SEO Agent Skill

Turn one natural-language request into an evidence-bounded SEO work plan across technical SEO, crawling and indexing, Search Console incidents, keyword-to-page mapping, migrations, experiments, international or ecommerce SEO, and AI-search foundations. Use for 一句话SEO、技术SEO、自然搜索、收录诊断、关键词页面映射 and website SEO. Exclude paid search, ASO, ranking guarantees, link spam, live mutation without authorization, and unsupported metrics.

4k tokens

context cost

the whole folder, loaded on every use

files

ships runnable scripts

copies elsewhere

how many repositories repackaged it

101

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/yaojingang/GEOHub --skill seo

What comes with it

12 396 bytes besides the instruction

agents/interface.yaml

evals/output/cases.jsonl

evals/semantic_config.json

evals/trigger_cases.json

manifest.json

references/input-example.json

references/seo-method.md

reports/output_quality_scorecard.md

reports/skill-ir.json

reports/trust-report.md

scripts/run_seo.py

The instruction itself

4 sections, as written by the author

GEOHub — One-line SEO

Workflow

Read references/seo-method.md and normalize the request into references/input-example.json shape.
Run python3 scripts/run_seo.py --input <brief.json> --output <runs-root> or python -m geo_seo_hub seo --input <brief.json> --output <runs-root>.
Use the selected work mode and action plan to collect the named evidence. Preserve the coverage ledger and rerun inputs.
State observations, inference, hypotheses, and missing evidence separately. The deterministic planner keeps findings empty; later analysis needs a separately validated evidence-backed contract.
Keep audit and planning read-only. Implement only when the user explicitly authorizes the target, change, verification, and rollback boundary.

Output contract

Return the normalized brief, seo-plan.json, a Markdown report, evidence ledger, quality report, and run manifest under one Artifact Bus run.

Boundaries

Never invent search volume, difficulty, rankings, traffic, backlinks, crawl, index, competitor, conversion, or citation metrics. Keep provider and surface rules separate. Crawling, indexing, ranking, rich results, traffic, revenue, and AI citations remain unguaranteed outcomes.

How to use it

Copy the folder

Take yaojingang/seo from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.