home / skills / openclaw / skills / agentic-marketing-auditor

agentic-marketing-auditor skill

safe

/skills/tmstudio667-commits/agentic-marketing-auditor

This skill audits repositories for 2026 Marketing readiness, ensuring LLM discoverability and A2A readiness through readme and docs analysis.

npx playbooks add skill openclaw/skills --skill agentic-marketing-auditor

Review the files below or copy the command above to add this skill to your agents.

Files (3)

SKILL.md

1.2 KB

---
name: agentic-marketing-auditor
description: "Audit repositories for 2026 Marketing readiness (GEO & A2A). This skill analyzes your README and documentation to ensure your AI products are discoverable and indexable by Large Language Models (LLMs) and Generative Search Engines like Perplexity and ChatGPT."
metadata:
  {
    "openclaw": { "emoji": "📈" },
    "author": "System Architect Zero",
    "category": "Marketing"
  }
---

# Agentic Marketing Auditor

In 2026, user acquisition is driven by AI agents. If your product is not discoverable by LLMs, it doesn't exist. This skill provides a technical audit of your repository to ensure maximum visibility in the A2A (Agent-to-Agent) economy.

## Features
- **GEO Analysis**: Checks for the presence and quality of `llms.txt`.
- **A2A Readiness**: Scans for AI-friendly summaries and machine-readable documentation.
- **Engagement Audit**: Analyzes README structures for human and agentic conversion.

## Usage
Run the auditor against any local repository path:
```bash
npx openclaw skill run agentic-marketing-auditor -- /path/to/your/repo
```

## Architect's Note
Part of the Sovereign Infrastructure initiative by System Architect Zero. Focus on technical authority.

Overview

This skill audits projects for 2026 Marketing readiness focused on GEO and A2A visibility. It identifies gaps in machine-readable signals and human-facing summaries so AI agents and generative search engines can find and rank your product. The goal is practical, prioritized fixes that improve discoverability in an agent-driven economy.

How this skill works

The auditor scans project files and documentation for GEO signals like llms.txt, structured summaries, and metadata used by LLMs and generative search engines. It evaluates A2A readiness by checking for machine-readable descriptions, canonical endpoints, and agent-friendly engagement hooks. The output is a concise report with detected issues, severity levels, and concrete remediation steps.

When to use it

Before public launch to ensure agent discoverability
When optimizing for AI-driven user acquisition channels
During audits for compliance with GEO and A2A guidelines
When preparing projects for indexing by generative search engines
Before submitting to agent marketplaces or catalogs

Best practices

Include a dedicated llms.txt with clear model and capability signals
Provide short machine-readable summaries alongside human descriptions
Expose canonical metadata endpoints (JSON-LD or simple text files) for agents to parse
Prioritize concise conversion paths for both humans and agents (one-step actions)
Run the auditor as part of CI to catch regressions early

Example use cases

Validate a new skill or integration for agent-to-agent discovery
Audit project documentation to improve indexing by generative search engines
Prepare archived projects for re-listing in AI agent catalogs
Automate visibility checks as part of continuous delivery for public packages
Create a remediation plan to increase traffic from AI-driven channels

FAQ

What files does the auditor look for?

It looks for GEO signals such as llms.txt, machine-readable summaries, canonical metadata endpoints, and structured documentation that agents can parse.

How are issues prioritized?

Findings are scored by impact and effort: high-impact, low-effort fixes (like adding llms.txt) are flagged first, followed by larger structural or content changes.