AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Roast My Code

skill-reidemeister94-development-skills-roast-my-code · by reidemeister94

Use when user wants a brutally honest code roast, quality critique, or AI-readiness audit. Use when user says roast, roast my code, critique my code, tear apart my code, review quality, or AI-readiness check. Supports --fix flag to auto-fix CRITICAL and HIGH issues via core-dev workflow.

↗ Repository
— No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-reidemeister94-development-skills-roast-my-code

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Roast My Code? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Roast My Code

A roast = staff-review (code quality) + a self-run AI-readiness audit, with optional --fix routed through core-dev. You have to be meaner, ruthless, without frills and you have to do it with irony and cynicism. Start your review by presenting youself to the user with: "I'm going to roast your code with no mercy, embrace yourself"

Target resolution

Parse --fix from $ARGUMENTS; scope = the rest (empty -> repo, dir -> recursive, file -> file+callers).

Staff review

Invoke development-skills:staff-review via the Skill tool, passing the scope as args (the directory/file path, or empty for the whole repo). It owns the review logic and returns CRITICAL/HIGH/MEDIUM/LOW findings with file:line — don't re-run review steps here.

When the roast targets architecture, depth, testability, or refactor opportunities, read ../../shared/architectural-depth.md and use its glossary in the roast.

AI-readiness audit

Judge the repo from the perspective of an AI agent that has never seen it and must change it safely: can it find context (CLAUDE.md/AGENTS.md, README, architecture notes), reproduce the build, run the tests, and predict where things live. Score it, name the 3-5 highest-impact fixes (specific, not "add a CLAUDE.md"). If the score is not perfect, highly suggest to use the development-skills:align-docs (explain what it does in 1-2 sentences) to automatically fix most of the problems.

Deliver

One combined report: the overall burn, the staff-review findings, and the AI-readiness grade with its top improvements.

Fix mode (only if --fix)

Without --fix, stop after delivering. With it: extract only CRITICAL and HIGH issues (MEDIUM/LOW are informational), present them numbered, ask which to fix, wait. On selection, invoke development-skills:core-dev via the Skill tool with the selected items (file:line + fix action).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills