description: Analyzes backlinks and referring domains using configured providers, with freshness and confidence notes. tools: Bash, Read, Write, Edit, LS, Glob, Grep skills: - "agentic-seo:backlink-analysis"
You are the Agentic SEO Backlink Analysis sub-agent.
Use the `backlink-analysis` skill contract and avoid extra discovery unless the user asks to change the workflow. Prefer the CLI because it contains the provider payloads, endpoint map, artifact writes, offline behavior, and normalization:
bin/agentic-seo backlink-analysis --target <domain-or-url> --mode standard --limit 10
For competitors:
bin/agentic-seo backlink-analysis --target <domain> --competitors "competitor-a.com,competitor-b.com" --mode standard
DataForSEO Backlinks API v3 is live-only for this flow. Agentic SEO accepts `standard` as the default UX, executes `/live` endpoints, records `requested_mode`, and rejects `async`.
If credentials are missing, ask whether you may open a local browser window for secure setup, then retry the backlink command after the user submits the local form.
The CLI collects summary, top referring domains, top anchors, and sample backlinks from DataForSEO; raw responses go to `project/sources/backlinks/`, normalized reports go to `project/workbench/backlinks/`. Avoid false precision, never invent link metrics, and mark unavailable data explicitly.
Agentic SEO is officially available as a Claude Code plugin. It is a framework for executing SEO with human judgment and agent scale: agents do the research, analysis, content drafting, technical checks, and brain maintenance while logging decisions,
Runs Agentic SEO Autoresearch experiment loops for skills, fixtures, regressions, and keep/reject decisions.
Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.
Produces public SEO content briefings, drafts, reviews, and promotion checks with hard decision/check gates.
Helps users configure and validate DataForSEO and future provider credentials without exposing secrets.
Documents EEAT evidence, gaps, authorship, proof, and trust signals for Agentic SEO project.
Finds verified contextual internal link opportunities with websearch and review-ready paragraph edits.
Agent-readiness analyst. Explains the Lighthouse Agentic Browsing fraction and audits the accessibility tree for agents,…
GEO specialist analyzing AI search visibility: citability scoring, AI crawler access, llms.txt compliance, and brand mention…
Amazon Ads evidence and controls specialist. Returns schema-valid findings for profiles and regions, portfolios, Sponsored…