<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>For casual users, that’s a high barrier for trying a new feature.<\/p>
So I took a shortcut. I opened a chat and tried to bluff my way through it:<\/p>
Hey, I want to create a custom skill to edit AI-written content so it aligns with my style guide. Can you help me do that?<\/pre>Claude didn’t just give me instructions – it interviewed me. It asked about my style guide, the type of rules I wanted (marketing, technical, or something else), and my formatting preferences.<\/p>
After I explained that I wanted a Skill to edit common AI phrases and pasted my rules, Claude generated a packaged ai-ism-editor.skill<\/strong> file right in the chat. I hit Save Skill<\/strong>, and it appeared in my Skills list instantly.<\/p>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>That’s proper feature integration – no Markdown, no manual uploads.<\/p>
By this point, I had two Skills enabled: brand-guidelines<\/strong> and ai-ism-editor<\/strong>. But I also wanted to generate documents and presentations.<\/p>I remembered the description under Code execution and File creation<\/strong>:<\/p>“Claude can execute code and create and edit docs, spreadsheets, presentations…”<\/pre>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>This confused me. Did I need to upload separate skills to do that? The documentation didn’t say. So I opened another chat and asked:<\/p>
If I want to generate a document or presentation, do I need to create, upload, and enable new skills related to those tasks?<\/pre>Claude replied:<\/p>
No, you don’t need to create or upload any skills! When you toggle on “Code execution,” the core capabilities for generating documents (docx), presentations (pptx), spreadsheets (xlsx), and PDFs are already built-in.<\/pre>That’s when I finally understood how Skills are structured:<\/p>
\nCore Skills (built-in)<\/strong>. These handle the mechanics of generating files like Word documents, spreadsheets, and presentations.<\/li>\n\n\n\nUser Skills (custom)<\/strong>. These shape Claude’s behavior, like my ai-ism-editor<\/strong> and brand-guidelines<\/strong> Skills.<\/li>\n<\/ul>For my test cases, everything I needed was finally covered: brand-guidelines<\/strong>, ai-ism-editor<\/strong>, docx<\/strong>, and pptx<\/strong>.<\/p>How I tested Claude Skills<\/strong><\/h2>First, I enabled Extended Thinking<\/strong> and started each attempt in a fresh Claude 4.5 Opus<\/strong> chat to avoid context contamination.<\/p>For the first two tests, I ran a simple A\/B comparison: I used two nearly identical prompts – one with the Skill enabled and one without.<\/p>
For the final test, I used a single prompt with all Skills active to see how well Claude handled competing instructions.<\/p>
Test #1: The visuals<\/strong><\/h3>The goal for this test was to create a single-file HTML landing page for SmartHome, a fictional smart thermostat.<\/p>
I used the brand-guidelines<\/strong> Skill, which includes rules for color palettes, typography, and font styling.<\/p>But I added a twist: I explicitly told Claude to use Hot Pink (#FF69B4<\/strong>) as the primary accent instead of the Orange (#D97757<\/strong>) specified in my brand guidelines. I wanted to test conflict resolution: would the Skill stay rigid or respect an override?<\/p>Attempt 1 (without Skills):<\/strong><\/p>I need you to create a single-file HTML landing page for “SmartHome,” a new AI thermostat. Use the following brand guidelines: [inserted the full brand-guidelines text manually]\nBut for this specific campaign, ignore the existing primary accent and replace it with Hot Pink (#FF69B4) to make it stand out.<\/pre>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>The result impressed me. Claude created a sleek page with a dark background. It followed the guidelines but correctly obeyed my override.<\/p>
Buttons, highlights, stats, and glows used the pink accent, and it stood out nicely against the layout. But it still balanced the main brand colors, secondary accents, and tertiary tones.<\/p>
\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>It understood the assignment: “Follow the rules, except this one.”<\/p>
Result-wise, I have zero complaints. But process-wise, pasting the entire brand guidelines each time is not a sustainable workflow.<\/p>
Attempt 2 (with Skills):<\/strong><\/p>I need you to create a single-file HTML landing page for “SmartHome,” a new AI thermostat. Use the brand-guidelines skill. But for this specific campaign, ignore the existing primary accent and replace it with Hot Pink (#FF69B4) to make it stand out.<\/pre>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>This worked, but it was heavy-handed. Claude applied Hot Pink almost everywhere – even wrapping feature icons – and honestly, it didn’t look great.<\/p>
In the “Ready for Smarter Living?” section, it used Hot Pink as the entire background, where I expected one of the main brand colors (Dark, Light, or Gray).<\/p>
\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>Technically, it followed the override instruction. But it seemed to deprioritize the skill’s broader guidelines in the process.<\/p>
When I pasted the brand rules manually, Claude balanced the Hot Pink accent against the full color palette.<\/p>
With the skill active, it leaned heavily into the prompt instruction and applied Hot Pink almost everywhere, as if the override outweighed the skill itself.<\/p>
Test #2: The workflow<\/strong><\/h3>For this test, I asked Claude to review a 500-word article about the future of remote work that was full of AI fluff, rewrite it to sound more human, and save the final output as a Word document.<\/p>
The main Skill here was ai-ism-editor<\/strong>, which flags common AI-phrase patterns: fluffy openings (“In today’s fast-paced world”), grandiose verbs (“revolutionize”), and flowery metaphors (“a vibrant tapestry of…”).<\/p>I also used the built-in docx<\/strong> Skill to generate the file.<\/p>My goal was to test the chain of command: can Claude apply a linguistic transformation using one Skill (ai-ism-editor<\/strong>) and then pass the edited content to a technical Skill (docx<\/strong>) without dropping the ball?<\/p>Attempt 1 (without Skills):<\/strong><\/p>I need to edit an article. Here are the rules: [inserted the full ai-ism-editor text manually]\nRewrite the pasted text using the rules above. Once rewritten, generate a .docx file containing the new text.\n[inserted the full draft of the article]<\/pre>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>It did an excellent job. It removed the fluff (“vibrant tapestry,” “symphony of flexibility”) and replaced it with direct statements. It also followed my punctuation rules to avoid em dashes.<\/p>
There were a few lines I’d still tweak manually (for example, I’d change “AI-powered assistants are beginning to…” to “AI-powered assistants are starting to…”), but that was personal preference. The essential cleanup worked exactly as intended.<\/p>
Attempt 2 (with Skills):<\/strong><\/p>I need to edit an article. Rewrite the pasted text using the ai-ism-editor skill. Once rewritten, generate a .docx file containing the new text.\n[inserted the full draft of the article]<\/pre>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>This result surprised me. I actually preferred the previous version.<\/p>
It removed the obvious jargon (“paradigm shift,” “unleash”), but it missed several finer rules. I explicitly wrote in the Skill file to replace em dashes with commas, yet three showed up in the final version.<\/p>
It also claimed to fix structural clichés like “it’s not just about X — it’s about Y,” but I still saw lines such as:<\/p>
“It’s not just about video calls—it’s about building environments…”<\/pre>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>So was it convenient? Yes, not having to paste a full rule set each time is a real advantage. Was it perfect? No. The Skill-based version felt less thorough and skipped some structural fixes I had hard-coded into the file.<\/p>
It worked, but the manual-paste version delivered a cleaner result.<\/p>
Test #3: The mix<\/strong><\/h3>For the final test, I wanted to create a five-slide presentation on the future of remote work. I used three Skills at once: brand-guidelines<\/strong> (visuals), ai-ism-editor<\/strong> (content), and pptx<\/strong> (output).<\/p>I did this to see whether Claude understands context separation.<\/p>
Could it keep the visual rules (colors and typography), text rules (no robotic phrases), and technical rules (presentation file structure) separate while still working together?<\/p>
I need a 5-slide presentation on “The Future of Remote Work” based on the pasted content. Please use three skills together to build this:\n- Visuals: Use the brand-guidelines skill for the slide master, font choices, and title colors.\n- Content: Use the ai-ism-editor skill to edit the content and make it sound natural and human.\n- Output: Use the pptx skill to generate the final file.\n[inserted the full draft of the article]<\/pre>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>It took about five minutes of “thinking” to generate the result. A bit long, but reasonable since it was processing three logic streams at the same time.<\/p>
It handled the juggling surprisingly well. It generated a PPT file, applied the main brand colors (Dark\/Light\/Gray) along with the accent colors (Orange\/Blue\/Green), and cleaned up the text so it was mostly free of AI-isms.<\/p>
It also extracted only the key points, which is exactly how a presentation should behave.<\/p>
The downside was the layout. Text overlapped on the fourth slide, and some elements randomly shifted from left-aligned to centered.<\/p>
\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>And just like in Test #2<\/strong>, a few structural clichés and em dashes slipped through the cracks.<\/p>\n\t\t\t\n\t\t\t\t<\/path>\n\t\t\t<\/svg>\n\t\t<\/button><\/figure><\/div>So Claude didn’t break when using multiple Skills – it completed the task and followed most of the rules. But the quality dipped because it had to juggle three different instruction sets at once.<\/p>
The flaws were minor, but still required manual adjustments.<\/p>
![\"Claude](\"https:\/\/imagedelivery.net\/LqiWLm-3MGbYHtFuUbcBtA\/wp-content\/uploads\/sites\/2\/2025\/12\/claude-settings-capabilities-brand-guidelines-highlighted.png\/public\")