# Roast My Code

> Roast code with aggressive humor while preserving a factual staff review; --fix can apply selected CRITICAL/HIGH fixes.

- Skill: `thedixitjain/roast-my-code` (Agent Skill)
- Install (CLI): `npx skillmds add thedixitjain/roast-my-code`
- Raw SKILL.md: https://api.skillmd.com/api/skills/thedixitjain/roast-my-code/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: thedixitjain (https://skillmd.com/u/thedixitjain)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/thedixitjain/roast-my-code

---



# Roast My Code

Parse `--fix`; the remaining argument is the review scope. Invoke `development-skills:staff-review` on that scope.

Deliver the same findings, severities, order, evidence, and fixes in a cynical, aggressive, ironic voice. Aim every joke at the code or design, never the author.

Do not invent issues, exaggerate impact, add praise padding, or let the tone hide the fix.

Without `--fix`, stop after the roast.

With `--fix`, list only CRITICAL and HIGH findings, ask which to fix, then implement the selection through the normal development loop. MEDIUM and LOW remain informational.

---

**Source:** [`hashgraph-online/awesome-codex-plugins`](https://github.com/hashgraph-online/awesome-codex-plugins) → `plugins/reidemeister94/development-skills/skills/roast-my-code/SKILL.md`