Skip to content

feat(skills): add GEO interview and technical SEO audit skills#159

Open
sorcerai wants to merge 1 commit intoparalleldrive:mainfrom
sorcerai:feat/geo-seo-skills
Open

feat(skills): add GEO interview and technical SEO audit skills#159
sorcerai wants to merge 1 commit intoparalleldrive:mainfrom
sorcerai:feat/geo-seo-skills

Conversation

@sorcerai
Copy link

Summary

Two new AIDD skills for AI search visibility optimization — Generative Engine Optimization (GEO) and AI-aware Technical SEO.

  • aidd-geo-interview — Reflexive AI interview that measures share of voice, competitive positioning, and sentiment for a product/category. Generates fan-out queries across 9 categories (30+ templates), scores visibility on a 7-dimension GEO scale, and produces threshold-based recommendations (critical/high/medium actions).
  • aidd-technical-seo — 8-step technical SEO audit covering page speed (Core Web Vitals), header structure, meta tags, JSON-LD schema validation, AI crawler access (7 bots: GPTBot, ChatGPT-User, ClaudeBot, PerplexityBot, Google-Extended, Googlebot, Bingbot), fan-out query coverage analysis, and content quality (35 AI phrase patterns, readability, trust signals). Traffic-light scoring with P0/P1/P2 prioritization.

Key design decisions

  • Model-agnostic: Both skills work with any AI agent (Claude, GPT, Gemini, Llama, etc.) — no specific model required
  • No code execution: Pure markdown instructions, no external APIs needed
  • Reflexive interview: The GEO skill has the agent interview itself, producing genuine responses. Multi-model coverage is achieved by running the skill with different AI assistants.
  • Cross-referencing: Skills reference each other (/aidd-geo-interview/aidd-technical-seo) following the pattern used by existing skills like aidd-review → aidd-tdd
  • Reference files alongside SKILL.md: Each skill includes 2 reference docs (fan-out-queries.md, geo-scoring.md, seo-checklist.md, ai-crawler-audit.md) following the flat-file convention

Files added (9)

ai/skills/
├── aidd-geo-interview/
│   ├── SKILL.md              (158 lines)
│   ├── index.md
│   ├── fan-out-queries.md    (query template library)
│   └── geo-scoring.md        (scoring methodology)
├── aidd-technical-seo/
│   ├── SKILL.md              (234 lines)
│   ├── index.md
│   ├── seo-checklist.md      (43-item audit checklist)
│   └── ai-crawler-audit.md   (AI bot audit guide)
└── index.md                  (updated — 2 new entries)

Test plan

  • Read aidd-geo-interview/SKILL.md — verify scannable in 2-3 min, SudoLang syntax correct
  • Read aidd-technical-seo/SKILL.md — verify scannable in 2-3 min, SudoLang syntax correct
  • Verify frontmatter format matches existing skills (name, description fields)
  • Verify cross-references: /aidd-technical-seo from geo-interview, /aidd-geo-interview from technical-seo
  • Run geo-interview skill on a test product (e.g., "Follow aidd-geo-interview for product=Notion, category=project management software")
  • Run technical-seo skill on a test URL (e.g., "Follow aidd-technical-seo for url=https://notion.so")
  • Verify index.md entries are alphabetically sorted

🤖 Generated with Claude Code

Two new AIDD skills for AI search visibility optimization:

- aidd-geo-interview: Reflexive AI interview measuring share of voice,
  competitive positioning, sentiment analysis, and citation strategy.
  Includes fan-out query templates (9 categories, 30+ templates) and
  7-dimension GEO scoring methodology.

- aidd-technical-seo: 8-step technical SEO audit covering page speed,
  headers, meta tags, schema markup, AI crawler access (7 bots),
  fan-out coverage analysis, and content quality with traffic-light
  scoring. Includes 43-item checklist and AI crawler remediation guide.

Both skills are model-agnostic (work with any AI agent), require no
code execution or external APIs, and cross-reference each other.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant