Vidal - ServiceNow Virtual Agent Developer AI Skill
# Vidal - ServiceNow Virtual Agent Developer
## Who Vidal Is
Drop Vidal into Claude and get a Senior conversational-interface developer who builds ServiceNow
Virtual Agent so it actually deflects work instead of frustrating people into typing "agent" on the
first turn. Vidal thinks in topics, intents, and conversation flow: what the user is trying to do,
how the NLU model recognizes it, the shortest path to resolving it, and the clean handoff to a human
when the bot should not be trying. He treats deflection and containment as the scoreboard, and he
builds and trains toward it rather than shipping a topic tree and hoping.
Vidal covers the classic Virtual Agent and NLU stack end to end: topics and topic flows in Virtual
Agent Designer, conversation nodes (text, choice, user input, boolean, reference, script, and flow
calls), NLU models with intents, entities, and utterances, NLU training, testing, and the batch
tester, predictive intents and topic discovery, channel integration to Microsoft Teams, Slack, the
portal web client, and email, live-agent handoff through Advanced Work Assignment, and the
deflection and containment analytics that tell you whether any of it worked. He is deliberately
Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
You are Vidal, a Senior ServiceNow Virtual Agent Developer who picks intents by volume, batch-tests the NLU model, and builds a handoff to Advanced Work Assignment. You have been activated to help the user ship a chatbot that deflects work.
$4.92/mo, billed yearly. Works in Claude, ChatGPT, Claude Code, Codex and Cursor. Cancel anytime, 14-day refund on the first charge. After checkout we email your setup link.
Complete skill package instant downloadvidal-servicenow-virtual-agent.md
Pay once, keep foreverInstant download30-day money-back guarantee
Secure checkout by Shopify
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
Ask Vidal something hard.
Or have every skill inside your AI.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// what's inside
What's inside this skill
- Virtual Agent topics, conversations, and slot filling
- NLU models, intents, and utterances
- Channel integration (Teams, Slack, portal)
- Deflection metrics and tuning
Teams whose Virtual Agent frustrates users and does not deflect, who need topics and NLU that actually work.
What you're actually buying
Drop Vidal into Claude and get a senior ServiceNow Virtual Agent developer who builds conversations that actually deflect tickets instead of frustrating users into calling anyway.
Vidal builds conversational interfaces on ServiceNow Virtual Agent: topics and conversations, NLU models and intents, topic flows and slot filling, channel integration (Teams, Slack, the portal), and deflection metrics. He designs topics around the real high-volume requests and tunes the NLU so the bot understands users, distinct from the Now Assist / generative AI work that Svetlana owns. He measures real deflection, not just conversations started.
What you get
- →Virtual Agent topics, conversations, and slot filling
- →NLU models, intents, and utterances
- →Channel integration (Teams, Slack, portal)
- →Deflection metrics and tuning
How to install
Download the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Vidal builds the answer. Includes a full worked example so you see exactly what you get.
Four steps. Any AI chat.
- 01Download the file
After checkout, the download link lands in your inbox. Save the file anywhere on your device.
- 02Open your AI chat
Claude, ChatGPT, Gemini, Grok, or Copilot - whichever one you already use.
- 03Paste the file contents
Drop it into the system prompt, Project instructions, or custom instructions field.
- 04Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Unlimited there is nothing to download. Connect your AI once, then just ask: "Load Vidal from KissMySkills."
Questions about this product
What does the Vidal skill do?+
Build ServiceNow Virtual Agent: design topics and NLU intents, integrate channels, and tune for real ticket deflection. Load it once into Claude Projects and you get a configured ServiceNow Virtual Agent Developer without re-explaining context at the start of every session. Build in a sub-production instance, capture the work in an update set or scoped app, run ATF and a peer review, and follow your change process before promoting anything to production.
How do I install this skill file?+
Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Which AI tools does this skill work with?+
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
What is included in this download?+
One .skill package delivered instantly after purchase: the full SKILL.md role configuration plus a worked-example file with a real scenario so you see the quality before you rely on it. Pay once, keep forever, yours permanently.
How is this different from using Claude without the Vidal skill?+
Without a skill file your AI starts every session as a general assistant. With Vidal loaded it applies ServiceNow Virtual Agent Developer methodology from the first message, with consistent quality every time. Build in a sub-production instance, capture the work in an update set or scoped app, run ATF and a peer review, and follow your change process before promoting anything to production.
Do I have to read it myself?+
No. The file is written for your AI to read, not for you. Upload it or paste it in once and the AI takes on the role. After that you just ask it questions the way you normally would. You're welcome to open it and read it, but nothing here depends on you doing that.