<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[LachlanCB]]></title><description><![CDATA[LachlanCB]]></description><link>https://lachlancb.hashnode.dev</link><image><url>https://cdn.hashnode.com/res/hashnode/image/upload/v1593680282896/kNC7E8IR4.png</url><title>LachlanCB</title><link>https://lachlancb.hashnode.dev</link></image><generator>RSS for Node</generator><lastBuildDate>Tue, 08 Sep 2026 19:12:16 GMT</lastBuildDate><atom:link href="https://lachlancb.hashnode.dev/rss.xml" rel="self" type="application/rss+xml"/><language><![CDATA[en]]></language><ttl>60</ttl><item><title><![CDATA[Building Custom Skills for Claude Code: A Practical Guide]]></title><description><![CDATA[Originally published at lachlancb.me. I run a one-person agency from Claude Code and this is the piece I point people to when they ask how.
What Are Claude Code Skills?
Skills are markdown files that ]]></description><link>https://lachlancb.hashnode.dev/building-custom-skills-for-claude-code-a-practical-guide</link><guid isPermaLink="true">https://lachlancb.hashnode.dev/building-custom-skills-for-claude-code-a-practical-guide</guid><category><![CDATA[AI]]></category><category><![CDATA[claude]]></category><dc:creator><![CDATA[Lachy]]></dc:creator><pubDate>Sat, 05 Sep 2026 05:47:49 GMT</pubDate><content:encoded><![CDATA[<p><em>Originally published at</em> <a href="https://lachlancb.me/building-custom-skills-claude-code/"><em>lachlancb.me</em></a><em>. I run a one-person agency from Claude Code and this is the piece I point people to when they ask how.</em></p>
<h2>What Are Claude Code Skills?</h2>
<p>Skills are markdown files that turn Claude Code into something personal.</p>
<p>Without them, Claude Code is a powerful general-purpose terminal assistant. With them, it becomes <em>your</em> terminal assistant: one that knows your brand voice, your deploy workflow, your sales scripts, and your content pipeline.</p>
<p>A skill is just a <code>.md</code> file stored in <code>~/.claude/skills/</code>. Each one contains instructions for how Claude should behave when you invoke it. Type <code>/blog-draft</code> and it writes an SEO-optimised article in your brand voice, publishes it, generates a cover image, and attaches a CTA card. Type <code>/sales-script</code> and it runs you through cold call roleplay with objection handling. Type <code>/evening</code> and it reads your Notion planner, reflects on your day, and saves a diary entry to Obsidian.</p>
<p>That's the difference. Skills are how you stop prompting from scratch every session and start building on top of what you've already figured out.</p>
<h2>The Neo Metaphor Nobody's Making</h2>
<p>Remember the scene in The Matrix where Neo plugs in and downloads kung fu in seconds? "I know kung fu."</p>
<p>That's what installing skills feels like.</p>
<p>You find a skill repo on GitHub, run one command, and suddenly Claude Code knows how to do things it couldn't do 30 seconds ago. Build Terraform infrastructure. Run Playwright end-to-end tests. Optimise PostgreSQL queries. Design UI components. Conduct security audits.</p>
<p>I have 320 skills installed right now. That's not a flex. It's a deliberate operating system I've built over months. Each skill encodes a workflow I used to do manually. Some I built myself. Some came from the community. All of them compound.</p>
<p>The implications are wild if you think about it. The gap between "I don't know how to do X" and "I can do X at a professional level" is collapsing to the time it takes to install a markdown file. The learning curve isn't gone. It's been absorbed into the skill itself.</p>
<h2>How I Actually Use Skills Daily</h2>
<p>Here's what a normal day looks like with my skill stack:</p>
<p><strong>Morning:</strong> <code>/morning</code> pulls my Notion planner, intelligence feed, and most important tasks, then saves a briefing to my Obsidian vault.</p>
<p><strong>Content:</strong> <code>/blog-draft personal "topic"</code> researches sources, writes a full article in my brand voice, publishes it, generates cover images and infographics, injects CTAs. One command.</p>
<p><strong>Sales:</strong> <code>/sales-script</code> loads my cold calling system with Hormozi-style objection handling. I use it for roleplay practice before call blocks.</p>
<p><strong>Research:</strong> <code>/skills-search</code> is one of the most underrated skills. I type a keyword and it surfaces the 3-4 most relevant skills for what I'm building. It's like having an index of capabilities I forgot I had.</p>
<p><strong>Evening:</strong> <code>/evening</code> reads my completed Notion template, gives me Life Coach feedback on my patterns, and saves a reflection to my diary.</p>
<p><strong>Debugging:</strong> <code>/debugger</code> kicks in automatically when something breaks. It follows a systematic debugging flow instead of guessing.</p>
<p>The pattern is the same every time: encode the workflow once, invoke it forever. The skill does the heavy lifting. I do the thinking.</p>
<h2>How to Build Your Own Skill</h2>
<p>A skill is a <code>SKILL.md</code> file in a folder under <code>~/.claude/skills/your-skill-name/</code>. The structure is simple.</p>
<p>The file starts with frontmatter (name, description, triggers) followed by plain markdown instructions. Tell Claude what to do step by step: what tools to use, what format to output, what mistakes to avoid. The more specific you are, the better the skill performs.</p>
<pre><code class="language-markdown">---
name: blog-draft
description: Write and publish a blog article in my brand voice. Fires on "blog", "write a blog", "/blog-draft".
---

## Steps
1. Read the brand voice file at knowledge/canonical/voice.md before writing anything.
2. Research 3-5 sources on the topic. Cite them inline.
3. Write 1,200-1,800 words. Grade 5-6 reading level. Short paragraphs. No passive voice.
4. One H2 every 300 words. End with a single CTA.
5. Save to content/blog/&lt;slug&gt;.mdx and show me the draft before publishing.

## Never
- Invent statistics, reviews or client counts.
- Use another person's name or business in a public post.
</code></pre>
<p><strong>The key principles:</strong></p>
<ul>
<li><p><strong>Be explicit.</strong> Don't say "write good content." Say "use short paragraphs, Grade 5 reading level, no passive voice, include one H2 every 300 words."</p>
</li>
<li><p><strong>Include examples.</strong> Show Claude what the output should look like. One good example beats a page of rules.</p>
</li>
<li><p><strong>Chain tools.</strong> A single skill can read files, search the web, call APIs, take screenshots, and write code. The power is in composition.</p>
</li>
<li><p><strong>Iterate.</strong> Your first version will be rough. Run it, see what breaks, tighten the instructions. After 3-4 iterations, it becomes reliable.</p>
</li>
</ul>
<h2>Where to Find Skills</h2>
<p>The community has exploded. Three repos worth bookmarking:</p>
<ul>
<li><p><strong>awesome-claude-code</strong>: 35,000+ stars on GitHub. The largest collection of skills, hooks, slash commands, and agent orchestrators for Claude Code.</p>
</li>
<li><p><strong>awesome-agent-skills</strong> by VoltAgent: 13,000+ stars. Cross-platform skills that work with Claude Code, Codex, Gemini CLI, and Cursor.</p>
</li>
<li><p><strong>awesome-claude-code-toolkit</strong>: 135 agents, 35+ curated skills, 400,000+ via SkillKit.</p>
</li>
</ul>
<p>Installing a skill is usually as simple as copying a folder into <code>~/.claude/skills/</code>. Some repos include install scripts that handle it for you.</p>
<h2>Getting Started With Claude Code</h2>
<p>If you don't have Claude Code yet, it's Anthropic's official CLI tool. Install it with:</p>
<pre><code class="language-bash">npm install -g @anthropic-ai/claude-code
</code></pre>
<p>Then run <code>claude</code> in your terminal. That's it. You're in.</p>
<p>From there, start with one or two skills that match your daily workflow. Don't try to install 320 on day one. Pick your highest-friction task, the one you repeat most often, and encode it as a skill. Use it for a week. Then build the next one.</p>
<h2>The Future of Skills</h2>
<p>Here's what I think is coming.</p>
<p>Right now, skills are text files written by humans. They work because Claude Code is smart enough to interpret detailed instructions and execute them reliably.</p>
<p>But the trajectory is clear. Skills will get more compositional: skills that call other skills. They'll get smarter, adapting their behaviour based on context, past results, and your preferences. They'll get shareable: marketplaces where you can browse, install, and rate skills the way you browse apps today.</p>
<p>The Matrix metaphor isn't just cute. It's directionally accurate. We're building toward a world where capability is downloadable. Where the question isn't "can you do this?" but "do you have the skill installed?"</p>
<p>The people who start building their skill stack now, encoding their workflows, their voice, their decision-making, will have an enormous compounding advantage. Because every skill you build today makes tomorrow slightly easier. And that compounds.</p>
<p>Start with one skill. Make it good. Then build the next.</p>
<hr />
<p><em>If you want the longer version of how this stack runs a business, I wrote up</em> <a href="https://lachlancb.me/1000-hours-in-claude-code/"><em>what 1,000 hours in Claude Code taught me</em></a><em>.</em></p>
]]></content:encoded></item></channel></rss>