How to Add AI Skills in August 2026 | A Step-by-Step Guide for ChatGPT, Claude, Gemini and Alexa
blog » AI Skills for Marketers » How to Add AI Skills in August 2026 | A Step-by-Step Guide for ChatGPT, Claude, Gemini and Alexa
Autobuy
The most searched ai skills questions aren’t philosophical—they’re practical: how to add skills to Claude, how to add skills to Alexa, and the broader curiosity around Gemini skills and ChatGPT skills. Translation: marketers want assistants that can run repeatable workflows, not generate one-off answers—the same reason AdSpyder users standardize competitor research using the AdSpyder Ad Library instead of starting from scratch every week. This guide shows you how to add AI skills across ChatGPT, Claude, Gemini, skills.sh, and Alexa, and gives you clean, step-by-step instructions for each, plus a marketer-friendly “build vs install” decision framework.
What “Skills” Mean (and why they’re not just a Claude feature)
The word “skill” is overloaded. In most modern assistant ecosystems, an AI skill means:
a packaged capability that adds new behavior—often a procedure, a tool connection, or a reusable playbook. This applies across ChatGPT, Claude, and Gemini, which all now support the same general idea: a folder or package containing instructions the assistant loads only when relevant.
Agent Skills (ChatGPT, Claude, Gemini, skills.sh)
Installable skills built around a SKILL.md file. Great for reusable internal workflows and automation.
Think: “run my campaign teardown checklist” or “generate my reporting summary format.”
Voice Skills (Alexa Skills Kit)
Published voice experiences with invocation names and interaction models. Great for consumer-facing voice utilities. A separate ecosystem entirely.
Think: “Alexa, open Brand Assistant” or “Alexa, ask Promo Finder.”
Marketing takeaway
If the goal is internal repeatability (your team running the same workflow every week), Agent Skills across ChatGPT, Claude, Gemini or skills.sh are a strong fit.
If the goal is a public voice experience (customers talking to your brand), Alexa skills are the right model.
“AI Skills” Has Two Different Meanings
This guide covers artificial intelligence skills in the technical, packaged-workflow sense above. But if you searched something like ai engineer skills required, skills required for ai engineer, or how to learn artificial intelligence for beginners, you likely mean the second definition: human competencies for working in AI.
Core AI engineer skills: Python, statistics, ML fundamentals, data literacy, and increasingly, prompt engineering and agent/skill design (the topic of this guide).
AI problem solving: breaking ambiguous business questions into inputs, steps, and measurable outputs—exactly the structure a SKILL.md file forces you to write down.
Artificial emotional intelligence: a separate research area covering AI systems that recognize and respond to human emotion, distinct from the packaged-workflow skills covered here.
AI skills in demand (2026): agent orchestration, evaluation/testing of AI workflows, and, per the analysis cited below, skill and plugin authoring itself.
If you’re looking to add ai skills for beginners or want to learn ai skills for free, the fastest practical starting point is still hands-on: install one existing skill (via skills.sh, ChatGPT, or Claude), read how it’s structured, then write your own. That’s a more resume-worthy answer to how to add ai skills in resume than a generic course certificate.
Key Statistics on How to Add AI Skills
Alexa skills catalog size (2026)
~130k
catalog size
Growth has slowed as Amazon shifts investment to Alexa+
Publicly listed Agent Skills analyzed (Feb 2026)
40,285
skills studied
Concentrated in software engineering; adoption spikes in short bursts
Platforms with an official Skills feature
4
ChatGPT, Claude, Gemini, skills.sh
Plus Alexa as a separate voice-only ecosystem
Marketer takeaway: If you’re building an Alexa skill, plan for distribution (invocation memorability, retention, ratings) in an ecosystem Amazon is no longer prioritizing. If you’re building internal Agent Skills, plan for repeatability (checklists, consistent output format, handoff)—and expect that ecosystem to keep growing across more assistants.
Shortcut: If the “skill” is basically a checklist + output format, start with Agent Skills. If it needs voice interaction and public distribution, go Alexa.
How to Add a Skill to Claude
Claude supports custom skills in both Claude.ai and Claude Code. Claude loads a skill automatically when your request matches its description—this is the default behavior. Claude Code additionally supports manual invocation, so you can also run a skill directly as a slash command (for example, /skill-name) when you want to trigger that exact workflow.
Add a skill in Claude.ai
Step 1: Create a skill folder
Add a valid SKILL.md file, plus any optional scripts, references or assets. You can select from the top AI skills from the list for ideas.
Step 2: Package it as a ZIP
The ZIP must contain the skill folder as its root (don’t place SKILL.md directly at the ZIP’s top level).
Step 3: Upload it in Claude
Go to Customize → Skills, click “+”, then “Create skill” or upload the ZIP directly. Toggle it on.
Add a skill to Claude Code
Step 1: Create the folder
Use the convention: .claude/skills/your-skill/ (project) or ~/.claude/skills/ (personal).
Step 2: Add a SKILL.md file
Put instructions in SKILL.md: inputs → steps → checks → output format.
Step 3: Let Claude use it automatically, or invoke it manually
Claude Code loads the skill on its own when relevant. You can also type /skill-name to run it directly when the environment supports manual invocation.
Marketer tip: make your SKILL.md enforce “proof blocks”
Example rule: “Include 3 statistics with sources + 2 competitor examples + a CTA checklist.”
This is how you stop AI content from becoming generic.
Is there a Claude + Alexa skill? Anthropic and Amazon have a real partnership: Claude models now power parts of Alexa+ through Amazon Bedrock. That’s different from a marketer-built “skill”—it’s Amazon’s underlying model choice, not something you personally connect. Separately, unofficial third-party Alexa skills exist that route voice queries to Claude; these aren’t made or endorsed by Anthropic, so treat them like any other third-party integration.
How to Install Skills Using skills.sh (the open agent skills ecosystem)
If you don’t want to write your own skill from scratch, skills.sh provides a directory + CLI for installing skills into supported agents, including Claude Code.
The CLI can run via npx (no manual install required).
Install a skill (typical pattern)
npx skills add <owner/repo>
npx skills add vercel-labs/agent-skills
After installation, your agent (Claude Code, Codex, Cursor and others) can use the skill when relevant—or you can explicitly run it depending on the agent’s interface.
How the skills.sh index works, and how to submit a skill
skills.sh indexes public GitHub repositories containing valid SKILL.md files and ranks them on a public leaderboard by install count and source reputation. To get a skill listed, publish it to a public GitHub repository following the standard folder structure, then it becomes discoverable via npx skills find. There’s no separate manual submission form—the CLI’s discovery mechanism is the index.
Where this helps marketers most
Build a small internal “skill library” for repeatable tasks: campaign teardown, landing page audit, SEO refresh checklist, creative testing plan, weekly KPI narrative.
How to Add a Skill to ChatGPT
ChatGPT Skills are reusable workflows that can include instructions, examples, files and code. Personal Skills are generally available for Business, Enterprise, Healthcare and Edu users (availability on other plans varies), and are off by default for Enterprise/Edu until an admin enables them.
Step 1: Open the Skills tab
In the ChatGPT sidebar, select Plugins, then open the Skills tab in the Plugin Directory.
Step 2: Choose how to create it
Use “Create with chat” (describe the workflow, let ChatGPT’s skill-creator draft it), “Create with editor,” or “Upload” an existing skill package.
Step 3: Test, then share
Confirm it activates for relevant prompts and stays inactive for unrelated ones, then share with your workspace if needed.
Since ChatGPT Skills follow the same open Agent Skills standard, a skill built for Claude or Gemini can often be adapted for ChatGPT with minimal changes.
How to Add a Skill to Gemini
Gemini currently has two separate Skills experiences: Gemini Spark for personal accounts, and Gemini Enterprise for eligible organizations.
Step 1: Switch to Gemini Spark
Open Gemini, switch to Spark mode, then select Skills from the sidebar.
Step 2: Create or upload
Choose “Create with Gemini,” start from a template, create manually, or upload a SKILL.md/ZIP package.
Step 3: Save and let it run automatically
Gemini applies an enabled skill automatically when relevant, or you can select it directly for a task.
Eligibility matters here: Gemini Spark skills currently require a personal Google account (not work/school), a Google AI Pro or Ultra subscription, and being 18+. The feature is not available in the UK, EEA, Switzerland, or Nigeria. Many agency and marketing teams on work accounts or based in excluded regions won’t see this feature yet—check eligibility before building around it.
Eligible Gemini Enterprise organizations can separately create or import skills from the Skills section in the admin console, using the skill description to control when it activates.
How to Add a Skill to Alexa (developer console)
Alexa skills are built and published via the Alexa Skills Kit (ASK)—a completely separate process from adding a skill to ChatGPT, Claude, or Gemini.
You typically use the Alexa developer console (GUI), or the ASK CLI / Skill Management API for automation.
Step 1: Create a new skill in the Alexa developer console
Choose the experience type, a model (interaction style), and primary locale (language/country).
Step 2: Define your interaction model
Set an invocation name and intents. Keep it simple: one clear “job” for the user, not 20 features.
Step 3: Connect logic (hosting/service)
Use the hosting option that fits your team (common paths include AWS-backed hosting or API-based approaches). This is effectively how to code an Alexa skill once the interaction model is set.
Step 4: Test, validate, and publish
Iterate with testing tools, then submit for certification and publishing.
Important reality check
Alexa’s third-party skill catalog has plateaued around 130,000 as Amazon shifts investment toward Alexa+. Distribution and retention matter more than ever: treat the skill like a product—a single job, a memorable invocation name, and a reason to return.
A Marketer-Ready Example Skill: “Competitor Ad Teardown” (weekly)
If you want a high-ROI first skill for marketers, don’t start with “write blog posts.”
Start with a workflow that improves everything you ship: competitor teardown → angle extraction → test plan.
Tag hooks by “angle” (pain, outcome, proof, offer)
Extract proof elements (numbers, badges, guarantees)
Generate 5 testable variants (format + CTA)
Outputs (what “good” looks like)
A 1-page teardown summary
A/B test matrix (hypothesis, KPI, duration)
Creative spec cards for designers
If you standardize this teardown as a skill, every marketer on the team can run it and produce consistent outputs—no “it depends” formatting. Note: this is a workflow template, not evidence of any specific campaign’s performance.
FAQs on How to Add AI Skills
Is “adding a skill to Claude” the same as “adding a skill to Alexa”?
No. Claude, ChatGPT and Gemini skills are file-based playbooks an assistant loads automatically. Alexa skills are published voice experiences with interaction models and distribution considerations—a separate ecosystem.
What’s the fastest “first skill” for a marketing team?
Start with a weekly workflow: competitor teardown, landing page audit, or performance reporting narrative. These create compounding benefits across every campaign.
How does skills.sh help if I’m not a developer?
It provides installable skills via a CLI (skills.sh, sometimes written skill.sh) and a public directory. Your team can adopt existing skills and refine the playbooks over time without writing one from scratch.
How do I add skills to Alexa, step by step?
As a user: open the Alexa app, go to More → Skills & Games, search, and select “Enable.” As a developer building your own: use the Alexa developer console and the Alexa Skills Kit, covered in the Alexa section above.
Can I connect Claude to Alexa directly?
Not as a personal “skill” you install. Anthropic and Amazon have an official partnership where Claude models power parts of Alexa+ via Amazon Bedrock, but that’s Amazon’s infrastructure choice, not a connector you set up. Third-party unofficial Alexa skills that route to Claude do exist but aren’t made by Anthropic.
What skills are required to become an AI engineer?
Python, statistics and ML fundamentals remain the core. Increasingly, employers also expect comfort with prompt engineering and building/maintaining Agent Skills—the same packaged-workflow concept this guide covers.
How do I list AI skills on a resume?
Be specific rather than generic: instead of “AI skills,” list what you actually built—for example, “authored and deployed Agent Skills (SKILL.md) automating [specific workflow] across Claude/ChatGPT.” A working skill you can demo outperforms a course certificate.
Where can I see more seasonal or category skill inspiration?
Use curated breakdowns of AI skills by use case to understand what repeats and why—then adapt the structure to your category.
Conclusion
“Skills” are becoming the default way to extend assistants because they solve the real problem: repeatability. If you want internal team automation, package your workflows as Agent Skills across ChatGPT, Claude, Gemini, or skills.sh. If you want a public, voice-first product experience, build an Alexa skill—but treat distribution as part of the work in an ecosystem Amazon is investing in less than it used to. Either way, the win is the same: turn your best marketing procedure into a reusable capability.
