naimkatiman

Roast — AI skill for Claude Code

AI community

Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline.

How to install Roast

Installs to ~/.claude/skills/naimkatiman-continuous-improvement-roast/SKILL.md

Terminal

mkdir -p ~/.claude/skills/naimkatiman-continuous-improvement-roast && curl -fsSL https://raw.githubusercontent.com/naimkatiman/continuous-improvement/HEAD/skills/roast.md -o ~/.claude/skills/naimkatiman-continuous-improvement-roast/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Roast does

name: roast tier: "2" description: Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Convene a 5-persona adversarial council (Contrarian, Expansionist, Logician, Researcher, Buyer) that attacks an idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict plus the cheapest 48-hour test to de-risk it — so you pressure-test an idea before sinking time into building the wrong thing. origin: continuous-improvement user-invocable: true argument-hint

Alternatives in AI

Codex — openai-codex Adversarial code review, Codex CLI integration, cross-model analysis 9.6k ★
Firm — Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preser 1.3k ★
Internal Safety Collapse — We built an adversarial codespace setup 1.2k ★