# seo-geo-claude-skills

> 20 SEO & GEO skills for Claude Code, Cursor, Codex, and 35+ AI agents. Keyword research, content writing, technical audits, rank tracking. CORE-EEAT + CITE frameworks.

- **URL**: https://www.freshcrate.ai/projects/seo-geo-claude-skills
- **Author**: aaron-he-zhu
- **Category**: AI Agents
- **Latest version**: `v9.9.10` (2026-06-05)
- **License**: Apache-2.0
- **Source**: https://github.com/aaron-he-zhu/seo-geo-claude-skills
- **Homepage**: https://skills.sh/aaron-he-zhu/seo-geo-claude-skills
- **Language**: Shell
- **GitHub**: 1,117 stars, 163 forks
- **Registry**: github
- **Tags**: `agent-skills`, `ai-skills`, `claude-code`, `claude-skills`, `content-optimization`, `generative-engine-optimization`, `geo`, `marketing`, `python`

## Description

20 SEO & GEO skills for Claude Code, Cursor, Codex, and 35+ AI agents. Keyword research, content writing, technical audits, rank tracking. CORE-EEAT + CITE frameworks.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v9.9.10` | 2026-06-05 | High | **20 skills + 5 commands**, zero external-tool dependency. This release refocuses the library on the skills themselves and removes non-user-facing maintenance/process scaffolding.  ## Highlights  - **Command surface 17 → 5** *(breaking)*: `/aaron:auto`, `/aaron:research`, `/aaron:create`, `/aaron:audit`, `/aaron:track` (former `max` → `auto --deep`; mode flags like `--meta` / `--schema` / `--alert` / `--report` preserved). Paste any old `/seo:*` or prior command into `/aaron:auto` to recover its |
| `v9.9.9` | 2026-05-14 | High | Final 9.x release. Consolidates the entire post-v9.0.0 development line into a single shipment. **Upgrade directly from v9.0.0 to v9.9.9** — interim tags (v9.5.0, v9.9.0, v9.9.5) and the v10.x exploratory line have been retired and folded into this release.  ## Acknowledgements  External contributor credit for work landed during the v9.x cycle: - **@xiaolai** ([PR #10](https://github.com/aaron-he-zhu/seo-geo-claude-skills/pull/10)): `fix(contract-lint): add allowed-tools to enable hash verificat |
| `v9.9.5` | 2026-04-28 | High | ## Added - Added `/seo:skillify` as a read-only authoring workflow for skill completeness, routing, eval, and release-readiness proposals. - Added `references/skill-resolver.md` as a derived review index covering all 20 skills without becoming a runtime routing source of truth. - Added compatible routing eval seeds under existing skill eval suites using `type: eval-case`, `target_skill`, and `expected_behavior`.  ## Changed - Synchronized the public bundle to `9.9.5` across skill frontmatter, ma |
| `v9.1.0` | 2026-04-23 | High | ## Summary  Library-wide compression: 37,129 → 24,587 lines (-34%). All 20 skills and 15 commands preserved, no breaking changes.  ## What changed  - **SKILL.md files** (-20%): removed redundant boilerplate (When This Must Trigger, Validation Checkpoints, verbose Data Sources), preserved Quick Start + Instructions + Skill Contract - **Reference files** (-49%): compressed generic knowledge (robots-txt, http-status-codes, KPI definitions) to SEO-essential content; trimmed templates and process doc |
| `v9.0.1` | 2026-04-17 | High | ## 🛠 Patch: neutralize literal injection example in `/seo:geo-drift-check`  ClawHub's OpenClaw scanner flagged published **v9.0.0 as Suspicious (medium confidence)** — single hit on `commands/geo-drift-check.md:48`. The flagged line was a *defensive* warning block teaching the model to distrust AI-engine output, but its example text was an actual override-style directive. Under regex-only scanning, the literal example was indistinguishable from a real injection attempt.  ### What changed  - `co |
| `v9.0.0` | 2026-04-17 | High | Major release combining four streams of work:  1. **Multi-sprint quality pass** — legal/compliance hardening, 10 new playbooks, SKILL.md size compliance, memory scaffolding, i18n 2. **Native install for 5 more AI coding agents** — Gemini CLI, Qwen Code, Amp, Kimi Code CLI, CodeBuddy 3. **New experimental `/seo:geo-drift-check` command** — validates GEO Score against actual AI-engine citations (T+14/T+45/T+90 protocol) 4. **Zero-`.py` design philosophy enforced** — dev utilities now pure-markdown |
| `v8.0.0` | 2026-04-14 | High | ## v8.0.0 — Unified Version Release  Unifies all 20 skill versions to 8.0.0. Consolidates v7.0.0 (Wiki Knowledge Layer) and v7.1.0 (Auditor Runbook Inline Strategy) into a single coherent release.  ### Highlights  - **All 20 skills at 8.0.0** — no more split versions across research/build/optimize/monitor/cross-cutting - **Wiki Knowledge Layer** — auto-refreshed structured index (`memory/wiki/`), project isolation, `/seo:wiki-lint` - **Auditor Runbook** — single source of truth for handoff schem |
| `v7.0.0` | 2026-04-06 | High | ## Wiki Knowledge Layer + Infrastructure Upgrades  Major release adding a wiki compilation layer for cross-skill knowledge synthesis, inspired by [Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f). Consolidates all changes since v6.0.0.  ### Wiki Layer Highlights  - **Structured index** (`memory/wiki/index.md`) — auto-refreshed compiled index with precise fields (score, 健康度, status, next_action, mtime) - **Project isolation** — `memory/wiki/<project> |
| `v6.0.0` | 2026-03-31 | Medium | ## What's New in v6.0.0  Consolidates v5.1.0, v5.2.0, and v5.2.1 into a single major release. All 20 skills updated to 6.0.0.  ### Multilingual Triggers - **750+ triggers** across EN, ZH, JA, KO, ES, PT for all 20 skills - Optimized for ClawHub and skills.sh marketplace discovery  ### Shared Contract Upgrades - **Completion Status Protocol** — `DONE` / `DONE_WITH_CONCERNS` / `BLOCKED` / `NEEDS_INPUT` - **Escalation Protocol** — 3-fails → BLOCK; structured report format - **Anti-Slop Output Voice |
| `v5.0.0` | 2026-03-29 | Medium | ## What's New  Upgrades the library from 20 standalone skills into one shared operating system with automatic cross-skill coordination, persistent state, and protocol gates.  ### Hook Automation - **4 prompt-based hooks** covering the full session lifecycle (SessionStart, UserPromptSubmit, PostToolUse, Stop) - Session start auto-loads project memory; session end offers to save findings - Content writing auto-triggers a quality audit recommendation - Veto-level issues auto-save to hot cache — no |

## Citation

- HTML: https://www.freshcrate.ai/projects/seo-geo-claude-skills
- Markdown: https://www.freshcrate.ai/projects/seo-geo-claude-skills.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/seo-geo-claude-skills/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._