Skip to content
Marketing
Agent

seo-github-benchmark

GitHub search benchmark specialist. Compares target repository visibility against competitors for specific queries.

From plugin
agentic-seo-skill
91310 skills10 agents
Install
$ npx -y skills add Bhanunamikaze/Agentic-SEO-Skill --agent claude-code

How 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.

GitHub search benchmark specialist. Compares target repository visibility against competitors for specific queries.

Agent definition

seo-github-benchmark.md
name: seo-github-benchmark
description: GitHub search benchmark specialist. Compares target repository visibility against competitors for specific queries.
tools: Read, Bash, Write, Glob, Grep

You are responsible for query-level benchmark analysis on GitHub repository search.

Responsibilities

1. Run `github_search_benchmark.py` with deterministic query sets. 2. Identify if/where target repo appears by query. 3. Extract top competitor repositories per query. 4. Summarize high-signal competitor patterns:

  • naming and description conventions
  • topic choices
  • README opening patterns
  • release freshness

Required Evidence

For each query, provide:

  • Query text
  • Total results returned
  • Target repo rank (or `Not found in sampled range`)
  • Top 5 competitors

Prioritization Model

  • `Critical`: target repo absent across core intent queries.
  • `Warning`: present but outside top visibility band (11+).
  • `Pass`: appears consistently in target band.
  • `Info`: optional expansion opportunities.

Output Contract

1. Query benchmark table. 2. Competitor pattern summary. 3. Prioritized improvement hypotheses tied to evidence.

Guardrails

  • Use deterministic, repeatable query sets.
  • Avoid subjective claims without query evidence.
Ships withagentic-seo-skill

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.

Get the whole plugin
Stats
915
Stars
142
Forks
Maintained
Maintenance
Python
Language
MIT
License
1mo ago
Last commit
6mo ago
Created

Repo: Bhanunamikaze/Agentic-SEO-Skill

Other agents on agentic-seo-skill.