This Is Why You Should Build Your Own Claude Code Skills
The speaker explains why they build their own Claude Code skills from scratch rather than downloading pre-made ones. They cite two main reasons: security vulnerabilities in third-party skill marketplaces and the desire for highly personalized, tailored tools.
Summary
In this short clip, the speaker discusses their personal philosophy around using AI coding tools like Claude Code and Open Claw. Rather than downloading pre-built skills from marketplaces, they build everything themselves from scratch.
The speaker gives two core reasons for this approach. First, security: they claim that approximately 33% of skills available on the skill marketplace (referred to dismissively) contain prompt injections, meaning a significant portion of third-party skills could compromise the user's system or data.
Second, personalization: the speaker argues that their workflow and lifestyle differ substantially from the average user, making generic or 'normie' skills a poor fit. They prefer tools that are deeply tailored to their specific way of doing things, and building from scratch is the only way to achieve that level of customization.
Key Insights
- The speaker claims that 33% of skills on the Claude/AI skill marketplace contain prompt injections, framing third-party skill downloads as a major security risk.
- The speaker argues that pre-built 'normie' skills are fundamentally misaligned with users who have unconventional workflows, making self-built tools a necessity rather than a preference.
- The speaker builds all their own Claude Code skills from scratch as a deliberate practice, not just occasionally — framing it as a consistent personal policy.
- The speaker frames skill marketplaces dismissively, suggesting they are broadly untrustworthy and not worth engaging with given the high rate of malicious content.
- The speaker connects their AI tool-building philosophy directly to their broader lifestyle, suggesting that how one runs their life should dictate how they configure their AI tools.
Topics
Transcript
[0:00] When using Cloud Code or using Open Claw or anything like that, I build everything myself. Meaning, I don't actually go and download a bunch of skills. There's a few reasons for it. And number one, because that's typically how people get [ __ ] security-wise. [music] 33% of everything on Skill Claw or whatever the [ __ ] thing is called had prompt injections. That's like their marketplace and a third of it is just going to get you [ __ ] The other reason is I like to make my [ __ ] really, really tailored to me. And I do things really differently than most people out there. The way that I run my life is…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Mark Builds Brands
Do you need inhouse AI devs, to run the business?
A business leader explains that they no longer employ in-house AI developers because modern AI models and agents can accomplish nearly any development task efficiently. Instead of dedicated AI devs, they now prioritize hiring AI-enabled employees across all departments as a fundamental job requirement.
Can a Good CRV Save High CPMs?
A marketer discusses how high CPMs ($300-400) can still be acceptable if they deliver strong conversion rates (15%) and favorable unit economics. The speaker prioritizes CAC and ROAS over CPM metrics and views high CPMs as a solvable testing problem rather than a fundamental issue.
Are Winning Products Real?
The speaker argues that winning products are created through testing and science rather than luck, and that success depends primarily on marketing execution. Even copying proven products with equal or slightly inferior marketing can generate substantial revenue, particularly in commodity markets.
how to find unlimited ad hook (spoonfeeding you mfers)
The speaker explains a method called 'conscious doomscrolling' where marketers create fake social media accounts and strategically train algorithms within specific niches to identify viral content hooks and emotional triggers. By engaging authentically with content while remaining analytically focused, creators can identify what makes people stop scrolling and use those patterns to write more effective ad hooks.
What Your Best Performing Ad Is Telling You
The speaker criticizes surface-level ad analysis and argues that most people fail to deeply examine the psychological triggers and mechanisms underlying successful ad creatives. He emphasizes that true understanding of why ads work requires going far beyond obvious elements like curiosity hooks.