ForkFree

Agent skills and plugins

ai-marketing-panel

by rodaddy

An agent skill kit for Claude or Codex that builds a panel of researched customer composites from your own evidence, such as support tickets, sales calls and reviews. Each composite reacts separately to a landing page, price or email, and you get back a synthesis and a scored verdict.

Worth a lookEstablished, with a few things to check (listed below).

View on GitHub

Stars
56
Licence
MIT
Runs on
Your computer
Setup
Moderate
Language
TypeScript
Age
67 days

What you can do with it

  • Test a landing page, price or email against five to fifteen researched customer composites before launch
  • Get separate reactions, a synthesis that keeps disagreements, and a weighted score with three suggested rewrites
  • Record predictions and later real outcomes to check how well the panel's verdicts match reality

Make money with it

A freelance copywriter or marketing consultant could offer a pre-launch copy and pricing review, using the panel's findings as part of the deliverable.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Check landing page copy, pricing and email subject lines before launch, instead of paying for a commissioned focus group
  • Give clients a structured critique of their marketing drafts as part of a copywriting or consulting service

Can you use it commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

Getting it running

Clone the repository, check you have Node 22.18 or later, then drag the zipped kit into the Claude app or point Codex at the folder.

Follow the official instructions in the project README.

Things to check

  • Needs a Claude or Codex subscription or model usage, which costs money
  • Results are from simulated composites, not real customers, so treat them as directional only
  • Cost and time savings figures in the README are unmeasured estimates
  • Web chat use is unverified and loses the script-enforced checks

Who's talking about it

Checked 29 Oct 2026. Summary drafted by AI from the project's README.

More in Agent skills and plugins

security-audit-skill cloudflare
Worth a look

A skill for coding agents that runs a structured, multi-phase security audit of a codebase. It uses separate agents to find, challenge and verify vulnerabilities, then writes the results as machine-readable records and readable reports.

53.3k stars +1411 a day MIT
ub-mode unclebob
Check the licence

ub-mode is a skill file for AI coding agents that makes them follow strict software engineering habits, such as test-driven development, low complexity and no duplicated code. It works alongside separate checking tools that measure complexity, duplication and test strength.

5k stars +1033 a day Unclear
skills anthropics
Check the licence

This is Anthropic's public collection of example Agent Skills, which are folders of instructions and scripts that Claude loads to handle specialised tasks in a repeatable way. It covers areas such as documents, design, development and communications, and includes a template and the skills specification.

184.6k stars +231 a day Unclear