Skip to content

Add static marketing website and marketing audit under website/ #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
PredictabilityAtScale merged 1 commit into from
Apr 19, 2026
Merged

Add static marketing website and marketing audit under website/ #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,6 +330,10 @@ Prompt files use YAML front matter with these fields:
| `tiers` | `object` | Named tier overrides |
| `metadata` | `object` | `{ owner, tags, review_required, stable }` |

## Website

The `website/` directory contains a standalone marketing website for PromptOpsKit.

## License

[MIT](LICENSE)
209 changes: 209 additions & 0 deletions website/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,209 @@
<!doctype html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>PromptOpsKit | Open-Source Prompt Management Toolkit for Developers</title>
<meta
name="description"
content="PromptOpsKit is an open-source toolkit and CLI for versioning, validating, composing, and rendering AI prompts as code across OpenAI, Anthropic, Gemini, and OpenRouter."
/>
<meta
name="keywords"
content="PromptOpsKit, prompt management, prompts as code, OpenAI prompts, Anthropic prompts, Gemini prompts, OpenRouter, developer toolkit, prompt engineering"
/>
<meta name="robots" content="index,follow,max-image-preview:large" />
<meta name="author" content="Predictability at Scale, Inc." />
<link rel="canonical" href="https://github.com/PredictabilityAtScale/promptopskit" />

<meta property="og:type" content="website" />
<meta property="og:title" content="PromptOpsKit | Open-Source Prompt Management Toolkit" />
<meta
property="og:description"
content="Treat prompts as code with markdown authoring, schema validation, provider adapters, and a CLI for production workflows."
/>
<meta property="og:url" content="https://github.com/PredictabilityAtScale/promptopskit" />
<meta property="og:site_name" content="PromptOpsKit" />

<meta name="twitter:card" content="summary" />
<meta name="twitter:title" content="PromptOpsKit | Prompt Infrastructure for Developers" />
<meta
name="twitter:description"
content="Open-source toolkit and CLI to version, validate, and render prompts for OpenAI, Anthropic, Gemini, and OpenRouter."
/>

<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "SoftwareApplication",
"name": "PromptOpsKit",
"applicationCategory": "DeveloperApplication",
"operatingSystem": "Cross-platform",
"license": "https://opensource.org/license/mit",
"codeRepository": "https://github.com/PredictabilityAtScale/promptopskit",
"url": "https://github.com/PredictabilityAtScale/promptopskit",
"description": "Open-source developer toolkit for versioning, validating, composing, and rendering prompts as code.",
"offers": {
"@type": "Offer",
"price": "0",
"priceCurrency": "USD"
}
}
</script>

<link rel="stylesheet" href="./styles.css" />
</head>
<body>
<header class="site-header">
<div class="container nav">
<a class="brand" href="#top" aria-label="PromptOpsKit home">PromptOpsKit</a>
<nav aria-label="Primary">
<a href="#why">Why</a>
<a href="#features">Features</a>
<a href="#quickstart">Quick start</a>
<a href="#faq">FAQ</a>
<a href="#oss">Open source</a>
</nav>
<a class="button button-primary" href="https://github.com/PredictabilityAtScale/promptopskit">GitHub</a>
</div>
</header>

<main id="top">
<section class="hero container">
<p class="eyebrow">Open-source prompt infrastructure</p>
<h1>Ship AI prompts with the same rigor as application code.</h1>
<p class="lead">
PromptOpsKit is a developer-first toolkit and CLI for authoring prompts in Markdown,
validating schema and variables before runtime, and rendering provider-specific request bodies
without locking you into a transport stack.
</p>
<div class="hero-actions">
<a class="button button-primary" href="https://www.npmjs.com/package/promptopskit">Install from npm</a>
<a class="button" href="https://github.com/PredictabilityAtScale/promptopskit#quick-start">Read the quick start</a>
</div>
<pre><code>npm install promptopskit
npx promptopskit init ./prompts
promptopskit validate ./prompts --strict</code></pre>
</section>

<section id="why" class="container section">
<h2>Why teams adopt PromptOpsKit</h2>
<div class="grid three">
<article class="card">
<h3>Predictable prompt changes</h3>
<p>Store prompts in markdown with front matter so every change is diffable, reviewable, and auditable.</p>
</article>
<article class="card">
<h3>Portable provider output</h3>
<p>Generate request bodies for OpenAI, Anthropic, Gemini, and OpenRouter while keeping network logic in your app.</p>
</article>
<article class="card">
<h3>Safer releases</h3>
<p>Catch invalid schema, unresolved variables, and malformed composition before your production calls fail.</p>
</article>
</div>
</section>

<section id="features" class="container section">
<h2>Prompt management features for engineering teams</h2>
<div class="grid two">
<article class="card">
<h3>Authoring format engineers already trust</h3>
<ul>
<li>Markdown files with YAML front matter</li>
<li>H1 sections for system instructions and prompt template</li>
<li><code>{{ variable }}</code> interpolation and strict checks</li>
</ul>
</article>
<article class="card">
<h3>Composition and overrides without duplication</h3>
<ul>
<li><code>includes</code> for shared policy, tone, and safety blocks</li>
<li>Environment and tier-specific overrides</li>
<li>Deterministic precedence: base → env → tier → runtime</li>
</ul>
</article>
<article class="card">
<h3>CLI for local and CI pipelines</h3>
<ul>
<li><code>init</code>, <code>validate</code>, <code>render</code>, <code>inspect</code>, <code>compile</code>, and <code>skill</code></li>
<li>Pre-compile prompts to JSON/ESM artifacts</li>
<li>Use in pre-merge checks and release workflows</li>
</ul>
</article>
<article class="card">
<h3>No transport lock-in</h3>
<ul>
<li>Adapters return request body only</li>
<li>You keep control of auth, retries, headers, and observability</li>
<li>Integrates with existing HTTP and infra standards</li>
</ul>
</article>
</div>
</section>

<section id="quickstart" class="container section">
<h2>PromptOpsKit quick start</h2>
<div class="grid two">
<article class="card">
<h3>1) Install and scaffold</h3>
<pre><code>npm install promptopskit
npx promptopskit init ./prompts</code></pre>
</article>
<article class="card">
<h3>2) Render for your target provider</h3>
<pre><code>import { createPromptOpsKit } from 'promptopskit';

const kit = createPromptOpsKit({ sourceDir: './prompts' });
const result = await kit.renderPrompt({
path: 'support/reply',
provider: 'openai',
variables: { user_message: 'How do I reset my password?' }
});</code></pre>
</article>
</div>
</section>

<section id="faq" class="container section">
<h2>Frequently asked questions</h2>
<div class="grid two">
<article class="card">
<h3>Is PromptOpsKit only for one model provider?</h3>
<p>No. It supports OpenAI, Anthropic, Gemini, and OpenRouter adapters out of the box.</p>
</article>
<article class="card">
<h3>Does PromptOpsKit make HTTP requests?</h3>
<p>No. It returns request-body payloads so your app controls auth, transport, retries, and headers.</p>
</article>
<article class="card">
<h3>Can we validate prompts in CI before deploy?</h3>
<p>Yes. Use the CLI validate and compile commands in your CI pipeline to catch issues before release.</p>
</article>
<article class="card">
<h3>Is PromptOpsKit open source?</h3>
<p>Yes. The project is MIT-licensed and maintained in a public GitHub repository.</p>
</article>
</div>
</section>

<section id="oss" class="container section">
<h2>Open source and production-ready defaults</h2>
<p>
PromptOpsKit is MIT-licensed and designed for teams that need testable prompt operations.
Use source prompts in development and pre-compiled artifacts in production for speed and reliability.
</p>
<p>
Explore docs, examples, and API details in the repository.
</p>
<a class="button button-primary" href="https://github.com/PredictabilityAtScale/promptopskit">View repository</a>
</section>
</main>

<footer class="site-footer">
<div class="container footer-content">
<p>PromptOpsKit • MIT License</p>
<p><a href="https://github.com/PredictabilityAtScale/promptopskit">GitHub</a></p>
</div>
</footer>
</body>
</html>
77 changes: 77 additions & 0 deletions website/marketing-audit.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,77 @@
# PromptOpsKit Marketing Audit and Website Plan

## Scope

This audit reviews the current repository messaging (especially `README.md`), identifies conversion and clarity gaps for a developer audience, and proposes a standalone marketing site in `website/`.

## Current repo strengths

1. **Strong technical depth**: README explains architecture, provider support, overrides, composition, and API details.
2. **Real implementation credibility**: examples and CLI coverage signal production intent.
3. **Clear open-source positioning**: MIT license and explicit no-lock-in approach are present.

## Problems observed

### 1) README is optimized for existing users, not first-time evaluators

- The README has extensive details and many sections before a concise value hierarchy is established.
- New visitors must parse a lot of implementation material before understanding the product's outcome for teams.

**Solution in marketing site**
- Lead with a short developer value proposition.
- Add an immediate “why adopt” section with three concrete outcomes.
- Keep quick-start command block near the hero.

### 2) Value differentiation exists but is not tightly packaged for decision makers

- Differentiators such as “request-body-only adapters”, “overrides precedence”, and “pre-compile for production” are present but spread across sections.

**Solution in marketing site**
- Consolidate differentiators into scannable feature cards.
- Prioritize claims tied to operational outcomes: portability, release safety, and prompt governance.

### 3) The repo currently lacks a purpose-built landing experience

- There is no standalone page designed for top-of-funnel traffic from npm/GitHub/social links.
- No short narrative path from problem → capability → proof → CTA.

**Solution in marketing site**
- Add a static, framework-free landing page under `website/`.
- Keep this independent from library docs and package build/publish flow.

### 4) Design style in many AI-tool landers can feel generic

- Common patterns include heavy gradients, oversized “chip” labels, and highly rounded cards/buttons, which can reduce trust for technical audiences expecting precision and seriousness.

**Solution in marketing site**
- Flat background, restrained color system, low-radius corners, clear typographic hierarchy, and direct technical copy.

## Reference review (developer-focused OSS/product pages)

The proposed layout and copy structure were informed by public pages such as:

- LangChain product page patterns (clear value prop + adoption outcomes + CTA).
- LangGraph/LangChain ecosystem positioning (choose abstraction level for different teams).
- Supabase developer homepage structure (modular capability sections and clear open-source framing).
- Temporal messaging style (developer reliability + production outcomes).

## Information architecture for the new standalone website

1. **Hero**: one-sentence positioning + install/docs CTAs.
2. **Why adopt**: three outcome-focused cards.
3. **Features**: engineering workflow capabilities in compact lists.
4. **Quick start**: real commands and code snippet.
5. **Open source close**: governance and repository CTA.

## Packaging and distribution considerations

- The site lives in `website/` and does not affect runtime library code.
- npm package remains unaffected because publish `files` includes only `dist/`.
- This setup supports future deployment to any static host without changing package outputs.

## Next iteration recommendations

1. Add social proof (logos or usage metrics) once available.
2. Add “Architecture” section with one diagram for include/override/render pipeline.
3. Add benchmarks for parse/compile/validate latency.
4. Add docs deep-links per audience (library user vs platform engineer vs AI infra team).
4 changes: 4 additions & 0 deletions website/robots.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
User-agent: *
Allow: /

Sitemap: https://github.com/PredictabilityAtScale/promptopskit/blob/main/website/sitemap.xml
8 changes: 8 additions & 0 deletions website/sitemap.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<url>
<loc>https://github.com/PredictabilityAtScale/promptopskit</loc>
<changefreq>weekly</changefreq>
<priority>0.8</priority>
</url>
</urlset>
Loading
Loading