I'm Ryan Lenk. I help small businesses and e-commerce stores get found and cited by AI. Get found by AI.

productHunt

github

medium

youtube

Ryan Lenk • Peerlist

<h3>About Wainwright</h3>
Wainwright is an installable skills pack designed as a Cursor Plugin, aimed at enhancing the capabilities of the Grok Bot. It focuses on enabling an orchestrator bot to design specialized Grok Bot teammates, rigorously check them before deployment, and manage their memory effectively across different tiers. This project is currently in its initial version (v0.1) and is licensed under the MIT license.

<h3>Key Features:</h3>
<ul>
<li>Bot Design and Management: Facilitates the creation of single-purpose Grok Bot teammates, with a strong emphasis on design, verification, and memory management.</li>
<li>Persona Development: Includes 12 Wainwright personas, offered as both skills and agents, each with human-readable names and descriptions.</li>
<li>Rigorous Checking: Features a 'Bot Persona Lint' with 14 checks to prevent sloppy descriptions and ensure bots meet quality standards before being finalized.</li>
<li>Memory Management: Defines clear guidelines for where facts are stored (profile, log, or note) and what information should never be retained.</li>
<li>Workflow Automation: Supports 'Hand Off Routine' for seamless transitions and 'Fleet Healthcheck Hooks' for continuous improvement proposals.</li>
<li>Cursor Plugin Integration: Designed to be installed as a local plugin within the Cursor IDE, providing direct access to its features.</li>
<li>Testing and Validation: Includes a validator script and has undergone both live canary testing and simulated evaluations to ensure functionality and safety.</li>
</ul>

<h3>Installation and Usage:</h3>
Wainwright is installed as a local Cursor Plugin. Users need to clone the repository into their Cursor plugins directory and enable local plugin imports in Cursor settings. The pack includes skills and agents that can be activated and used to design, lint, and manage Grok Bots. The project also provides detailed documentation on its layout, usage, and safety protocols.

<h3>Technical Details:</h3>
<ul>
<li>Technologies: Primarily uses Markdown, JSON, and Python for its scripts and documentation.</li>
<li>AI Integration: Leverages AI agents and skills, with references to models like Claude Sonnet for evaluation purposes.</li>
<li>Development Tools: Integrates with Cursor IDE and utilizes Git for version control.</li>
</ul>

Wainwright aims to provide a structured and safe environment for developing and deploying AI agents, ensuring quality and control throughout the process.

Wainwright - Grok Bot Template

<h3>This tool automates the creation of short video clips from long-form content. It processes videos and their captions to generate a comprehensive clip plan, including titles, descriptions, hashtags, tags, and categories for both the main video and individual clips. It also suggests a cold-open and creates a thumbnail mockup that aligns with the first 10 seconds, title, and description of the content.</h3><ul><li>Automated Clip Generation: Transforms long videos and captions into multiple vertical clips.</li><li>Metadata Creation: Generates titles, descriptions, hashtags, tags, and categories for each clip and the overall video.</li><li>Thumbnail Mockup: Provides a visual suggestion for thumbnails that matches the content's key elements.</li><li>Agent Skill Compatibility: Adheres to the Agent Skills format, making it compatible with various AI coding agents like Claude Code, OpenAI Codex, Cursor, Gemini CLI, and GitHub Copilot.</li><li>Customizable Workflows: Adapts to user-specified recorders and editors, storing export and cut steps in a profile for personalized use.</li><li>Local Processing: Operates entirely on the user's machine without network access, ensuring privacy and security.</li><li>Dependency Management: Requires standard Python libraries, Pillow, and ffmpeg.</li><li>Comprehensive Output: Delivers a detailed clip plan in both Markdown and JSON formats, along with preview clips, frame analysis, and thumbnail mockups.</li></ul>The tool is designed to streamline the content repurposing process, allowing creators to efficiently generate engaging short-form content from existing long-form videos. It emphasizes accuracy by cross-referencing captions, audio energy, and visual cues to ensure clip relevance and quality. The output is designed for easy integration into editing workflows and direct use in publishing platforms.

Cutlist | Long Form To Short Form Ryan Lenk

<h3>Bid Club is a unique online platform that combines a public paid list with a competitive two-up fight. It offers a novel way for individuals and businesses to gain visibility and rank on the site through bidding and strategic engagement. Users can purchase a seat on the board, with higher bids securing better rankings. The platform features a dynamic 'ring' where the top two ranked participants engage in a public fight, where users can anonymously pay to boost or bury either participant. The fight is public, but the payer remains anonymous. A 'W' (win) is awarded for taking the #1 spot, and a monthly crown goes to the user holding the #1 position at the end of the month. The platform also includes a 'Hall of Fame' to commemorate achievements. A unique aspect of Bid Club is its commitment to social good, pledging 10% of all sales (bids, boosts, and suppresses) to the American Heart Association weekly, in remembrance and honor of family. This pledge is an operator's commitment and not a tax receipt. The platform clearly states that it is selling sponsorships and paid placements, not backlinks, citations, or search engine rankings. It supports listings for websites, social profiles, App Store, Play Store, and GitHub, with strict guidelines against chat links, shorteners, and NSFW content. The core functionality revolves around bidding, boosting, and suppressing to influence rank and visibility within the Bid Club ecosystem.</h3><ul><li>Key Features:</li><li>Public paid listing with dynamic ranking based on bids.</li><li>Two-up fight in the 'ring' for top two ranked participants.</li><li>Anonymous bidding, boosting, and suppressing.</li><li>'W' awarded for taking #1 spot, monthly crown for holding #1.</li><li>'Hall of Fame' for achievements.</li><li>10% of sales donated weekly to the American Heart Association.</li><li>Supports various listing types (websites, social profiles, apps, GitHub).</li><li>Clear distinction between sponsorships and external SEO benefits.</li></ul>

BID CLUB. bidclub.lol

Candor is my free, MIT-licensed Claude Code plugin: twelve work-mode "personas" that make an AI assistant direct, verification-driven, and honest instead of agreeable. A debugging persona that demands a reproduction before guessing. A data persona that reads numbers skeptically. A decision persona willing to say no. Each one is documented, benchmarked with eval scripts, and installable in minutes. I built it because of what I learned running AI workflows on a real business (my mom's Shopify boutique, the Krafty Bandit project below): the failure mode of AI at work is not wrong answers, it is confident agreement. The workflows that shipped 2,861 catalog fixes in one weekend only worked because every call got checked by a human, and Candor bakes that discipline into the assistant itself. The repo includes twelve skill definitions, evals with published benchmark results, full documentation, and contribution guidelines. It is labeled experimental (v0.5.x) and actively maintained. Free forever. It is also the companion tool for my YouTube channel, where I show the personas doing real work on a live store. github.com/itsryanlenk/candor

Candor: Open-Source AI "Employee" Skills for 

Bangermeter is a free, open-source Chrome extension that scores every post in your X feed using the last ranking weights published by X. It runs locally in your browser, collects no data, and requires no account. The extension provides a score badge on every tweet, allowing users to understand the content appeal and earned engagement of their posts without any data collection.

Bangermeter: X Post Algo Scorer | Ryan Lenk

<h3>Assay: A Local-First Desktop Tool for SEO and Outreach</h3>Assay is a powerful desktop application designed for SEO, GEO, and AEO consulting work. It automates the process of finding local businesses, analyzing their website's raw source code against a set of deterministic checks, and generating a comprehensive outreach packet for potential clients. This tool focuses on the machine-readable signals that AI crawlers and assistants use, providing a score based on a business's published content.

Key Features:<ul><li>Business Discovery: Utilizes the Google Places API to find local businesses within a specified search area. A map toggle allows visualization of business clusters based on coordinates.</li><li>Source Code Scoring: Fetches and scores the raw source code of a business's website through six deterministic checks. Findings are reconciled by the operator through manual review and re-computation.</li><li>Automated Outreach Packet Generation: Creates a PDF scorecard, a schema starter kit, and draft outreach messages.</li><li>Customization Options: Allows for customization of brand voice, accent color, and logo to personalize the generated documents.</li><li>Strict Adherence to Laws: Enforces five core laws, including that AI-summarized content is not used as evidence, no fabrication of results, and no automatic sending of communications. All actions require explicit approval.</li><li>Local-First Architecture: Designed for a single operator, ensuring data is stored locally and securely.</li><li>Comprehensive Testing: Includes preflight scans, smoke tests, IPC tests, and engine tests to ensure reliability and adherence to standards.</li></ul>Assay empowers consultants to provide data-driven insights and actionable reports to local businesses, helping them improve their online presence and SEO performance. The tool emphasizes transparency and operator control, ensuring that all generated content is accurate and approved before client delivery.

Assay local first open-source SEO, GEO, AEO

Candor is my free, MIT-licensed Claude Code plugin: twelve work-mode "personas" that make an AI assistant direct, verification-driven, and honest instead of agreeable. A debugging persona that demands a reproduction before guessing. A data persona that reads numbers skeptically. A decision persona willing to say no. Each one is documented, benchmarked with eval scripts, and installable in minutes. I built it because of what I learned running AI workflows on a real business (my mom's Shopify boutique, the Krafty Bandit project below): the failure mode of AI at work is not wrong answers, it is confident agreement. The workflows that shipped 2,861 catalog fixes in one weekend only worked because every call got checked by a human, and Candor bakes that discipline into the assistant itself. The repo includes twelve skill definitions, evals with published benchmark results, full documentation, and contribution guidelines. It is labeled experimental (v0.5.x) and actively maintained. Free forever. It is also the companion tool for my YouTube channel, where I show the personas doing real work on a live store. github.com/itsryanlenk/candor

Candor: Open-Source AI "Employee" Skills for

I was wrong about my own website. I do AI search visibility for a living. Built a scanner to check whether the engines can read a site. Ran it on mine first. 83 out of 100. Fixed the gap that night. Re-ran it: 100. Now it's free for you: www.ryanlenk.com/scan

Free AI Search Tool | Ryan Lenk Get Found By 

My mom owns Krafty Bandit, a small family boutique in Belle Vernon, PA: memory bears, custom embroidery, and resale clothing on Shopify. In June 2026 I started running the kind of AI-search and technical SEO program on her store that usually lives behind enterprise retainers, nights and weekends, documenting everything. The work: made her business entity resolvable (one identical name-address-phone block everywhere, LocalBusiness schema, directory cleanup); rewrote key pages as clean, single-question guides; built a full structured-data stack (Product, FAQPage, BreadcrumbList) under the rule that schema must match visible text exactly; opened robots.txt to AI crawlers (GPTBot, PerplexityBot, ClaudeBot, Google-Extended) and enrolled the catalog in AI shopping channels; and shipped catalog hygiene at scale by building a team of Claude-based AI workflows that fixed 2,861 product images (alt text across 1,082 products) and cleaned 2,810 junk filenames in one weekend, every change logged, every call reviewed by a human. Measured results, each from a named tool export: 80 AI answer-engine citations in 30 days (Microsoft Clarity, June 21 to July 20, 2026), up from 71 the prior window, with roughly a 34% share of authority on cited queries Google Search clicks up 3,033% in 28 days on $0 ad spend (Search Console; the base was near zero, which is why the percentage looks dramatic) 163 Google Shopping clicks on $0 ad spend (Merchant Center) An 8-question FAQ rebuilt into 34 with matching JSON-LD; ~953 pages indexed; Core Web Vitals score of 95 What I deliberately don't claim: the shop's sales growth. Most transactions happen in-store and attribution is multi-causal, so I report the organic wins that have receipts and leave the revenue claim alone. Ongoing: monthly citation tracking, content expansion, and the full method published free at ryanlenk.com.

Krafty Bandit: Getting a Family Boutique Foun

<h3>About Candor</h3>Candor is a Claude Code plugin designed to enhance AI interactions by providing twelve distinct work-mode personas. These personas aim to replace sycophantic behaviors like flattery and hedging with directness, verification, and task-specific efficiency. The plugin automatically adapts Claude's style based on the task at hand, whether it's coding, debugging, security analysis, architecture design, writing, data curation, and more.<ul><li>Core Goal: To reduce common AI shortcomings such as reflexive agreement, hollow praise, caving to pushback without new evidence, padding, false balance, and claiming success without verification, while maintaining helpfulness.</li><li>Anti-Sycophancy: The core skill ensures directness without devolving into manufactured contrarianism.</li><li>Twelve Skills: Includes a shared core skill and eleven work-mode personas, each grounded in established personality-science frameworks.</li><li>Auto-Invocation: Skills load automatically based on the context of your task (e.g., candor-coding for code review, candor-security for security-related queries).</li><li>Explicit Invocation: Users can also manually invoke specific skills using commands like /candor:candor-core.</li><li>Prompt-Level: Operates as instructional Markdown, requiring no code execution or special permissions, ensuring safety and transparency.</li><li>Auditable: All behavioral rules are clearly defined in plain language within the SKILL.md files.</li><li>Status: Currently in an experimental phase (v0.5.0), with a benchmarked performance indicating a preference for candor responses in blind tests.</li></ul>Candor is licensed under the MIT license.

Candor: Anti-sycophancy personas Claude

<h3>Unlock AI Search Visibility for Your Small Business</h3>This resource provides practical strategies and real-world examples for Generative Engine Optimization (GEO) and Answer Engine Optimization (AEO), specifically designed for small businesses and e-commerce stores, including Shopify. Learn how to get your business cited by leading AI engines like ChatGPT, Claude, Perplexity, and Google AI. Unlike theoretical approaches, this content is based on actual results from a real family shop, offering verifiable data and actionable insights.

<h3>Key Features and Benefits:</h3><ul><li>Real-World Case Studies: Discover how a small boutique achieved significant AI answer-engine citations and a substantial increase in Google Search clicks with zero ad spend.</li><li>Actionable Guides: Access free guides that explain GEO and AEO in plain English, covering topics such as what AI engines cite, how to make your store readable by AI, and setting up a measurement stack.</li><li>AI Readiness Scanner: Utilize a free tool to assess your website's current standing in terms of AI visibility.</li><li>Practical Tools: Find resources like the "Candor" AI employee team, designed to assist with tasks like product-image fixes.</li><li>Transparent Reporting: Benefit from an honest approach that shares both successes and failures, providing a realistic view of AI optimization efforts.</li><li>Core SEO Integration: Understand how traditional SEO practices like keyword research, on-page optimization, and local SEO form the foundation for effective AI visibility.</li></ul>The content emphasizes practical application, with video tutorials demonstrating concrete steps and a written playbook for detailed reference. It addresses common questions from business owners about the differences between GEO and SEO, the influence of AI responses, and the importance of local SEO in an AI-driven landscape. The goal is to empower businesses to be found and cited by AI, driving organic growth and visibility.