Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jezweb/claude-skills --skill product-showcasegit clone --depth 1 https://github.com/jezweb/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jezweb/claude-skills/product-showcase)<a href="https://agentmods.dev/skills/jezweb/claude-skills/product-showcase"><img src="https://agentmods.dev/badge/skills/jezweb/claude-skills/product-showcase/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jezweb/claude-skills/product-showcase"><img src="https://agentmods.dev/badge/skills/jezweb/claude-skills/product-showcase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 382 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00117 | $0.04975 |
| Opus 5 | $0.00059 | $0.02488 |
| Sonnet 5 | $0.00023 | $0.00995 |
| Haiku 4.5 | $0.00012 | $0.00498 |
Grade A, and why
product-showcase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Showcase Generator
Generate a marketing website that actually teaches people what a web app does. Not just a hero and feature grid — a multi-page site with real screenshots, animated GIF walkthroughs of workflows, feature deep-dives, and progressive depth from "what is this" to "here's exactly how it works."
Especially valuable for complex apps, agentic AI tools, and anything where a static screenshot doesn't convey the value.
Depth Levels
| Depth | Output | Duration |
|---|---|---|
| quick | Single page — hero, features, CTA. Same as before. | 15-20 min |
| standard | Multi-page site — home, features page, how-it-works with screenshots. | 1-2 hours |
| thorough | Comprehensive site — home, per-feature pages, animated GIF walkthroughs, use cases, comparison page, docs-style demo. | 3-6 hours |
Default: standard
Browser Tool Detection
Before starting, detect available browser tools:
- Chrome MCP (
mcp__claude-in-chrome__*) — preferred for authenticated apps - Playwright MCP (
mcp__plugin_playwright_playwright__*) — for public apps - playwright-cli — for scripted flows
Workflow
1. Gather Input
| Field | Required | Example |
|---|---|---|
| App URL | Yes | https://app.example.com or http://localhost:5173 |
| App name | Yes | "Acme CRM" |
| Tagline | No | "The CRM that gets out of your way" |
| Target audience | No | "Small business owners" |
| Pricing info | No | Free tier, $29/mo pro |
| CTA text + URL | No | "Start Free Trial" → signup page |
| Testimonials | No | User provides or skip section |
2. Capture Screenshots
Use capture-screenshots (shipped in bin/) to capture the app. This is faster and more consistent than generating Playwright scripts each time.
Quick capture (all key pages at once):
capture-screenshots http://localhost:5173 \
--pages /,/dashboard,/contacts,/settings \
--output showcase/screenshots \
--prefix screen \
--mobile --dark
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 488 lines · 117 tokens per session scan A f815f7392056
product-showcase is a skill published in the GitHub repository jezweb/claude-skills (1,001 stars, last pushed 2mo ago), licensed MIT. It adds 117 tokens to every session and 4,975 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ensemble-solving
Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality.
code-transfer
Transfer code between files with line-based precision. Use when users request copying code from one location to another, moving functions or classes between files, extracting code blocks, or inserting code at specific line numbers.
feature-planning
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.
review-implementing
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
codebase-documenter
Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.
conversation-analyzer
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.