If you are retyping context and re-explaining tasks in every single chat, three skills fix that permanently, and you only have to build them once. The first is /how-to. It takes any task from start to finish, even one you have never done, by turning a simple prompt into a full step-by-step plan and asking you the right questions along the way. Add ELI5 and it explains the plan simply instead of technically. To create it, download the skill file, go to Claude, Customize, Skills, and upload it, then type /how-to plus whatever you want to do in any chat. The second is /about-me. It saves your context once, who you are, how you work, what good looks like, and loads it only when you invoke it, not on every message. This matters more than it sounds. Burying your context in global settings so it is always on makes Claude circle back to the same answers and kills creativity. A skill that loads on demand keeps that context available without letting it flatten everything you ask. To create it, take your old about-me file, ask Claude to turn it into a skill, upload it, and invoke /about-me whenever a task actually needs that context. The third is /skill-creator, the skill that builds the other two. It interviews you, compiles your instructions into one skill file, and saves them under a name you can load anytime with a slash command. You can also share it with your whole team through Customize, Skills, Share. To create it, type /skill-creator in any chat and answer the questions, or just ask Claude directly to make it a skill. Bookmark this before you write the same explanation into Claude for the five hundredth time.

this is how i make AI videos people think are real.. Claude Opus 5.5 wrote the scenes. Seedance 2.5 on PromptWise made them real This is the part most people hide, so here’s the full breakdown👇

We’ve raised $85M for this moment. Introducing Warp 2.0: The first AI Head of HR. Every company is building AI to replace jobs. Warp is building AI to do the jobs no human should have to: If you work in HR, I want you to spend time with the manager who needs help or building company culture people actually want to work at. If you’re a founder, I want you to focus on signing clients or spending time with your family. You shouldn’t have to figure out how to register state tax in California. You shouldn’t have to pay outrageous penalties because you don't know what a DE 9C is. I want to make HR human again. Today, this is finally possible with the Warp Agent. I’d love for you to see it in action: warp.co/agent

Today we're releasing Mk1.5: a new intelligence layer for embodied agents. It flies drones, controls quadrupeds, powers smart glasses, tracks objects, searches the web, reasons visually, and dispatches its own sub-agents. One model, no platform-specific retraining. 🧵

Spent the weekend deep-diving into WorkSwarm's source code and honestly, the coordination layer is what stuck with me most. It doesn't just add more agents. It turns individual AI workers into a coordinated system where specialized agents divide complex tasks and hand off work as the workflow progresses. WorkSwarm by openJiuwen makes that possible. A few things that stood out: → Multi-agent collaboration with different models for different roles → Persistent Sessions that keep roles, decisions, and ownership stable over long workflows → RSI framework that uses real task feedback to propose, execute, and verify improvements Open source under Apache 2.0. Worth a look if you're building agent systems. GitHub 👉 github.com/openJiuwen-ai/jiu… #AI #Agent #openJiuwen #WorkSwarm

Opus 5.5 beats Jev and GPT-6 Sol in 3 moves: Rubik’s Cube race We made 4 models run with same limits for all: 20 moves or 5 minutes. Every move = 1 API call. Results: Opus 5.5: solved in 1m 12.87s with the perfect 3 moves GPT-6 Sol: wrong first move, out of time after 4 moves Jev: 20 moves in 20 seconds, ran out of moves Laya: 20 moves in 9.5s, ran out of moves Opus, GPT, and Jev ran via aimlapi.com, Laya ran locally.

If you want ChatGPT to recommend your business when someone asks who they should buy from, there is a pretty straightforward opportunity hiding in plain sight. New data across 289,105 cited URLs across ChatGPT, Google AI Mode, AI Overviews and Perplexity offers a unique window into what matters most. Let’s go through it. And if you want to see whether ChatGPT, Claude, Google AI, Perplexity, Grok and broader AI search are already recommending your business, start here (it's free): seo-stuff.com/free-audit Surfer analyzed nearly 1000 prompts across 12 industries, generating 26,573 AI calls and 289,105 cited URLs over seven days. Then they asked a fairly simple question: When an AI system recommends several brands, is there a relationship between how prominently each brand appears and how many of the cited sources mention that brand? Spoiler alert: there was. Brands mentioned across a larger share of the sources being used by the AI tended to appear higher in the response. Obviously that does NOT mean Surfer proved that brand mentions cause higher AI rankings, but the relationship is strong enough that businesses working on AI visibility should probably pay attention. Think about how this can work. Someone asks: “What are the best accounting platforms for a small nonprofit?” The AI retrieves information from several sources. Maybe multiple articles mention Company A, compare it with competitors and describe its use cases. Company B appears once. Company A now has a much larger body of information surrounding it across the source set. Your website matters, but the wider web matters too, and the results became even more interesting when Surfer broke them down by platform. ChatGPT showed the strongest relationship between brand presence across cited sources and recommendation position among the systems tested. It also cited substantially more sources in this dataset: 84.7% more than Google AI Mode and 129.7% more than Google AI Overviews. So if ChatGPT is working from a larger source pool, there are potentially more places where your brand can either appear or be absent. This is why treating AI Search Optimization as something that happens entirely on your own website does not make much sense. Your website is one source and the system may be looking at many others. And if your competitors repeatedly appear across those sources while your business does not, they are giving the AI a much broader information footprint to work with. That is exactly why SEO Stuff combines content with authority: seo-stuff.com/gold-plan-pack… The content side helps your own website explain who you are, what you do, who you serve, which problems you solve, how you compare and what buyers should know. The authority side creates additional third-party references around the company. There is an important distinction here though, as this study measured BRAND MENTIONS, not backlinks. A backlink can still matter for traditional SEO, but Surfer measured whether the cited page actually mentioned the brand. That means a good editorial placement can potentially do two different jobs. It can provide a legitimate backlink that supports traditional search authority, while also putting your brand, category and context onto a third-party page an AI system may encounter. The research found something particularly interesting about blogs too. Brand-owned blogs represented 16.2% of cited sources and third-party blogs another 12.5%, meaning blogs accounted for 28.7% of the cited source set. But brand mentions appearing in blog content showed the strongest correlation with recommendation position of any content type Surfer analyzed. That matters because blogs are one of the areas businesses can actually influence. You can publish useful content, create original research, contribute expert commentary, earn editorial coverage and get included in relevant industry articles. But one of the most valuable things you can do is identify the pages AI systems already cite for the commercial questions your customers ask. Do not just think: “I need more backlinks.” Think: “What does ChatGPT cite when someone asks who the best company in my category is?” “What sources does Google AI Mode use?” “Which comparison pages keep showing up?” “Which of those pages mention my competitors but not me?” That creates a much more useful target list than simply sorting websites by Domain Rating. If you're starting from scratch today, here's how I'd play it: Start with the commercial questions that matter, then look at the sources AI systems actually use when answering them. Which brands keep appearing? Which websites keep getting cited? Where are competitors mentioned? Where are you missing? Then work on both sides. Build your own content so AI systems have accurate, useful first-party information about your company, and build a credible third-party footprint so your website is not the only place on the internet associating your brand with the category. That is increasingly what AI Search Optimization looks like. Useful content, commercial topic coverage, clear brand information, relevant third-party mentions and contextual authority across the web. And if you want to see where your business currently stands across ChatGPT, Claude, Google AI, Perplexity, Grok and broader AI search, start here: seo-stuff.com/free-audit