onvoyage-ai/gtm-engineer-skills

Claude Code skill for improving website AEO (AI Engine Optimization) and GEO (Generative Engine Optimization) scores — 16 foundational checks, 6 intelligence dimensions, framework-specific fixes

What it solves

Search is evolving from traditional blue-link results to AI-driven answer engines like ChatGPT, Claude, and Google AI Overviews. This project provides a toolkit to help businesses optimize their online presence for these AI systems, ensuring content is discoverable, citable, and structured for AI parsing rather than just traditional search engine crawlers.

How it works

The repository contains a collection of modular agent skills that can be symlinked into agent frameworks like Claude Code or Codex. Each skill is a focused workflow—such as brand research, keyword analysis, or website auditing—that produces specific artifacts like brand DNA documents, content architectures, or code-level fixes. These skills are designed to be chained together into a pipeline where the output of one step provides the context for the next.

Who it’s for

This project is for GTM (Go-To-Market) operators, SEO professionals, and developers who need to adapt their marketing and web strategy to the rise of Generative AI search. It is particularly useful for those building or managing websites that need to be cited and surfaced by LLM-based search tools.

Highlights

  • Provides 12 specialized agent skills for tasks like brand research, content planning, and AEO (Answer Engine Optimization) auditing.
  • Includes deterministic scripts for technical tasks, such as a zero-dependency Node.js crawler for AEO checks.
  • Supports structured output formats like CSV and JSON-LD to ensure content is machine-readable.
  • Offers a modular design that allows users to pick and choose skills to integrate into their existing agentic workflows.
  • Grounded in industry research on how AI systems prioritize citations and structure.

Related

  • Project
    Ataraxy-Labs/weave

    weave is a Rust‑based Git merge driver that parses code with tree‑sitter and merges at the level of functions, classes, and other language entities, automatically resolving false conflicts that arise when multiple agents edit the same file.

  • Project
    lean-dojo/LeanCopilot

    Lean Copilot is an open‑source Lean 4 library that lets you call LLMs from within Lean to suggest tactics, search for proofs, and retrieve useful lemmas. It ships with small pre‑trained models (via CTranslate2) and a plug‑in system for any custom model, enabling neural‑assisted theorem proving directly in the Lean environment.

  • Project
    vshulcz/deja-vu

    deja-vu is a local, private memory engine for coding AI agents. It indexes transcripts from 41+ agent harnesses (Claude Code, Codex, Cursor, etc.), stripping secrets, and provides instant search, recall, and MCP integration so agents remember past fixes, commands, and file changes across sessions and tools. It features a fast CLI/TUI, proactive session-start recall, and benchmarks showing 97.2% R@5 on LongMemEval-S.

  • Project
    open-gsd/gsd-pi

    GSD Pi is a local‑first AI coding assistant that helps you plan, write, verify, and track software projects from the command line (or optional web UI). It organizes work into milestones, uses Git worktrees for isolated implementation, stores all project state in a hidden `.gsd/` folder, and supports any LLM provider (e.g., Claude, Cursor Agent). Install via `npx @opengsd/gsd-pi@latest`, run `gsd`, and use slash commands like `/gsd auto` or `/gsd quick "task"` to let the agent handle the work.