Revenue Centric Design
Product-design, conversion & behavioral-science principles for SaaS
Install
npx skills add heliocosta-dev/revenue-centric-designInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Revenue-Centric Design — an Agent Skill
A distilled, English-language playbook for designing SaaS & startup products that convert, retain, and monetize — packaged as an Agent Skill for Claude Code, Cursor, Codex, Copilot, Gemini, and any skills.sh-compatible agent.
134 principles distilled from the X/Twitter writing of Richard (@richardrx) — a product designer specializing in conversion-rate optimization, churn reduction, and applied behavioral science (ex-Volkswagen, ex-PayPal, ex-IBM). The throughline is his coined philosophy, Revenue-Centric Design (RCD): design should serve the user and the business — value and revenue, not one or the other.
Last updated: 3 September 2026 Coverage: @richardrx's curated posts from 3 Nov 2025 → 26 Aug 2026 (136 posts). Anything posted after this date is not yet included — see Updating.
Install
npx skills add heliocosta-dev/revenue-centric-design
This pulls the skill into your agent's skills directory (.claude/skills/, .agents/skills/, …) and works with any Agent Skills–compatible agent.
Already installed it? Pull the latest version with npx skills update revenue-centric-design (or a bare npx skills update to refresh every installed skill). The command re-fetches from GitHub; your agent picks up the new content on its next session.
Or install it manually:
git clone https://github.com/heliocosta-dev/revenue-centric-design.git ~/.claude/skills/revenue-centric-design
⚠️ Usage boundary
🚫 Not for betting, casino, or gambling products. The author granted permission to reuse this material on the explicit condition that it is never used for gambling/betting/casino work (including loot-box / real-money-gaming mechanics). The skill instructs agents to decline such requests. See LICENSE.
What's inside
The skill loads only the theme relevant to your question (progressive disclosure). Each principle follows a fixed shape — Principle → Apply when → The move → Evidence → Visual → Source — so your agent gets the named lever (decoy effect, Swiss Knife Index, GBB, Eugene Schwartz's awareness levels, loss aversion, peak-end rule…), the concrete action, and the proof.
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
