Files
skills/public/skill-prompt-discovery.html
zeekayandHanzo Dev 9e10c1c10e Each llms index points at the other two
hanzoskills.com/llms.txt now opens with the install line, the API
reference index and the company index, so an agent that lands on any
one of the three can find the rest.

robots.txt claimed 537 documents while llms.txt counts 920. The number
is gone from robots.txt; llms.txt derives it.

public/ is regenerated from scripts/site.py, which it had fallen
behind: the copy-prompt menu and agent bar were in the generator and
not in the committed pages. tests/site.mjs passes against the result.

Co-authored-by: Hanzo Dev <[email protected]>
2026-09-11 00:27:59 -07:00

504 lines
29 KiB
HTML

<!doctype html>
<html lang="en"><head>
<meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
<title>skill-prompt-discovery</title>
<meta name="color-scheme" content="dark">
<style>
/* Committed to one visual world: a dark instrument panel. No light variant —
the dot field and the hairline rules only read on black, and a naive
inversion would wash both out. Every colour is painted explicitly so the page
never borrows a host background. */
@font-face{font-family:'Zen';src:url('/fonts/Zen-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen';src:url('/fonts/Zen-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Variable.woff2') format('woff2');font-weight:100 900;font-style:normal;font-display:swap}
@font-face{font-family:'Zen Mono';src:url('/fonts/ZenMono-Italic-Variable.woff2') format('woff2');font-weight:100 900;font-style:italic;font-display:swap}
@font-face{font-family:'Zen Pixel Square';src:url('/fonts/ZenPixel-Square.woff2') format('woff2');font-style:normal;font-display:swap}
:root{
--ink:#f4f4f2; --soft:#9c9c98; --faint:#6a6a66; --ground:#000; --panel:#0a0a0a;
--line:#232323; --line-hi:#3a3a3a; --accent:#f4f4f2;
--font-zen-sans:'Zen',-apple-system,BlinkMacSystemFont,"Segoe UI",Helvetica,Arial,sans-serif;
--font-zen-mono:'Zen Mono',ui-monospace,"SF Mono",SFMono-Regular,Menlo,Consolas,monospace;
--font-zen-pixel-square:'Zen Pixel Square',monospace;
--mono:var(--font-zen-mono);
--sans:var(--font-zen-sans);
/* Controls are pills and surfaces are soft, as on hanzo.ai. */
--r:999px; --r-soft:14px;
}
*{box-sizing:border-box}
html{-webkit-text-size-adjust:100%}
body{margin:0;background:var(--ground);color:var(--ink);font-family:var(--sans);
font-size:16px;line-height:1.65;-webkit-font-smoothing:antialiased}
.wrap{max-width:60rem;margin:0 auto;padding:0 1.75rem}
/* The dot field. A halftone made of one repeating radial-gradient, faded out
along the diagonal by a mask so it reads as a wave rather than wallpaper. */
/* No overflow clip here: the dot field is inset to the box already, and a clip
would cut off the copy-prompt menu. */
.hero{position:relative;border-bottom:1px solid var(--line)}
.hero::before{content:"";position:absolute;inset:0;
background-image:radial-gradient(var(--line-hi) 1px, transparent 1px);
background-size:7px 7px;
-webkit-mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
mask-image:linear-gradient(115deg,#000 0%,rgba(0,0,0,.55) 38%,transparent 72%);
pointer-events:none}
.hero .wrap{position:relative;padding-top:5.5rem;padding-bottom:4rem}
nav{border-bottom:1px solid var(--line)}
nav .in{max-width:60rem;margin:0 auto;padding:1.1rem 1.75rem;display:flex;
justify-content:space-between;align-items:center;gap:1rem}
.brand{font-family:var(--mono);font-size:.85rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--ink);text-decoration:none;
display:inline-flex;align-items:center;gap:.6rem}
.brand i{font-style:normal;color:var(--faint)}
.mark{width:1.15em;height:1.15em;display:block;flex:0 0 auto}
nav a.up{font-family:var(--mono);font-size:.72rem;letter-spacing:.14em;
text-transform:uppercase;color:var(--soft);text-decoration:none}
nav a.up:hover{color:var(--ink)}
h1{font-family:var(--mono);font-size:clamp(2rem,5.4vw,3.4rem);line-height:1.12;
letter-spacing:-.02em;margin:0 0 1.1rem;font-weight:500;text-wrap:balance}
h1 em{font-style:normal;color:var(--faint)}
.lede{color:var(--soft);font-size:1.05rem;max-width:52ch;margin:0 0 2.25rem}
.btns{display:flex;flex-wrap:wrap;gap:.7rem;margin:0 0 .5rem;align-items:center}
.btn{display:inline-flex;align-items:center;gap:.5rem;font-family:var(--mono);
font-size:.72rem;letter-spacing:.14em;text-transform:uppercase;
padding:.8rem 1.4rem;border:1px solid var(--line-hi);border-radius:var(--r);
color:var(--ink);text-decoration:none;background:transparent;cursor:pointer;
line-height:1.2;font-weight:400}
.btn:hover{background:#141414;text-decoration:none;border-color:var(--soft)}
.btn.solid{background:var(--ink);color:#000;border-color:var(--ink)}
.btn.solid:hover{background:#d8d8d4}
.btn .chev{width:.7em;height:.7em;flex:0 0 auto;transition:transform .15s ease}
.btn[aria-expanded="true"] .chev{transform:rotate(180deg)}
/* Copy-prompt selector. Each row copies the prompt for its own target. */
.copy{position:relative;display:inline-flex}
.menu{position:absolute;top:calc(100% + .5rem);left:0;z-index:20;min-width:21rem;
background:var(--panel);border:1px solid var(--line-hi);border-radius:var(--r-soft);
padding:.4rem;display:flex;flex-direction:column;
box-shadow:0 12px 32px rgba(0,0,0,.75)}
.menu[hidden]{display:none}
.mi{display:flex;align-items:center;gap:.7rem;width:100%;text-align:left;
padding:.62rem .8rem;border:0;border-radius:calc(var(--r-soft) - .35rem);
background:transparent;color:var(--ink);font-family:var(--mono);font-size:.76rem;
letter-spacing:.04em;text-decoration:none;cursor:pointer;line-height:1.3;
white-space:nowrap}
.mi:hover,.mi:focus-visible{background:#181818;outline:none}
.mi .mark{width:1.05rem;height:1.05rem;color:var(--soft)}
.mi:hover .mark{color:var(--ink)}
.mi u{margin-left:auto;color:var(--faint);text-decoration:none;font-size:.68rem;
letter-spacing:.1em;text-transform:uppercase}
/* Works-with bar: one scrolling row, name and mark per agent. */
.strip{border-bottom:1px solid var(--line);background:var(--panel)}
.strip .in{max-width:60rem;margin:0 auto;padding:.9rem 1.75rem;display:flex;
align-items:center;gap:1.25rem;font-family:var(--mono);font-size:.72rem;
letter-spacing:.1em;text-transform:uppercase;color:var(--faint)}
.strip b{color:var(--soft);font-weight:400;flex:0 0 auto;
border-right:1px solid var(--line);padding-right:1.25rem;align-self:stretch;
display:flex;align-items:center}
.bar{display:flex;align-items:center;gap:.5rem;flex:1 1 auto;min-width:0;
overflow-x:auto;scrollbar-width:none;scroll-snap-type:x proximity;
-webkit-overflow-scrolling:touch;
-webkit-mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent);
mask-image:linear-gradient(90deg,#000 calc(100% - 3rem),transparent)}
.bar::-webkit-scrollbar{display:none}
.agent{display:inline-flex;align-items:center;gap:.45rem;flex:0 0 auto;
padding:.4rem .85rem;border:1px solid var(--line);border-radius:var(--r);
color:var(--soft);white-space:nowrap;scroll-snap-align:start;
text-decoration:none;background:var(--ground)}
.agent:hover{color:var(--ink);border-color:var(--line-hi);text-decoration:none}
.agent .mark{width:.95rem;height:.95rem}
h2{font-family:var(--mono);font-size:1.1rem;letter-spacing:-.01em;margin:2.75rem 0 .75rem;font-weight:500}
h3{font-size:1rem;margin:2rem 0 .5rem;font-weight:600}
h4,h5,h6{font-size:.94rem;margin:1.5rem 0 .5rem;font-weight:600}
p{margin:0 0 1rem;max-width:70ch}
ul,ol{margin:0 0 1rem;padding-left:1.35rem;max-width:70ch}
li{margin:.22rem 0}
a{color:var(--ink);text-decoration:underline;text-underline-offset:3px;
text-decoration-color:var(--line-hi)}
a:hover{text-decoration-color:var(--ink)}
a:focus-visible{outline:1px solid var(--ink);outline-offset:3px}
code{font-family:var(--mono);font-size:.85em;background:var(--panel);
border:1px solid var(--line);border-radius:5px;padding:.1em .36em}
pre{background:var(--panel);border:1px solid var(--line);padding:1rem 1.1rem;
border-radius:var(--r-soft);overflow-x:auto;margin:0 0 1.25rem}
pre code{background:none;border:0;padding:0;font-size:.82rem;line-height:1.7}
blockquote{margin:0 0 1rem;padding-left:1rem;border-left:1px solid var(--line-hi);color:var(--soft)}
hr{border:0;border-top:1px solid var(--line);margin:2.5rem 0}
table{border-collapse:collapse;width:100%;margin:0 0 1.25rem;font-size:.92rem;
display:block;overflow-x:auto}
th,td{border:1px solid var(--line);padding:.5rem .7rem;text-align:left}
.curl{display:block;background:var(--panel);border:1px solid var(--line);
border-radius:var(--r-soft);padding:.95rem 1.1rem;font-family:var(--mono);
font-size:.8rem;color:var(--soft);overflow-x:auto;margin:0 0 2.5rem;
white-space:pre;line-height:1.9}
.curl b{color:var(--ink);font-weight:400}
.curl i{font-style:normal;color:var(--faint)}
/* index */
#q{width:100%;padding:.85rem 1.2rem;font-family:var(--mono);font-size:.85rem;color:var(--ink);
background:var(--panel);border:1px solid var(--line);border-radius:var(--r);margin:0 0 .6rem}
#q::placeholder{color:var(--faint);text-transform:uppercase;letter-spacing:.1em;font-size:.72rem}
#q:focus{outline:none;border-color:var(--soft)}
#count{color:var(--faint);font-family:var(--mono);font-size:.72rem;letter-spacing:.1em;
text-transform:uppercase;margin:0 0 2rem}
.cat{margin:2.5rem 0 .5rem;font-family:var(--mono);font-size:.7rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);border-bottom:1px solid var(--line);
padding-bottom:.45rem}
.row{display:block;padding:.6rem .9rem;margin:0 -.9rem;border-bottom:1px solid var(--line);
border-radius:var(--r-soft);text-decoration:none}
.row:hover{background:#0a0a0a}
.nm{font-family:var(--mono);font-size:.84rem;color:var(--ink);display:block}
.ds{color:var(--soft);font-size:.9rem;display:block;margin-top:.12rem}
footer{margin-top:4rem;padding:2rem 0 4rem;border-top:1px solid var(--line);
color:var(--faint);font-size:.85rem}
footer a{color:var(--soft)}
.fmap{display:grid;gap:1.75rem;grid-template-columns:repeat(auto-fit,minmax(11rem,1fr));
margin:0 0 2rem;font-size:.85rem}
.fmap b{display:block;font-family:var(--mono);font-size:.68rem;letter-spacing:.16em;
text-transform:uppercase;color:var(--faint);font-weight:400;margin:0 0 .6rem;
border-bottom:1px solid var(--line);padding-bottom:.4rem}
.fmap a{display:inline-block;color:var(--ink);text-decoration:none;margin:.3rem .35rem 0 0}
.fmap a:hover{text-decoration:underline}
.fmap div{color:var(--faint);line-height:1.5}
.fend{border-top:1px solid var(--line);padding-top:1.25rem;font-size:.82rem}
@media (max-width:640px){
.hero .wrap{padding-top:3.25rem;padding-bottom:2.75rem}
.btns{gap:.5rem}
.btn{padding:.75rem 1.15rem;font-size:.68rem}
.copy,.copy .btn{width:100%;justify-content:center}
.menu{left:0;right:0;min-width:0}
.strip .in{flex-direction:column;align-items:flex-start;gap:.6rem;padding:.9rem 1.75rem}
.strip b{border-right:0;padding-right:0}
.bar{width:100%}
}
</style>
<link rel="alternate" type="text/markdown" href="/skill-prompt-discovery.md">
<link rel="icon" href="/favicon.svg">
<link rel="canonical" href="https://hanzoskills.com/skill-prompt-discovery">
</head>
<!-- Reading this with a machine? Every page here is also plain markdown.
This one: https://hanzoskills.com/skill-prompt-discovery.md
Index: https://hanzoskills.com/llms.txt
Corpus: https://hanzoskills.com/all.md
Append .md to any path for the markdown twin. -->
<body>
<nav><div class="in">
<a class="brand" href="/"><svg class="mark" viewBox="0 0 67 67" fill="currentColor" aria-hidden="true"><path d="M22.21 67V44.6369H0V67H22.21Z"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z"/><path d="M22.21 0H0V22.3184H22.21V0Z"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z"/></svg> HANZO<i>SKILLS</i></a>
<a class="up" href="/">All skills</a>
</div></nav>
<div class="wrap">
<h1>skill-prompt-discovery</h1><p class="lede">User makes a request involving specific technologies or frameworks</p><h1>Prompt Skill Discovery</h1>
<p><strong>Scope</strong>: Analyzing user prompts/context to identify which existing skills should be activated <strong>Lines</strong>: ~390 <strong>Last Updated</strong>: 2025-10-18</p>
<h2>When to Use This Skill</h2>
<p>Activate this skill when:</p>
<ul><li>User makes a request involving specific technologies or frameworks</li><li>Context mentions specialized tools, languages, or platforms</li><li>Task requires domain expertise beyond general programming</li><li>Multi-step workflow requires skill composition</li><li>Proactive skill activation during conversation is needed</li><li>Determining which skills to read from _INDEX.md</li></ul>
<h2>Core Concepts</h2>
<h3>Intent Analysis</h3>
<p><strong>What is the user trying to accomplish?</strong></p>
<ul><li>Extract the primary goal (build, debug, optimize, deploy, learn)</li><li>Identify the outcome they want (working app, fixed bug, faster system)</li><li>Separate explicit requests from implied needs</li><li>Consider context from conversation history</li></ul>
<p><strong>Types of intent:</strong></p>
<ul><li><strong>Building</strong>: Creating new systems, features, or components</li><li><strong>Debugging</strong>: Fixing errors, investigating issues, troubleshooting</li><li><strong>Optimizing</strong>: Improving performance, reducing costs, enhancing quality</li><li><strong>Deploying</strong>: Shipping to production, CI/CD setup, infrastructure</li><li><strong>Learning</strong>: Understanding concepts, exploring options, research</li></ul>
<h3>Tech Signal Extraction</h3>
<p><strong>Keywords → Technologies mapping:</strong></p>
<ul><li>Look for framework names: &quot;Next.js&quot; → <code>nextjs-*.md</code></li><li>Look for languages: &quot;Zig&quot;, &quot;Swift&quot;, &quot;Go&quot; → language-specific skills</li><li>Look for platforms: &quot;Modal&quot;, &quot;Heroku&quot;, &quot;Netlify&quot; → platform skills</li><li>Look for domains: &quot;database&quot;, &quot;API&quot;, &quot;TUI&quot; → domain skills</li><li>Look for tools: &quot;Docker&quot;, &quot;Terraform&quot;, &quot;Kubernetes&quot; → tool skills</li></ul>
<p><strong>Implicit signals:</strong></p>
<ul><li>&quot;iOS app&quot; → SwiftUI/Swift skills even if not explicitly mentioned</li><li>&quot;TUI&quot; or &quot;terminal dashboard&quot; → Bubble Tea or Ratatui</li><li>&quot;ML model&quot; → Modal GPU + ML skills</li><li>&quot;REST API&quot; → API design + auth + database skills</li><li>&quot;CI/CD&quot; → GitHub Actions + testing + deployment skills</li></ul>
<h3>Workflow Pattern Matching</h3>
<p><strong>Request → Skill chain:</strong></p>
<ul><li>Single-step tasks → 1-2 skills</li><li>Multi-component systems → 3-6 skills in workflow</li><li>Full-stack applications → 6+ skills across layers</li><li>Infrastructure projects → IaC + security + observability chain</li></ul>
<p><strong>Common patterns:</strong></p>
<pre><code>&quot;Build X&quot; → Architecture skill + Implementation skills + Testing
&quot;Deploy Y&quot; → Containerization + CI/CD + Infrastructure
&quot;Debug Z&quot; → Troubleshooting skill + Domain skills
&quot;Optimize A&quot; → Performance skill + Profiling + Monitoring</code></pre>
<h3>Context-Aware Activation</h3>
<p><strong>Conversation history matters:</strong></p>
<ul><li>Previous skills activated inform current needs</li><li>Build on existing context (don&#x27;t re-read same skills)</li><li>Track what the user is working on across turns</li><li>Recognize continuation vs new topic</li></ul>
<p><strong>Project context signals:</strong></p>
<ul><li>Existing files mentioned → Infer tech stack</li><li>Error messages shown → Identify troubleshooting skills</li><li>Commands run → Understand current workflow phase</li><li>Git repo structure → Detect project type</li></ul>
<hr>
<h2>Patterns</h2>
<h3>Pattern 1: Technology Keyword Extraction</h3>
<pre><code class="lang-python"># Conceptual pattern (not actual code)
def extract_tech_signals(prompt: str) -&gt; list[str]:
&quot;&quot;&quot;Extract technology keywords from user prompt&quot;&quot;&quot;
tech_keywords = {
# Frameworks
&quot;next.js&quot;: [&quot;nextjs-*.md&quot;, &quot;react-*.md&quot;],
&quot;swiftui&quot;: [&quot;swiftui-*.md&quot;, &quot;swift-*.md&quot;, &quot;ios-*.md&quot;],
&quot;bubble tea&quot;: [&quot;bubbletea-*.md&quot;, &quot;tui-*.md&quot;],
&quot;ratatui&quot;: [&quot;ratatui-*.md&quot;, &quot;tui-*.md&quot;],
# Languages
&quot;zig&quot;: [&quot;zig-*.md&quot;],
&quot;swift&quot;: [&quot;swift-*.md&quot;, &quot;swiftui-*.md&quot;, &quot;ios-*.md&quot;],
&quot;go&quot;: [&quot;bubbletea-*.md&quot;] if &quot;tui&quot; in prompt else [],
&quot;rust&quot;: [&quot;ratatui-*.md&quot;] if &quot;tui&quot; in prompt else [],
# Platforms
&quot;modal&quot;: [&quot;modal-*.md&quot;],
&quot;heroku&quot;: [&quot;heroku-*.md&quot;],
&quot;netlify&quot;: [&quot;netlify-*.md&quot;],
&quot;aws&quot;: [&quot;aws-*.md&quot;, &quot;infrastructure/*.md&quot;],
# Domains
&quot;database&quot;: [&quot;postgres-*.md&quot;, &quot;database-*.md&quot;],
&quot;api&quot;: [&quot;api-*.md&quot;, &quot;rest-*.md&quot;, &quot;graphql-*.md&quot;],
&quot;testing&quot;: [&quot;test-*.md&quot;, &quot;unit-*.md&quot;, &quot;integration-*.md&quot;],
&quot;docker&quot;: [&quot;docker-*.md&quot;, &quot;container-*.md&quot;],
}
return [skill for keyword, skills in tech_keywords.items()
if keyword in prompt.lower() for skill in skills]</code></pre>
<p><strong>When to use:</strong></p>
<ul><li>User explicitly mentions technologies</li><li>Prompt contains framework/tool names</li><li>Clear technical domain identified</li></ul>
<p><strong>Example:</strong></p>
<ul><li>Prompt: &quot;Help me build a Next.js app with Postgres&quot;</li><li>Signals: <code>nextjs-<em>.md</code>, <code>react-</em>.md</code>, <code>postgres-<em>.md</code>, <code>database-</em>.md</code></li></ul>
<h3>Pattern 2: Intent-Based Skill Selection</h3>
<pre><code>Intent mapping:
├─ &quot;build&quot; / &quot;create&quot; / &quot;start&quot;
│ └─ Architecture + Setup + Testing skills
│
├─ &quot;debug&quot; / &quot;fix&quot; / &quot;error&quot;
│ └─ Troubleshooting + Domain skills
│
├─ &quot;deploy&quot; / &quot;production&quot; / &quot;ship&quot;
│ └─ CI/CD + Infrastructure + Observability
│
├─ &quot;optimize&quot; / &quot;improve&quot; / &quot;speed up&quot;
│ └─ Performance + Profiling + Monitoring
│
└─ &quot;learn&quot; / &quot;understand&quot; / &quot;explain&quot;
└─ Conceptual skills + Architecture patterns</code></pre>
<p><strong>Example workflows:</strong></p>
<pre><code class="lang-markdown"># Build intent
&quot;Build a REST API&quot; →
1. rest-api-design.md (architecture)
2. api-authentication.md (implementation)
3. postgres-schema-design.md (data layer)
4. unit-testing-patterns.md (quality)
# Debug intent
&quot;Debug slow Postgres queries&quot; →
1. postgres-query-optimization.md (direct solution)
2. database-connection-pooling.md (if pooling issue)
3. orm-patterns.md (if ORM N+1 problem)
# Deploy intent
&quot;Deploy to production&quot; →
1. dockerfile-optimization.md (containerization)
2. github-actions-workflows.md (CI/CD)
3. infrastructure-security.md (hardening)
4. structured-logging.md (observability)</code></pre>
<h3>Pattern 3: Multi-Domain Detection</h3>
<pre><code>Example: &quot;Build ML API on Modal with Postgres&quot;
Domains detected:
1. ML inference → modal-gpu-workloads.md
2. API layer → modal-web-endpoints.md, api-*.md
3. Database → postgres-schema-design.md
4. Cloud platform → modal-functions-basics.md
Skill chain:
modal-functions-basics.md (foundation)
→ modal-gpu-workloads.md (ML workloads)
→ modal-web-endpoints.md (API endpoints)
→ postgres-schema-design.md (data persistence)
→ api-authentication.md (security)</code></pre>
<p><strong>When to use:</strong></p>
<ul><li>Prompt mentions multiple technologies</li><li>Complex system with multiple layers</li><li>Full-stack or end-to-end projects</li></ul>
<h3>Pattern 4: _INDEX.md Quick Reference First</h3>
<pre><code class="lang-markdown"># Decision tree for skill discovery
User prompt received
↓
Is it a common task? (check _INDEX.md Quick Reference Table)
├─ YES: Read listed skills directly
└─ NO: Continue analysis
↓
Identify technology/domain keywords
↓
Search _INDEX.md by pattern:
- By Technology section
- By Task Type section
- By Problem Domain section
↓
Find category, read relevant skills
↓
Check &quot;Common workflows&quot; in category
↓
Activate skill chain</code></pre>
<p><strong>Example using _INDEX.md:</strong></p>
<pre><code>Prompt: &quot;Setup Heroku deployment&quot;
Quick Reference lookup:
| Deploy to Heroku | heroku-deployment.md, heroku-addons.md | 1→2 |
Result: Read heroku-deployment.md, then heroku-addons.md</code></pre>
<h3>Pattern 5: Workflow Composition</h3>
<pre><code>Complex workflow detection:
&quot;Build production-ready iOS app&quot; →
Layer 1 (Foundation):
- swiftui-architecture.md
- swift-concurrency.md
Layer 2 (Features):
- ios-networking.md
- swiftdata-persistence.md
- swiftui-navigation.md
Layer 3 (Quality):
- ios-testing.md
- web-accessibility.md (if applicable)
Read order: Layer 1 → Layer 2 → Layer 3</code></pre>
<p><strong>Heuristics for composition:</strong></p>
<ul><li>0-2 components → Read 1-3 skills</li><li>3-5 components → Read 4-7 skills</li><li>6+ components or &quot;production-ready&quot; → Read 8+ skills across layers</li></ul>
<h3>Pattern 6: Context Continuation</h3>
<pre><code class="lang-python"># Track conversation state
class ConversationContext:
active_skills: set[str] = set()
tech_stack: set[str] = set()
current_phase: str = &quot;unknown&quot; # setup, implementation, debugging, deployment
def should_activate_skill(skill: str, context: ConversationContext) -&gt; bool:
&quot;&quot;&quot;Determine if skill should be activated given conversation context&quot;&quot;&quot;
# Don&#x27;t re-read recently active skills (unless debugging)
if skill in context.active_skills and context.current_phase != &quot;debugging&quot;:
return False
# Activate complementary skills based on phase
if context.current_phase == &quot;deployment&quot;:
return skill in [&quot;ci-*.md&quot;, &quot;infrastructure-*.md&quot;, &quot;observability-*.md&quot;]
# Activate based on established tech stack
if &quot;modal&quot; in context.tech_stack:
return skill.startswith(&quot;modal-&quot;)
return True</code></pre>
<p><strong>Example:</strong></p>
<pre><code>Turn 1: &quot;Start Zig project&quot;
→ Activate: zig-project-setup.md, zig-build-system.md
Turn 2: &quot;Add tests&quot;
→ Activate: zig-testing.md
→ Skip: zig-project-setup.md (already covered)
Turn 3: &quot;Link to C library&quot;
→ Activate: zig-c-interop.md
→ Context: Still working on Zig project</code></pre>
<hr>
<h2>Quick Reference</h2>
<h3>Technology → Skills Map</h3>
<pre><code>Technology | Skill Patterns | Count
--------------------|---------------------------------------------|------
Next.js | nextjs-*.md, react-*.md, frontend-*.md | 8
SwiftUI/iOS | swiftui-*.md, swift-*.md, ios-*.md | 6
Modal.com | modal-*.md | 8
Zig | zig-*.md | 6
Go TUI | bubbletea-*.md, tui-*.md | 3
Rust TUI | ratatui-*.md, tui-*.md | 3
PostgreSQL | postgres-*.md, database-*.md | 8
REST API | rest-api-*.md, api-*.md | 7
GraphQL | graphql-*.md, api-*.md | 5
Docker | docker-*.md, container-*.md | 5
Kubernetes | kubernetes-*.md, infrastructure-*.md | 6
Heroku | heroku-*.md | 3
Netlify | netlify-*.md | 3
LLM Fine-tuning | unsloth-*.md, llm-*.md, lora-*.md | 4
Diffusion Models | diffusion-*.md, stable-diffusion-*.md | 3
React Native | react-native-*.md, mobile-*.md | 4
Lean 4 | lean-*.md | 4
Z3 Solver | z3-*.md, sat-*.md, smt-*.md | 3
Beads | beads-*.md | 4</code></pre>
<h3>Intent → Skill Priority</h3>
<pre><code>BUILD new system:
Priority 1: Architecture/setup skills (swiftui-architecture.md, zig-project-setup.md)
Priority 2: Implementation skills (domain-specific)
Priority 3: Testing/quality skills (test-*.md)
DEBUG existing system:
Priority 1: Troubleshooting skills (*-troubleshooting.md, *-debugging.md)
Priority 2: Domain skills (postgres-query-optimization.md)
Priority 3: Observability skills (structured-logging.md)
DEPLOY to production:
Priority 1: CI/CD skills (github-actions-*.md, cd-*.md)
Priority 2: Infrastructure skills (terraform-*.md, kubernetes-*.md)
Priority 3: Observability skills (metrics-*.md, alerting-*.md)
OPTIMIZE performance:
Priority 1: Performance-specific skills (*-performance-*.md, *-optimization-*.md)
Priority 2: Profiling/monitoring skills (metrics-*.md)
Priority 3: Architecture review skills (react-component-patterns.md)
LEARN technology:
Priority 1: Basics/fundamentals (*-basics.md, *-architecture.md)
Priority 2: Patterns/best practices (*-patterns.md, tui-best-practices.md)
Priority 3: Advanced/specialized (*-advanced-*.md)</code></pre>
<h3>Decision Matrix</h3>
<pre><code>Prompt Complexity | Skills to Read | Strategy
------------------|----------------|----------
Simple (1 tech) | 1-2 skills | Direct lookup in _INDEX.md Quick Reference
Medium (2-3 tech) | 3-5 skills | Check &quot;By Technology&quot; section, compose workflow
Complex (4+ tech) | 6-10 skills | Check &quot;Skill Combination Examples&quot;, use workflow chains
Unclear | 0 skills | ASK for clarification before reading skills</code></pre>
<h3>Common Patterns Quick Lookup</h3>
<pre><code>✅ DO: Check _INDEX.md Quick Reference Table first
✅ DO: Search by technology pattern (modal-*.md, zig-*.md)
✅ DO: Use &quot;By Task Type&quot; section for common tasks
✅ DO: Reference &quot;Skill Combination Examples&quot; for complex workflows
✅ DO: Compose multiple skills for multi-domain requests
❌ DON&#x27;T: Read skills before understanding user intent
❌ DON&#x27;T: Read all skills in a category (select relevant ones)
❌ DON&#x27;T: Re-read skills already active in conversation
❌ DON&#x27;T: Activate skills for technologies not actually used
❌ DON&#x27;T: Over-activate (10+ skills) for simple tasks</code></pre>
<hr>
<h2>Anti-Patterns</h2>
<p>❌ <strong>Reading skills before analyzing intent</strong>: Waste time reading irrelevant skills ✅ Extract intent first, then determine which skills apply</p>
<p>❌ <strong>Activating skills for unrelated technologies</strong>: User says &quot;iOS app&quot;, you activate Android skills ✅ Match technology signals precisely (iOS → SwiftUI, not Android)</p>
<p>❌ <strong>Over-activating skills</strong>: Simple &quot;add button to SwiftUI view&quot; → Read all 6 iOS skills ✅ Read only swiftui-architecture.md for component patterns</p>
<p>❌ <strong>Under-activating skills</strong>: &quot;Production Next.js app&quot; → Only read nextjs-app-router.md ✅ Activate frontend performance, SEO, testing, deployment skills too</p>
<p>❌ <strong>Ignoring conversation context</strong>: Re-reading same skill every turn ✅ Track active skills, only re-read if phase changes or debugging</p>
<p>❌ <strong>Not using _INDEX.md</strong>: Searching files manually instead of using Quick Reference ✅ Check _INDEX.md Quick Reference Table for common tasks first</p>
<p>❌ <strong>Missing implicit signals</strong>: &quot;TUI app&quot; → Don&#x27;t recognize Bubble Tea or Ratatui needed ✅ Map domain keywords to specific implementations (TUI → Bubble Tea/Ratatui)</p>
<p>❌ <strong>Flat skill activation</strong>: Read all skills without considering dependencies ✅ Follow skill workflows (foundation → implementation → quality)</p>
<hr>
<h2>Related Skills</h2>
<ul><li><code>skill-prompt-planning.md</code> - Planning responses and task breakdown after skill activation</li><li><code>skill-repo-discovery.md</code> - Discovering codebase structure to inform skill needs</li><li><code>skill-creation.md</code> - Creating new skills when gaps are discovered</li><li><code>beads-workflow.md</code> - Managing multi-step workflows that require skill composition</li><li><code>beads-context-strategies.md</code> - Preserving skill activation context across sessions</li></ul>
<hr>
<p><strong>Last Updated</strong>: 2025-10-18 <strong>Format Version</strong>: 1.0 (Atomic)</p>
<footer>
<div class="fmap">
<div><b>Build</b>
<a href="https://hanzo.app">hanzo.app</a> app builder
<a href="https://hanzo.codes">hanzo.codes</a> code with an agent
<a href="https://hanzoskills.com">hanzoskills.com</a> what an agent reads</div>
<div><b>Run</b>
<a href="https://console.hanzo.ai">console.hanzo.ai</a> cloud console
<a href="https://api.hanzo.ai">api.hanzo.ai</a> the API</div>
<div><b>Account</b>
<a href="https://hanzo.id">hanzo.id</a> sign in
<a href="https://pay.hanzo.ai">pay.hanzo.ai</a> top up
<a href="https://billing.hanzo.ai">billing.hanzo.ai</a> invoices and usage</div>
<div><b>Company</b>
<a href="https://hanzo.ai">hanzo.ai</a> canonical
<a href="https://hanzo.ventures">hanzo.ventures</a> ventures</div>
</div>
<div class="fend"><a href="/skill-prompt-discovery.md">This page as plain text</a> · <a href="/llms.txt">Index for agents</a></div>
</footer>
</div></body></html>