SEO & GEO Skills Library

20 skills. 20 commands. Plan, audit, and monitor SEO/GEO work.

English | 中文

Claude Skills and Commands for Search Engine Optimization (SEO) and Generative Engine Optimization (GEO). This repository is the candidate SEO/GEO anchor capability pack for slash-aaron. Skill content is zero-dependency Markdown; Claude Code hooks use a small Bash runner. Install targets and support claims are maintained in the Marketplace Module and platform registry. Content quality uses CORE-EEAT (80 items); domain trust uses CITE (40 items).

Quick Start

Common install paths are below. Support level, evidence, manifest ownership, and release rules live in marketplaces/README.md and distribution/platforms.json.

Tool	Install
Claude Code	/plugin marketplace add aaron-he-zhu/seo-geo-claude-skills
ClawHub.ai / OpenClaw	clawhub install aaron-he-zhu/<skill> or bundle
Gemini CLI	gemini extensions install https://github.com/aaron-he-zhu/seo-geo-claude-skills
Qwen Code	qwen extensions install https://github.com/aaron-he-zhu/seo-geo-claude-skills
Amp	amp skill add aaron-he-zhu/seo-geo-claude-skills
Kimi Code CLI	kimi plugin install https://github.com/aaron-he-zhu/seo-geo-claude-skills.git
CodeBuddy	/plugin marketplace add aaron-he-zhu/seo-geo-claude-skills then /plugin install aaron-seo-geo
skills.sh / generic Agent Skills hosts	npx skills add aaron-he-zhu/seo-geo-claude-skills

Single skill: npx skills add aaron-he-zhu/seo-geo-claude-skills -s keyword-research.

If your host supports automatic skill routing, try a natural-language request:

Research keywords for my SaaS product targeting small teams

Slash-command entrypoint when your host exposes ./commands/:

/aaron:auto audit https://example.com/blog/my-article

Optional tools are documented in CONNECTORS.md; every skill also works at Tier 1 with user-provided data.

Operating Model

Every skill follows the same activation contract: Quick Start, Skill Contract, Handoff Summary, Data Sources, Instructions, Reference Materials, and Next Best Skill. Four cross-cutting skills form the protocol layer:

Protocol skill	Role
content-quality-auditor	80-item CORE-EEAT publish gate
domain-authority-auditor	40-item CITE trust gate
entity-optimizer	Canonical entity profile
memory-management	HOT/WARM/COLD project memory + wiki layer (compile · query · contradiction-resolution · retire · restore; v9.9.9+)

Shared refs: skill-contract.md, state-model.md, auditor-runbook.md.

Wiki Layer (v9.9.9+)

Project memory matures from raw WARM files → derived wiki pages → optional retirement of covered WARM into COLD. Three phases:

• Phase 1 — auto-refreshed memory/wiki/index.md (Phase 1 is automatic; no user action needed)
• Phase 2 — compiled wiki pages: type "compile a wiki page on X" / "synthesize what we know about X" / "整理一下X的资料" once you have ≥3 WARM files referencing entity X. Contradictions surface at next session as (a)/(b)/(s)/(i) prompt.
• Phase 3 — user-initiated retirement: /aaron:guard --wiki --retire-preview lists candidates; explicit confirmation moves WARM to memory/archive/. Recover any time by saying /aaron:remember recover wiki (memory-management runs the recovery for you). Power users can also bash scripts/recover-retired-warm.sh directly.

rm -rf memory/wiki/ always reverts cleanly. Retirement history (Phase 3) survives in COLD frontmatter — not destroyed by wiki deletion.