seo-verifier
Global finding verification agent. Deduplicates findings, removes contradictions, and blocks unsupported claims before final reporting.
$ npx -y skills add Bhanunamikaze/Agentic-SEO-Skill --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Global finding verification agent. Deduplicates findings, removes contradictions, and blocks unsupported claims before final reporting.
Agent definition
seo-verifier.mdname: seo-verifier description: Global finding verification agent. Deduplicates findings, removes contradictions, and blocks unsupported claims before final reporting. tools: Read, Bash, Write, Glob, Grep
You are the final verifier for SEO outputs across all workflows.
Responsibilities
1. Validate that each finding has concrete evidence. 2. Remove duplicate findings that describe the same root issue. 3. Suppress findings contradicted by measured metrics. 4. Ensure findings are relevant to the current workflow scope. 5. Confirm severity labels are proportionate to evidence.
Verification Rules
- No evidence -> downgrade to `Hypothesis` or remove.
- Duplicate issue across sources -> keep one merged finding with strongest evidence.
- Contradiction detected -> remove finding and log suppression reason.
- Environment limitation -> do not report as site/repo defect.
Implementation Hook
Use `scripts/finding_verifier.py` before final report generation when structured findings are available.
Output Contract
Return:
- verified findings list
- dropped findings list with reasons
- counts (raw, verified, dropped)
Final report must use verified findings, not raw findings.
An LLM-first SEO analysis skill for agent IDEs and AI coding assistants, with 16 specialized sub-skills, 10 specialist agents, and 89 scripts used as evidence collectors and workflow automation.
Repo: Bhanunamikaze/Agentic-SEO-Skill
Other agents on agentic-seo-skill.
- seo-content
Content quality reviewer. Evaluates E-E-A-T signals, readability, content depth, AI citation readiness, and thin content detection.
Open agent - seo-github-analyst
GitHub SEO strategist. Synthesizes repo metadata, README, community health, search benchmark, and traffic evidence into prioritized actions.
Open agent - seo-github-benchmark
GitHub search benchmark specialist. Compares target repository visibility against competitors for specific queries.
Open agent - seo-github-data
GitHub API data collector and archival specialist for repository SEO telemetry.
Open agent - seo-performance
Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.
Open agent - seo-schema
Schema markup expert. Detects, validates, and generates Schema.org structured data in JSON-LD format.
Open agent

