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

Ryan Lenk  • Peerlist

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.