AI

Part 2 of a 5-part series on building production-grade skills for Claude Previous: Part 1: What Are Claude Skills | Next: Part 3: Building Your First Skill A skill is simply a folder with no special tooling, no compilation step, and no package manager required, yet the structure of that folder and the precision of its metadata determine whether Claude uses your skill effectively or ignores it entirely. File Structure your-skill-name/ ├── SKILL.md # Required: main instruction file ├── scripts/ # Optional: executable code │ ├── process_data.py │ └── validate.sh ├── references/ # Optional: documentation loaded as needed │ ├── api-guide.md │ └── examples/ └── assets/ # Optional: templates, fonts, icons └── report-template.md Critical naming rules: ...

Part 3 of a 5-part series on building production-grade skills for Claude Previous: Part 2: Anatomy of a Skill | Next: Part 4: Skill Patterns That Work The most effective skill creators start by doing the task manually with Claude, iterating until it works, and then extracting the winning approach into a skill rather than beginning with YAML. This part walks through that process. Step 1: Start With Use Cases, Not Code Before writing anything, identify 2 to 3 concrete use cases. A well-defined use case looks like this: ...

Part 4 of a 5-part series on building production-grade skills for Claude Previous: Part 3: Building Your First Skill | Next: Part 5: Testing, Debugging, and Distributing These patterns emerged from skills built by early adopters and Anthropic’s internal teams, and they represent common approaches that work well rather than prescriptive templates. Pick the one that matches your use case. Problem-First vs. Tool-First Before choosing a pattern, decide your framing: Problem-first: “I need to set up a project workspace” → Your skill orchestrates the right MCP (Model Context Protocol) calls in sequence, where users describe outcomes and the skill handles tools. Tool-first: “I have Notion MCP connected” → Your skill teaches Claude optimal workflows and best practices, where users have tool access and the skill provides expertise. Most skills lean one direction, and knowing which one helps you pick the right pattern. ...

Part 5 of a 5-part series on building production-grade skills for Claude Previous: Part 4: Skill Patterns That Work A skill that works in your head but breaks in production remains a draft until you validate it. This final part covers how to validate, debug, and ship your skills to users. Testing Approaches by Rigor Choose based on your audience: Approach Best For Setup Required Manual testing in Claude.ai Personal skills, rapid iteration None Scripted testing in Claude Code Team skills, repeatable validation Minimal Programmatic testing via Skills API Enterprise skills, CI/CD (Continuous Integration/Continuous Deployment) integration Moderate A skill used internally by a small team has different testing needs than one deployed to thousands of enterprise users. Match your rigor to your risk. ...

Part 1 of a 5-part series on building production-grade skills for Claude Next: Part 2: Anatomy of a Skill If you’ve ever caught yourself re-explaining the same workflow to Claude (your team’s code review process, your document formatting standards, your data pipeline methodology), skills solve that problem permanently by letting you teach Claude once so it applies that knowledge every time. A skill is a folder containing instructions, packaged as Markdown with YAML frontmatter, that teaches Claude how to handle specific tasks or workflows. Think of it as encoding your domain expertise into a reusable, portable unit that Claude loads on demand. ...

By Boris Cherny, Creator of Claude Code at Anthropic Originally posted as a thread on X: I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is… — Boris Cherny (@bcherny) January 31, 2026 I’m Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code – everyone’s setup is different. You should experiment to see what works for you! ...

Turning browser-automated AI into a 60-day ranking weapon — according to one of the world’s top-ranked SEO experts I don't understand why people aren't using Claude Cowork to crush local SEO. I CAN OUTRANK YOUR LOCAL BUSINESS IN 60 DAYS WITH JUST CLAUDE COWORK. Here's how I would do it: — Sarvesh Shrivastava (@bloggersarvesh) January 31, 2026 In late January 2026, Sarvesh Shrivastava — Favikon-ranked #1 SEO professional worldwide, TEDx speaker, and founder of Alventra Marketing — published a viral X thread that caught serious attention in the SEO community. The core claim was bold: ...

This is a talk I gave at DevFest Mt.Kenya, in November, 2025. AI Ethics in Africa: Building for Communities, Not Just Corporations — DevFest Mt. Kenya Region What Do I Feel? Ever seen a really good ad, could be about a music video that’s really cool, or maybe an application that helps you do some cool shit, then when you click on the link, you get that annoying message: “Not available in Your Country”, that’s exactly how I feel about most of these AI things that are happening. ...

Article Banner — This image is AI generated, looks great right! I suck at Canva (imagine that) The ideal topic would have been: The Secret Life of ChatGPT: What 700 Million Users Reveal About AI but that feels too “AI” generated. (another but …) but first Nerds for Stats Category Statistic Adoption 700M weekly active users (WAU) by July 2025 (~10% of world’s adult population) Message Volume 18B messages per week (~2.5B per day) by July 2025 Growth Factor 5× increase in daily messages between Jul 2024 and Jul 2025 Work vs Non-Work (Jun 2024) 238M non-work (53%), 213M work (47%) per day Work vs Non-Work (Jun 2025) 1.91B non-work (73%), 716M work (27%) per day Main Usage Categories Practical Guidance, Seeking Information, Writing = ~80% of all conversations Writing Use 40% of work-related messages; ⅔ editing/critique/translation vs ⅓ generating new text Tutoring/Education ~10% of all messages Programming 4.2% of all messages (contrast: ~33% of Claude’s work-related conversations) Relationships/Companionship 1.9% (personal reflection), 0.4% (games/role play) Interaction Types Asking = 49%, Doing = 40%, Expressing = 11% Work-Specific Breakdown 56% of work-related = Doing; ~75% of those are Writing tasks Work Activities (O*NET) 81% of work use = (1) getting/interpreting info, (2) making decisions/solving problems/creative thinking Demographics – Gender Early (2022): ~80% male names. By Jun 2025: 48% male, slight female majority Demographics – Age ~50% of all messages from users <26 years old Geography Faster growth in low- and middle-income countries Economic Value Estimated consumer surplus ≥ $97B in 2024 (U.S. alone) Oooh and if you hate numbers, I have some good graphs for you … ...

I had some good time playing around with Google’s NotebookLM, and I remembered there’s this project I do with Green World Campaign Kenya, that is somehow really hard to explain to normies(non technical people). So … Here’s something that may help … What is AIRS? The abbreviation? Sure, it’s Automated Incentives for Regenerative Stewardship Now, what really is AIRS? Automated Incentives for Regenerative Stewardship (AIRS) is an initiative that leverages satellite technology, on-ground observations, blockchain, and smart contracts to transparently reward Kenyan farmers for regenerative land stewardship, transforming their environmental achievements into tradeable digital assets. ...

Telegram bots are automated applications that run inside Telegram. Users can interact with bots by sending messages, commands, and inline requests. Today, we’ll walk you through how to build a simple Telegram bot using Node.js that provides weather and time information for any city. Prerequisites Before we start, make sure you have the following: Node.js and npm are installed on your machine. A Telegram account to create and manage bots. An API key from OpenWeatherMap. Setting Up Your Project Firstly, install the required Node.js packages: dotenv, node-telegram-bot-api, axios, and moment-timezone. ...