gilles/claude-code-best-practice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

skills

Browse Source
This commit is contained in:
Shayan Rais
2026-04-24 21:18:45 +05:00
parent 634ae5f553
commit fcc3830226
1 changed files with 175 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html
+175 -25
View File
@@ -2019,6 +2019,7 @@ todoapp/
</div>
<p class="section-desc">The model's <strong>working memory</strong> &mdash; what it can see in this moment.</p>
<div style="display: flex; flex-wrap: wrap; gap: 10px; justify-content: center; margin-top: 28px;">
<span style="background: #2e7d32; color: #fff; padding: 8px 20px; border-radius: 999px; font-size: 1rem; font-weight: 600; white-space: nowrap; box-shadow: 0 2px 8px rgba(46,125,50,0.35);">&#x2705; Fresh every chat</span>
<span style="background: #c62828; color: #fff; padding: 8px 20px; border-radius: 999px; font-size: 1rem; font-weight: 600; white-space: nowrap; box-shadow: 0 2px 8px rgba(198,40,40,0.35);">&#x26A0;&#xFE0F; Dumb-zone problem</span>
<span style="background: #c62828; color: #fff; padding: 8px 20px; border-radius: 999px; font-size: 1rem; font-weight: 600; white-space: nowrap; box-shadow: 0 2px 8px rgba(198,40,40,0.35);">&#x26A0;&#xFE0F; <code style="background: rgba(255,255,255,0.2); color: #fff; padding: 2px 8px; border-radius: 4px; font-family: 'SF Mono', Monaco, 'Courier New', monospace;">/compact</code></span>
</div>
@@ -2062,19 +2063,168 @@ todoapp/
</div>
</div>
<!-- Slide 42: Context — Claude's Brain -->
<div class="slide" data-slide="42" data-level="context">
<div style="min-height: calc(100vh - 120px);">
<h1>&#x1F9E0; Claude's Brain</h1>
<div class="analogy-box">
<h4>Think of it like this</h4>
<p>Imagine Claude has a <strong>brain</strong> that holds everything it's aware of right now &mdash; your question, every file it's opened, every tool result, every word it's said back to you. If a thought isn't in the brain, Claude can't use it. Simple as that.</p>
</div>
<img src="../assets/concepts/context-window.jpeg" alt="Context window diagram showing how the 1M token limit is divided across system prompt, tools, files, and conversation" style="width: 100%; max-width: 800px; margin: 24px auto; display: block; border-radius: 8px;" />
<div class="use-cases">
<div class="use-case-item">
<span class="use-case-icon">&#x1F4AC;</span>
<div class="use-case-text">
<strong>Your messages</strong>
<span>Every question, clarification, and follow-up</span>
</div>
</div>
<div class="use-case-item">
<span class="use-case-icon">&#x1F4C4;</span>
<div class="use-case-text">
<strong>Every file Claude opens</strong>
<span>Read a 500-page PDF? All of it is in the brain now.</span>
</div>
</div>
<div class="use-case-item">
<span class="use-case-icon">&#x1F527;</span>
<div class="use-case-text">
<strong>Every tool result</strong>
<span>Web searches, command output, screenshots &mdash; all held in memory</span>
</div>
</div>
</div>
<div class="warning-box">
<h4>Two Things to Know</h4>
<p><strong>1. The brain is finite.</strong> It can hold about 1 million tokens &mdash; roughly 750,000 words. Big, but not infinite. <strong>2. The brain empties at the end of every chat.</strong> When you start a new conversation, Claude remembers <em>nothing</em> from the last one unless you tell it again.</p>
</div>
</div>
<div class="pillar-footer">
<div class="pillar-mini-card inactive" style="border-left: 3px solid #009688;">
<span class="pmc-emoji">&#x1F9D1;&#x200D;&#x1F4BC;</span>
<span class="pmc-title">Agents</span>
<span class="pmc-subtitle">&mdash; the specialists</span>
<span class="pmc-body">A dedicated Claude worker &mdash; own context, own tools, own focus. Each runs in isolation.</span>
<span class="pmc-badge" style="background: #e8f5e9; color: #2e7d32;">&#x2705; fresh working memory per run</span>
</div>
<div class="pillar-mini-card inactive" style="border-left: 3px solid #9c27b0;">
<span class="pmc-emoji">&#x1F4DD;</span>
<span class="pmc-title">CLAUDE.md</span>
<span class="pmc-subtitle">&mdash; your memory</span>
<span class="pmc-body">Knowledge <em>you</em> provide to the model. Read every session. Keep it under 200 lines.</span>
<span class="pmc-badge" style="background: #fce4ec; color: #c62828;">&#x26A0;&#xFE0F; 200-line problem</span>
</div>
<div class="pillar-mini-card inactive" style="border-left: 3px solid #4caf50;">
<span class="pmc-emoji">&#x1F3AF;</span>
<span class="pmc-title">Skills</span>
<span class="pmc-subtitle">&mdash; the know-how</span>
<span class="pmc-body">What the specialist (or Claude) can actually do. Loaded on demand &mdash; only when needed.</span>
<span class="pmc-badge" style="background: #e8f5e9; color: #2e7d32;">&#x2705; progressive disclosure</span>
</div>
<div class="pillar-mini-card" style="border-left: 4px solid #3f51b5;">
<span class="pmc-emoji">&#x1F4AD;</span>
<span class="pmc-title">Context</span>
<span class="pmc-subtitle">&mdash; the working memory</span>
<span class="pmc-body">What Claude holds in his head now &mdash; fresh every new chat. Finite budget; compact at ~50%.</span>
<span class="pmc-badge" style="background: #fce4ec; color: #c62828;">&#x26A0;&#xFE0F; dumb-zone problem</span>
</div>
<div class="pillar-mini-card inactive" style="border-left: 3px solid #ef6c00;">
<span class="pmc-emoji">&#x1F4D8;</span>
<span class="pmc-title">Workflows</span>
<span class="pmc-subtitle">&mdash; the instruction manual</span>
<span class="pmc-body">Repeatable step-by-step recipes &mdash; like an AC install guide. Deterministic, reproducible.</span>
<span class="pmc-badge" style="background: #e8f5e9; color: #2e7d32;">&#x2705; reproducible recipes</span>
</div>
</div>
</div>
<!-- Slide 43: Context — What Loads at Session Start -->
<div class="slide" data-slide="43" data-level="context">
<div style="min-height: calc(100vh - 120px);">
<h1>What Loads at Session Start</h1>
<p>The moment you open Claude Code, certain things land in Claude's brain <strong>before you've typed a word</strong>. The rest waits in the wings &mdash; only loaded when you actually need it. This is called <strong>progressive disclosure</strong>.</p>
<img src="../assets/concepts/context.jpg" alt="Diagram showing what loads into Claude's context window at session start" style="width: 100%; max-width: 800px; margin: 24px auto; display: block; border-radius: 8px;" />
<div class="use-cases" style="margin-top: 24px;">
<div class="use-case-item">
<span class="use-case-icon">&#x1F4CB;</span>
<div class="use-case-text">
<strong>CLAUDE.md &mdash; full content</strong>
<span>Standing instructions, every line. Always pinned in the brain at startup.</span>
</div>
</div>
<div class="use-case-item">
<span class="use-case-icon">&#x1F393;</span>
<div class="use-case-text">
<strong>Skills &mdash; descriptions only</strong>
<span>Claude knows which skills exist and what each does &mdash; the full content loads when the skill is actually invoked.</span>
</div>
</div>
<div class="use-case-item">
<span class="use-case-icon">&#x1F464;</span>
<div class="use-case-text">
<strong>Agents &mdash; descriptions only</strong>
<span>The roster of specialists. The full system prompt loads when the agent is dispatched.</span>
</div>
</div>
</div>
<div class="trigger-box">
<h4>The One-Liner</h4>
<p>Only <strong>descriptions</strong> of skills and agents are loaded at startup &mdash; the rest is fetched on-demand. That's <strong>progressive disclosure</strong>. It keeps the brain light.</p>
</div>
</div>
<div class="pillar-footer">
<div class="pillar-mini-card inactive" style="border-left: 3px solid #009688;">
<span class="pmc-emoji">&#x1F9D1;&#x200D;&#x1F4BC;</span>
<span class="pmc-title">Agents</span>
<span class="pmc-subtitle">&mdash; the specialists</span>
<span class="pmc-body">A dedicated Claude worker &mdash; own context, own tools, own focus. Each runs in isolation.</span>
<span class="pmc-badge" style="background: #e8f5e9; color: #2e7d32;">&#x2705; fresh working memory per run</span>
</div>
<div class="pillar-mini-card inactive" style="border-left: 3px solid #9c27b0;">
<span class="pmc-emoji">&#x1F4DD;</span>
<span class="pmc-title">CLAUDE.md</span>
<span class="pmc-subtitle">&mdash; your memory</span>
<span class="pmc-body">Knowledge <em>you</em> provide to the model. Read every session. Keep it under 200 lines.</span>
<span class="pmc-badge" style="background: #fce4ec; color: #c62828;">&#x26A0;&#xFE0F; 200-line problem</span>
</div>
<div class="pillar-mini-card inactive" style="border-left: 3px solid #4caf50;">
<span class="pmc-emoji">&#x1F3AF;</span>
<span class="pmc-title">Skills</span>
<span class="pmc-subtitle">&mdash; the know-how</span>
<span class="pmc-body">What the specialist (or Claude) can actually do. Loaded on demand &mdash; only when needed.</span>
<span class="pmc-badge" style="background: #e8f5e9; color: #2e7d32;">&#x2705; progressive disclosure</span>
</div>
<div class="pillar-mini-card" style="border-left: 4px solid #3f51b5;">
<span class="pmc-emoji">&#x1F4AD;</span>
<span class="pmc-title">Context</span>
<span class="pmc-subtitle">&mdash; the working memory</span>
<span class="pmc-body">What Claude holds in his head now &mdash; fresh every new chat. Finite budget; compact at ~50%.</span>
<span class="pmc-badge" style="background: #fce4ec; color: #c62828;">&#x26A0;&#xFE0F; dumb-zone problem</span>
</div>
<div class="pillar-mini-card inactive" style="border-left: 3px solid #ef6c00;">
<span class="pmc-emoji">&#x1F4D8;</span>
<span class="pmc-title">Workflows</span>
<span class="pmc-subtitle">&mdash; the instruction manual</span>
<span class="pmc-body">Repeatable step-by-step recipes &mdash; like an AC install guide. Deterministic, reproducible.</span>
<span class="pmc-badge" style="background: #e8f5e9; color: #2e7d32;">&#x2705; reproducible recipes</span>
</div>
</div>
</div>
<!-- ============================================================ -->
<!-- TOPIC 2: SKILLS (Slides 15-20) -->
<!-- ============================================================ -->
<!-- Slide 14: Skills Section Divider -->
<div class="slide section-slide" data-slide="42" data-level="skills">
<div class="slide section-slide" data-slide="44" data-level="skills">
<div class="section-number">Topic 2</div>
<h1>&#x1F393; Skills &mdash; What the Weather Reporter Knows</h1>
<p class="section-desc">Skills are the specific things the reporter has been trained to do. Our reporter has two: <strong>fetch the data</strong>, and <strong>render it as a card</strong>.</p>
</div>
<!-- Slide 15: The Training Manual -->
<div class="slide" data-slide="43">
<div class="slide" data-slide="45">
<h1>The Training Manual</h1>
<div class="analogy-box">
<h4>Think of it like this</h4>
@@ -2101,7 +2251,7 @@ todoapp/
</div>
<!-- Slide 16: When to Turn Something Into a Skill -->
<div class="slide" data-slide="44">
<div class="slide" data-slide="46">
<h1>When to Turn Something Into a Skill</h1>
<div class="info-box">
<h4>Tip from Boris Cherny (creator of Claude Code) &mdash; Feb 1, 2026</h4>
@@ -2138,7 +2288,7 @@ todoapp/
</div>
<!-- Slide 17: Why Separate Agents and Skills? -->
<div class="slide" data-slide="45">
<div class="slide" data-slide="47">
<h1>Why Separate Agents and Skills?</h1>
<div class="two-col">
<div>
@@ -2164,7 +2314,7 @@ todoapp/
</div>
<!-- Slide 18: How to Create Your Own Skill -->
<div class="slide" data-slide="46">
<div class="slide" data-slide="48">
<h1>How to Create Your Own Skill</h1>
<p>Skills are plain markdown files. If you can write a recipe, you can write a skill.</p>
<div class="how-to-trigger">
@@ -2217,7 +2367,7 @@ Fetch the current temperature for Dubai, UAE.
</div>
<!-- Slide 19: Skill Config Fields -->
<div class="slide" data-slide="47">
<div class="slide" data-slide="49">
<h1>Skill Config Fields</h1>
<p>The small config block at the top of a SKILL.md (the "frontmatter") controls how the skill behaves:</p>
<div style="margin: 24px 0;">
@@ -2257,14 +2407,14 @@ Fetch the current temperature for Dubai, UAE.
<!-- ============================================================ -->
<!-- Slide 20: Context Section Divider -->
<div class="slide section-slide" data-slide="48" data-level="context">
<div class="slide section-slide" data-slide="50" data-level="context">
<div class="section-number">Topic 3</div>
<h1>&#x1F9E0; Context &mdash; The Reporter's Brain</h1>
<p class="section-desc">Now that you've met the reporter and know their skills, let's understand what they can actually hold in mind at once. Every agent &mdash; including the weather reporter &mdash; gets its own fresh brain.</p>
</div>
<!-- Slide 21: Claude's Brain -->
<div class="slide" data-slide="49">
<div class="slide" data-slide="51">
<h1>Claude's Brain</h1>
<div class="analogy-box">
<h4>Think of it like this</h4>
@@ -2302,7 +2452,7 @@ Fetch the current temperature for Dubai, UAE.
</div>
<!-- Slide 22: What Loads at Session Start -->
<div class="slide" data-slide="50">
<div class="slide" data-slide="52">
<h1>What Loads at Session Start</h1>
<p>The moment you open Claude Code, certain things land in Claude's brain <strong>before you've typed a word</strong>. The rest waits in the wings &mdash; only loaded when you actually need it. This is called <strong>progressive disclosure</strong>.</p>
<img src="../assets/concepts/context.jpg" alt="Diagram showing what loads into Claude's context window at session start" style="width: 100%; max-width: 800px; margin: 24px auto; display: block; border-radius: 8px;" />
@@ -2336,7 +2486,7 @@ Fetch the current temperature for Dubai, UAE.
</div>
<!-- Slide 23: Keep the Brain Clear -->
<div class="slide" data-slide="51">
<div class="slide" data-slide="53">
<h1>Keep the Brain Clear</h1>
<p>The more stuff crammed into Claude's brain, the harder it is to focus on what matters. This is called <strong>context rot</strong> &mdash; performance drops as the brain gets crowded.</p>
<div class="info-box">
@@ -2380,7 +2530,7 @@ Fetch the current temperature for Dubai, UAE.
</div>
<!-- Slide 24: How to Manage Your Context -->
<div class="slide" data-slide="52">
<div class="slide" data-slide="54">
<h1>How to Manage Your Context</h1>
<p>You can't <em>create</em> the context &mdash; it's just there, the moment you open a chat. But you can <strong>see</strong> how full it is, <strong>trim</strong> it down, or <strong>wipe</strong> it clean. Three commands give you full control.</p>
<div class="how-to-trigger">
@@ -2425,14 +2575,14 @@ Fetch the current temperature for Dubai, UAE.
<!-- ============================================================ -->
<!-- Slide 25: CLAUDE.md Section Divider -->
<div class="slide section-slide" data-slide="53" data-level="claude-md">
<div class="slide section-slide" data-slide="55" data-level="claude-md">
<div class="section-number">Topic 4</div>
<h1>&#x1F4CB; CLAUDE.md &mdash; The Reporter's Pocket Rulebook</h1>
<p class="section-desc">The weather reporter consults this at the start of every shift &mdash; even though their brain resets overnight. It's the standing instructions pinned in that brain before you've said a word.</p>
</div>
<!-- Slide 26: The Employee Handbook -->
<div class="slide" data-slide="54">
<div class="slide" data-slide="56">
<h1>The Employee Handbook</h1>
<div class="analogy-box">
<h4>Think of it like this</h4>
@@ -2460,7 +2610,7 @@ This is the Q2 marketing campaign brief &mdash; targeting small business owners.
</div>
<!-- Slide 27: How to Create CLAUDE.md -->
<div class="slide" data-slide="55">
<div class="slide" data-slide="57">
<h1>How to Create Your CLAUDE.md</h1>
<p>You don't need to write CLAUDE.md by hand. Claude can look at your project and draft one for you.</p>
<div class="how-to-trigger">
@@ -2505,7 +2655,7 @@ open, edit, save <span class="comment"># Tweak it like any doc</span><
</div>
<!-- Slide 28: Grow CLAUDE.md With Every Mistake -->
<div class="slide" data-slide="56">
<div class="slide" data-slide="58">
<h1>Grow CLAUDE.md With Every Mistake</h1>
<div class="info-box">
<h4>Tip from Boris Cherny (creator of Claude Code) &mdash; Feb 1, 2026</h4>
@@ -2542,7 +2692,7 @@ open, edit, save <span class="comment"># Tweak it like any doc</span><
</div>
<!-- Slide 29: What Goes in CLAUDE.md -->
<div class="slide" data-slide="57">
<div class="slide" data-slide="59">
<h1>What Goes in CLAUDE.md</h1>
<div class="code-block"><span class="comment"># CLAUDE.md</span>
@@ -2570,7 +2720,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
</div>
<!-- Slide 30: How CLAUDE.md Loads -->
<div class="slide" data-slide="58">
<div class="slide" data-slide="60">
<h1>How CLAUDE.md Loads</h1>
<p>Claude Code uses two mechanisms to find CLAUDE.md files:</p>
<div class="two-col">
@@ -2603,14 +2753,14 @@ This is a TodoApp with a FastAPI backend and React frontend.
<!-- ============================================================ -->
<!-- Slide 31: Commands Section Divider -->
<div class="slide section-slide" data-slide="59" data-level="commands">
<div class="slide section-slide" data-slide="61" data-level="commands">
<div class="section-number">Topic 5</div>
<h1>&#x26A1; Commands &mdash; The Trigger</h1>
<p class="section-desc">One word kicks off the whole chain. <code>/weather-orchestrator</code> &rarr; agent &rarr; skill &rarr; SVG card. Commands are the entry point into any workflow.</p>
</div>
<!-- Slide 32: Commands — The Entry Point -->
<div class="slide" data-slide="60">
<div class="slide" data-slide="62">
<h1>Commands &mdash; The Entry Point</h1>
<div class="analogy-box">
<h4>Think of it like this</h4>
@@ -2654,7 +2804,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
</div>
<!-- Slide 33: How to Create Your Own Command -->
<div class="slide" data-slide="61">
<div class="slide" data-slide="63">
<h1>How to Create Your Own Command</h1>
<p>Commands are markdown files too. If you can write a recipe, you can write a command.</p>
<div class="how-to-trigger">
@@ -2709,14 +2859,14 @@ This is a TodoApp with a FastAPI backend and React frontend.
<!-- ============================================================ -->
<!-- Slide 34: Workflow Sub-Section (Putting It All Together) -->
<div class="slide section-slide" data-slide="62" data-level="workflow">
<div class="slide section-slide" data-slide="64" data-level="workflow">
<div class="section-number">Putting It All Together</div>
<h1>&#x1F3BC; Workflow &mdash; All Five Pieces Together</h1>
<p class="section-desc">Watch the weather reporter example run from one keystroke to SVG card output. Five concepts, one orchestrated flow.</p>
</div>
<!-- Slide 35: Command → Agent → Skill -->
<div class="slide" data-slide="63">
<div class="slide" data-slide="65">
<h1>Command &rarr; Agent &rarr; Skill</h1>
<p>This is the <strong>core architecture pattern</strong> of Claude Code workflows &mdash; demonstrated in this very repo by the weather example:</p>
<div class="code-block"><span class="comment">The Orchestration Flow</span>
@@ -2743,7 +2893,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
</div>
<!-- Slide 36: Two Ways Skills Are Used -->
<div class="slide" data-slide="64">
<div class="slide" data-slide="66">
<h1>Two Ways Skills Are Used</h1>
<p>The weather workflow demonstrates both skill patterns in a single flow:</p>
<div class="two-col">
@@ -2766,7 +2916,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
</div>
<!-- Slide 37: How to Wire Your Own Workflow -->
<div class="slide" data-slide="65">
<div class="slide" data-slide="67">
<h1>How to Wire Your Own Workflow</h1>
<p>A workflow isn't a separate file type. It <em>emerges</em> when one command calls agents and skills in sequence.</p>
<div class="how-to-trigger">
@@ -2817,7 +2967,7 @@ This is a TodoApp with a FastAPI backend and React frontend.
<!-- ============================================================ -->
<!-- SLIDE 40: Closing -->
<!-- ============================================================ -->
<div class="slide title-slide" data-slide="66">
<div class="slide title-slide" data-slide="68">
<h1>Journey So Far</h1>
<p class="subtitle">Five concepts, one running example</p>
<p style="margin-top: 20px; font-size: 1.1rem; color: #666; max-width: 640px;">From meeting the weather reporter to wiring the full <strong>Command &rarr; Agent &rarr; Skill</strong> chain. The same five pieces compose every workflow you'll ever build.</p>