You've Never Used Claude Code Skills Like This

Go on any social media site right now and you'll find different tribes rooting for different language models. You have team Claude, team Codeex, and team Gemini, as well as team every other language model on the planet. Everyone's got a laundry list of why their model choice is the absolute best compared to others. But instead of being pushed to pick a side, why not just use all of them? What if you could keep cloud code as your daily driver, but tap into the intelligence of Gemini and Codeex and whatever is the latest and greatest whenever you need it? I built a skill around this. And in this video, I'm going to show you how you can do it, too. It's a mega skill that lets you tap on the shoulders of giants and leverage any model you want depending on where you think these other models fit best. Let's dive in. So, the general concept is very simple. Instead of bickering about what model is the best today, whether it's 5.3 codeex, 5.9, 6.1 opus, whatever is going to be the next set of models, you can just focus on what works. And the way I've constructed the skill that I will give you by the end of this video is basically combining cloud code with open router. If you're not familiar with what open router is, it is essentially a service that lets you access all kinds of language models. So even though I'm primarily harping on Gemini and Codeex as the alternatives, you can choose whatever you want. If you think that Quen models are amazing at coding, you can leverage those and you can now create a pseudo council for your Claude code language model. So the way I'll put this council in action is I'll ask Claude code to do a task that I would typically do just with no language models whatsoever. And then I'll show you the power of being able to say, "Let's get a second opinion on this website, this app, this whatever that you can bring in a third-party source like Gemini to take a look at your front end and be like, "Step aside. I got this. Here's my advice on what you should do." And then Claude Code can take set advice and implement it. Same thing with Codeex. I actually use Codeex quite a bit for bug fixing. Once in a while, Opus will get stuck on a bug and instead of constantly spinning, I'll bring in something like Codeex to take a look at the entire codebase and [music] give me its best opinion on what's going wrong. Now, you might have your own opinions on which models are best for what. I totally respect them. Everyone has different use cases in different applications. So, without further ado, let's take a look at this skill. And what I've called it is just council. You can name it whatever you want. And I created it. So, it's a slash command as well. I can do / counsel and it will know that I'm trying to invoke the third party powers of a different language model or multiple for a particular problem. The description is get second opinions from competing AI models open AAI Google again you can add whatever you want here via open router without leaving cloud code important this skill takes priority over another skill that I have in my system so you can ignore that part. Trigger phrases would be get a second opinion ask Gemini ask GPT ask codeex consult. It just gives it a series of different ways to be triggered and invoked that are semantically similar. And the last thing I say here is never call Gemini or OpenAI's APIs without my direct intention to do so. So in terms of the rest of the scale, it's pretty straightforward. We have the overall setup where you'd have to just grab an API key from Open Router. You would throw it into the N file and then beyond that, you'd have three invocation methods. You already saw a few in the description. This goes a little bit deeper into others. And this config file is actually the most important part of this skill. And this is the part where you will want to chime in as the user. And I'll grab it over so we can take a look. And we'll zoom in so you can see exactly how it's structured. So if you are non-technical, there's nothing you actually have to worry about from a coding perspective. You just have to verbally tell cloud code to change this file whatever way you want. So in this case, I walk through the providers I really care about and then it figured out from the open router API how to call those models. So when we look at defaults, then you can say that when there's a bug fix that Opus for whatever reason can't fix, we'll bring in the powers of 5.3 codecs. And when it comes to front end, we can say to use the powers of Gemini 3.1 Pro preview or whatever latest model that is out by the time you're watching this. And you can do the same thing for architecture refactoring, anything in general or quick check. So quick check on front end could use Gemini 3 flash, which is still a very capable and pretty cheap model. And then as we go down we have different categories where we go deeper as to what to look for. Let's say the words bug fixes, error diagnosis, etc. And when to invoke different things like the bug fix, like the front end, and like the architecture language model. And just to make sure we're sending the right information to the right model at the right time, we have this section that's called context packaging. So I said when sending context to another model, include one, the specific question or problem statement. Two, relevant code snippets. This is probably the most important because if you want a proper consult, you should provide snippets of the existing code to see the opinions of other language models. And then this one is really important. What other approaches have been tried? So in a way you're having these office hours with different language models that are aware of what you've tried, what you want to do, and where you might be stuck. And then they can give their holistic opinion [music] in that way. And this is the last part I'll show that brings everything together, which are these synthesis rules. So after receiving a response from the council, present the raw response clearly labeled with the model name. State agreement or disagreement. So I want Claude code to chime in and be like, I agree somewhat with Gemini's take or Codex's take, but it's made me think of another solution. That's the goal. These are language models. So why not have the predictions of one improve and amilarate the predictions of the other? The last element here is the execute best approach. So end of the day, you're going to have different language models have egos about which one is right. But ideally, I want Claw to always pick the path of least resistance, even if that path wasn't carved by itself. Now, that's a run through of the skill. Let's actually put it to the test. So, if we open a terminal and I say something in one terminal, like, can you spin up a landing page for a new Claude Code boot camp? And it's a boot camp for someone that is more on the intermediate end. create a full landing page, a whole program, come up with pricing and spin up the resulting web page on local host. So, we will send this in two different terminals. Naturally, with language models, you'll have two slightly different results. With one, we'll keep it as is. With the other, I'll show you how just bringing in different opinions from different language models can change the entire equation. After a few minutes, we got two different websites from the two different terminals. Now, the first one looks like this. Nothing too crazy. Looks like a standard website. Could be a little bit easier on the eyes from a font perspective. And the second one is the exact same command. I just asked it to create a brand new folder. So this one looks like this. So stop prompting, start shipping, a little bit better hero statement. But the rest of this looks pretty similar. You can see the fonts are very similar. So what can we do to improve one versus the other? So this first tab, the website no cancel will act as our control. We're not going to change this at all. Whereas we're going to make only one set of changes using different language models just to show you how quickly you can improve things. So if we go to website council and we go to the bottom, I'll use my slash command slashcounsel and then this should now pose a question back to me. I'm already going to preemptively draft it and say the following. Okay, I want you to take a look at the web page that was put together and I want you to audit it from both a front-end perspective as well as a copy perspective. I want you to send snippets of the front-end code to Gemini 3.1 Pro and I want to send the copywriting to codeex to get their opinions on what are the best practices if we should keep things the same or improve them and if we should improve them in what way. So, a bit of a mouthful. And as I inhale oxygen, I will send this over and show you the result. And after 4 minutes, the skill comes back with a proposal for a front end as well as a copywriting set of changes. On the front end, it says what's working. So, at least the language model is understanding that things don't need to be fully rewritten from scratch, but it does flag some issues. So this goes into the spacing, the grids, the fact that mobile friendly is not optimized and then it proposes some changes. Then the same thing happens with codecs on the copyrightiting side. Then flags, it's basically like having a LLM as a judge except you get to tap into an LLM as a judge from a different language model that might have different pros and cons. And then this is the part that we should really care about which is clawed code synthesis. So, it agrees. It doesn't have an ego in this case. With both reviews on the high priority items, here's what I would prioritize. So, now you give Claude code the driver's seat taking consultations from these models. On the must fix, it says split typography, fix grid, add focus, smooth FAQ animation. Same thing on the copy. And then it says, okay, these are the things that are worth testing that they mentioned. And then it says, do you want me to implement any of these changes now? I do. It takes 5 10 minutes. And we get a much better version right here where it's deeper in terms of the outcome. It's better organized. Some things here, especially on the font, look a lot cleaner. The numbers here specifically look way better than it used to before. And overall, it's a lot tighter. It has some more FAQs. It has better pricing, more detailed and thoughtful pricing. And we did all this technically with just a single prompt. Now, let's say that was a complete fluke. Let's apply it to another scenario and see how it behaves. So if I say here create a new folder and create an analytics dashboard showing some mock data for a venture capital firm and then I tell it to spin up on a different port. It will go and it then created something like this which is okay. It's not the prettiest but it's manageable. And then the other version looked pretty rough as well. But in this case, we did the exact same thing and then we ran an audit sending the exact same prompt. And just to experiment, I sent this prompt right here without even invoking the slash command just to see if I sent it, would it be able to pick up the skill and then invoke it. In this case, it executes the council plan, asks me if we should proceed. Then it goes through and brings a very heavy front-end audit. So, it tells me what's solid, what are the top fixes. Same thing with Codeex. On the copy side, it scores it seven out of 10 and it comes up with both the issues as well as its proposed fixes. The main moral of this is that you don't have to just blindly [music] follow what these other language models are proposing. They can just add some more brainstorming. They can make you think more out of the box and you might not go with any of these, but you might come up with your own from having seen what they come up with. And again, Claude says here, "My take. I agree with both models on high priority items." And then where I'd push back slightly. Codeex's suggestion to rename markups, markdowns to unrealized value uplifts is technically correct, but for a dashboard, the shorter labels are fine. So there is this level of judgment while still taking the different pieces of advice into account. In this case, I just had Cloud Code blindly follow their suggestions and integrate it into its plan. And it came up with this very Bloomberg terminal looking UI that I think could be better, but overall looked infinitely better than the initial one. again with just one prompt taking external perspectives into account. And you can apply this skill to all kinds of scenarios, especially non-technical scenarios where you can bring in different language models with different strengths. You can even take the same language model like Claude and go through different versions of it to see what versions might say about the exact same task. So you could check Haiku, you could check sonnet, and you could check Opus all on the exact same task or the exact same copy or whatever it is you're trying to accomplish. So hopefully that shows you the power of creating a mega skill. And the beauty of these mega skills is you can combine them with additional skills, let's say the front-end skill, and create some form of symbiosis between both of them. So the more skills you can stack and the deeper you can make them, the higher leverage you'll have. And like I said, I'll attach the skill that I showed you in this video in the second link in the description below. And if you want access to my exclusive mega skills, then you'll want to check out the first link in the description below for my early AI adopters community. And for the rest of you, if you found this helpful, you found it novel, and you want to see more, then please leave me a like and a comment on the video. It really helps the video and the channel.

Join Early AI Dopters: https://www.skool.com/earlyaidopters/about Get the Council Skill: https://markkashef.gumroad.com/l/council-skill-claude-code --- Everyone's on a different AI team. Team Claude. Team Gemini. Team Codex. But why pick a side when you can use all of them? In this video I show you how I built a Claude Code skill called Council — a mega-skill that keeps Claude as your daily driver while tapping into Gemini, Codex, or any model on OpenRouter whenever you need a second opinion. Right model, right task, right time. No more switching apps, no more tribal loyalty. I demo it live on two builds: a Claude Code bootcamp landing page and a VC analytics dashboard. In both cases the council audit catches things Claude missed and the final result is noticeably better. I'm giving the skill away free — link above. --- Timestamps 00:00 - The tribal AI debate (and why it's a waste of energy) 00:30 - Introducing the Council skill 01:05 - Claude Code + OpenRouter explained 01:29 - What the council actually does 02:17 - Full walkthrough of the skill 03:04 - Setup: grab your OpenRouter API key 03:21 - The config file (the most important part) 04:32 - Context packaging 05:10 - Synthesis rules 05:49 - Time to test it 06:00 - Demo 1: Claude Code bootcamp landing page 07:18 - Running /council to audit the page 08:00 - Council results: frontend + copy audit 09:11 - The improved version 09:36 - Demo 2: Analytics dashboard for a VC firm 10:07 - Gemini 3.1 Pro frontend audit 10:34 - Codex copy audit 11:16 - Bloomberg Terminal-style result 11:33 - Applying this beyond technical use cases 12:15 - Get the skill free 12:20 - Early AI Dopters community --- Book a Consultation: https://calendly.com/d/crfp-qz3-m4z #claudecode #claudeskills #aitools #claudecodetutorial #openrouter #gemini #codex #aiautomation #anthropic #llm