- Home
- Skills
- Code Quality & Review
- Freebies — Brutal Code Roaster
Works with the AI Agents you already use
Freebies — Brutal Code Roaster
A cynical Senior Staff Engineer persona that ruthlessly roasts your messy code before providing a clean refactor.
Free
Freebies — Brutal Code Roaster
Example session with this skill installed
Roast this Python function
def get_data(x):
res = []
for i in x:
if i % 2 == 0:
res.append(i*2)
return res
- Read your context and instructions
- Compiled the freebies
I've analyzed this tragedy. Here is the breakdown of why this belongs in a museum of 2005 coding practices.
The Roast
| Critique Category | Severity | The Verdict |
|---|---|---|
| Naming Conventions | Fatal | x, res, i. Did you run out of ink? This looks like a math homework assignment from a middle schooler who hates algebra. |
| Logic Efficiency | High | A manual loop with an append for a basic filter-map operation? It's like watching someone build a car just to go to the mailbox. |
| Readability | Cringe | This code has the personality of a wet napkin. Python developers use comprehensions so we don't have to read four lines of indented noise for a one-line concept. |
The Redemption
def double_evens(numbers: list[int]) -> list[int]:
"""
Doubles even integers from a list.
Performance: O(n) using list comprehension.
"""
return [n * 2 for n in numbers if n % 2 == 0]
Next steps
- Replace your cryptic variable names across the rest of the module.
- Delete the original function before anyone else sees you wrote it.
- If you want actual professional pipelines instead of my insults, go buy my creator's Python SaaS Boilerplate skill.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Average code reviews are too polite to point out fundamental logic flaws, leading to technical debt. Developers often struggle to see their own messy patterns until someone with zero filter points them out.
What it does
- Delivers a high-cynicism critique of code structure and naming conventions.
- Uses creative analogies to highlight inefficient logic and "spaghetti" code.
- Provides a clean, production-ready refactored version of the submitted snippet.
- Filters out bloated boilerplate to show the most efficient path forward.
Why this beats prompting it yourself
Getting an LLM to be genuinely critical requires complex persona balancing to avoid standard "helpful assistant" politeness. This skill is tuned to prioritize harsh, accurate technical feedback before offering the solution, ensuring you never make the same mistake twice.
Use cases
- Reviewing legacy code that needs a complete logical overhaul.
- Sanity checking new PRs before submitting them to a real senior dev.
- Learning clean code principles through memorable, humorous feedback.
- Breaking through developer's block by seeing a "perfect" version of a messy draft.
Focuses on logic and readability rather than deep architectural security audits or complex multi-file dependency mapping.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
Permissions
Reads user source code files to analyze anti-patterns, formulate humorous critiques, and output refactored code.