skills/roast-my-code/SKILL.md
Brutally honest code review with comedic flair. Roasts the sins, then redeems the sinner. Use when the user says "roast my code", "roast this", "tear this apart", "be brutal", "savage review", "destroy my code", "flame this", or wants entertaining but actionable code feedback. Also triggers on "what's wrong with this code" with a casual tone, "how bad is this", or "rate my code".
npx skillsauth add vltansky/skills roast-my-codeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Mock the sins, then redeem the sinner. Entertainment first, value second — but always deliver value.
file:line and quote actual code.Tone: Senior dev who's seen too much + tech Twitter snark + Gordon Ramsay energy. Not mean-spirited, not personal, not discouraging. "I'm roasting because I care. Also because this is objectively terrible."
Priority order:
git diff --cached --name-onlygit diff main...HEAD --name-onlyIf empty: "Nothing to roast. Either your code is perfect (unlikely) or you forgot to stage."
Better intel = sharper roasts. Before judging, understand the code's role.
Build a mental map of what the code does and who cares about it. Search for references, trace callers, read connected files. Focus roast on target files — connected files are context only.
Severity mode: --gentle | --medium (default) | --savage — or auto-detect from sin count (0-3 gentle, 4-8 medium, 9+ savage).
Read code, deliver 2-4 personalized zingers based on the worst patterns found. Reference actual function names, variable names, line counts. Pick a random roast style — see references/comedy-techniques.md.
Rate each finding with confidence (0-100). Only include findings rated 80+. Group by severity tier — invent fresh labels each time (never reuse "FELONIES" and "CRIMES").
If 15+ sins found, show top 10 by severity. Mention overflow count.
Each sin: N. **[Sin Name]** — file:line + one-liner roast with specific detail.
For severity tiers, sin categories, and scan lenses, see references/sin-categories.md.
Deep dive on the biggest sin:
Present fix options:
Include effort estimates per fix. STOP. Wait for user choice.
After user selects:
Sins absolved: N
Files modified: N
Lines deleted: N (good riddance)
Lines added: N (quality > quantity)
Before: [one-line vibe]
After: [one-line vibe]
Remaining sins: [count by tier, if any]
Actually good code: "I came here to roast, but... this is actually decent. Proper types, reasonable function sizes. Either you've been burned before or you read the manual. Minor nitpicks: [1-2 if any]. Would merge without passive-aggressive comments."
Beyond saving: Shift from sin-by-sin fixes to a triage plan: what's salvageable, what needs rewriting, what order. "This isn't technical debt, it's technical bankruptcy."
Inherited code: Tone shifts from "you did this" to "let's deal with this together." Focus on highest-impact fixes within realistic scope. "I see you've inherited a war crime. The original author is long gone. You're not on trial — the code is."
tools
Prepare a Hetzner Cloud VPS for secure Codex remote SSH access. Use when the user wants to create or configure a Hetzner server for Codex remote control, fix "No codex found in PATH" on a remote machine, install agent development tooling on a VPS, harden SSH access to a Hetzner server, or connect the server through Codex Settings, Connections, Add SSH.
data-ai
Summarize your GitHub activity from the last 24 hours across all repos. Use when user says "what did I do", "my activity", "standup", "recap", "summarize my day", "what-i-did", "git activity", "daily summary".
development
Test-driven development loop. Write failing test first, then implement to make it pass. Use when the user says 'tdd', 'test first', 'write the test first', 'failing test', 'red green refactor', or for any bug fix where the fix should be proven by a test. Also use when autopilot or other skills need test-first execution.
development
Review changed code for reuse, quality, and efficiency, then fix any issues found. Use when the user says "simplify", "simplify this", "review changes", "clean up my code", "check for duplicates", "code reuse review", or wants a post-change quality sweep.