What does the Marius skill do?

Make it fast for real: profile the hot path, fix the true bottleneck, load-test it, and prove the gain. Load it once into Claude Projects and you get a configured Performance Engineer without re-explaining context at the start of every session. Test changes in a branch or staging environment, run the tests, and verify against your own stack, versions, and load before shipping to production.

How do I install this skill file?

Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.

Which AI tools does this skill work with?

Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.

What is included in this download?

One .skill package delivered instantly after purchase: the full SKILL.md role configuration plus a worked-example file with a real scenario so you see the quality before you rely on it. No subscription, yours permanently.

How is this different from using Claude without the Marius skill?

Without a skill file your AI starts every session as a general assistant. With Marius loaded it applies Performance Engineer methodology from the first message, with consistent quality every time. Test changes in a branch or staging environment, run the tests, and verify against your own stack, versions, and load before shipping to production.

Performance Engineer AI Skill for Claude & ChatGPT

Name: Marius — Performance Engineer AI Skill
Brand: KissMySkills
Price: 14.99 USD
Availability: InStock

Marius — Performance Engineer AI Skill

$14.99

Marius — Performance Engineer AI Skill

$14.99 this skill vs $130+/hr, hiring one

⚡ Instant download ◆ Claude & ChatGPT ∞ Keep forever

Instant download · 30-day money-back guarantee. Pay once, keep forever — no subscription. Refund policy

Make it fast for real: profile the hot path, fix the true bottleneck, load-test it, and prove the gain.

CPU/memory profiling and flame graphs
Latency, throughput, and tail-latency (p95/p99)
Load and stress testing (k6, JMeter, Locust)
Caching strategy and app-layer query tuning

Teams with a slow or expensive service who want the real bottleneck found and fixed, not guesswork.A senior performance engineer bills $130+/hr, this is one file, yours forever.

// what's inside

Drop Marius into Claude and get a senior performance engineer who measures before he changes anything and fixes the bottleneck that actually matters.

Marius makes software fast: CPU and memory profiling, flame graphs, latency and throughput analysis, tail-latency (p95/p99), load and stress testing (k6, JMeter, Locust), capacity planning, caching strategy, and application-layer database and query tuning. He refuses to optimize on a hunch: he profiles, finds the hot path, fixes it, and measures the result. He knows that the slow part is rarely where you first think it is.

What you get

→CPU/memory profiling and flame graphs
→Latency, throughput, and tail-latency (p95/p99)
→Load and stress testing (k6, JMeter, Locust)
→Caching strategy and app-layer query tuning

📄 marius-performance-engineer.skill Under 2 min install Works with Claude, ChatGPT & any AI chat

How to install

Download the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Marius builds the answer. Includes a full worked example so you see exactly what you get.

marius-performance-engineer.skill

# Marius - Performance Engineer

You are Marius, a senior Performance Engineer. You measure before you change anything and fix the bottleneck that actually matters.

## How you work
1. Reproduce and measure; capture a profile and a baseline
2. Find the true hot path (it is rarely the obvious one)
3. Fix the biggest cost first; change one thing at a time
4. Load-test and prove the gain against the baseline

Never optimize on a hunch. A change without a measurement is not a fix.

Excerpt from the actual file you'll download.

// try it

prompt

$Our API p99 latency is terrible under load. Find the bottleneck and give me a plan to fix it.

Marius returns a profiling plan and what to capture, the likely hot path from the symptoms, a load-test design with a clear pass/fail, the specific fixes ranked by impact, and a before/after on p95/p99 with the levers pulled.

// how to install Under 2 minutes

Four steps. Any AI chat.

01
Download the file
After checkout, the download link lands in your inbox. Save the file anywhere on your device.
02
Open your AI chat
Claude, ChatGPT, Gemini, Grok, or Copilot — whichever one you already use.
03
Paste the file contents
Drop it into the system prompt, Project instructions, or custom instructions field.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.