Banner image for AI Skills
Core Concepts 6 min read

AI Skills

AI Skills give the Catalio assistant different areas of expertise — from requirements writing to security analysis — and are selected automatically based on what you ask

Updated
On this page

AI Skills are specialized modes that change how the Catalio assistant responds. Each skill gives the assistant a different area of expertise. When you send a message in AI Chat, Catalio automatically picks the most relevant skill based on what you wrote — no configuration required.

Think of skills as the AI wearing different hats. Ask about acceptance criteria and the Product Manager skill takes over. Mention a security vulnerability and the Cyber Security skill activates. Ask a general question and you get the General Assistant.

How Skill Selection Works

Every time you send a message, Catalio looks at your wording and picks the skill whose area of expertise best fits. If a specialized skill matches, you get that expertise. If nothing specific fits, the General Assistant handles the request.

When more than one skill could fit, Catalio breaks the tie by topic specificity — for example, “grade this requirement” will activate the Requirement Grader (very specific) rather than the Product Manager (broader). This is invisible to you; you just see the AI responding in the most appropriate style.

The Seven Built-In Skills

General Assistant

The default skill used when no other skill fits. Helps with general questions, listing and searching records, navigation, and handing off to a more specialized skill when one becomes appropriate. Also surfaces interactive blocks when a structured choice is needed.

Product Manager

Activates when you mention: user story, requirement, acceptance criteria, process, workflow, feature request, sprint, and similar phrases.

Specializes in capturing requirements through natural conversation, writing grade-ready user_want and user_benefit fields, drafting use cases in Gherkin format, and helping with persona identification. When editing existing records, it follows a strict propose-then-review flow: it drafts changes, sends you to the form, and waits for you to confirm before anything is saved.

Technical Architect

Activates when you mention: architecture, API, database, schema, integration, capability, system design, infrastructure, scalability, performance, microservice.

Specializes in system architecture, capability mapping, API design, technical policies, and data modeling. Presents recommendations with explicit tradeoffs before documenting anything.

QA / Testing

Activates when you mention: test, testing, QA, quality, coverage, edge case, acceptance test, bug, defect, regression, scenario, validation.

Specializes in test case design, edge case identification, test strategy, and acceptance criteria verification.

Cyber Security

Activates when you mention: security, vulnerability, compliance, encryption, authentication, authorization, threat, risk, SOC 2, GDPR, HIPAA, PCI, penetration, audit, access control.

Specializes in security requirements, compliance frameworks, threat modeling, and security-control documentation.

Initiative Management

Activates when you mention: initiative, strategic intent, scope summary, process domain, create an initiative, or phrases like connect X to initiative.

Specializes in creating and managing Initiatives. Can set name, description, strategic intent, scope summary, process domains, start date, and target date. Also handles connecting entities (requirements, personas, journeys, policies, and more) into an Initiative’s scope.

Requirement Grader

Activates when you mention: grade, quality score, or phrases like assess this requirement.

Evaluates a requirement across Clarity, Completeness, Feasibility, and Quality — the same rubric the AI Grader uses in the background. Useful for getting an interactive explanation of a grade or targeted advice on improving a specific dimension.

What You See

Skills are mostly invisible. You do not pick a skill manually — you just write naturally and the right expertise is applied. The only signal is the AI’s behavior: a question about acceptance criteria produces a structured draft with Gherkin use cases (Product Manager); a question about API design produces an architecture recommendation with tradeoffs (Technical Architect).

If the AI’s response style seems off for what you asked, you can steer it explicitly. “Help me write a security policy for data retention” reliably activates Cyber Security even if your original phrasing did not include a trigger word.

Skills and the AI Grader

The Requirement Grader skill and the AI Grader background feature share the same rubric. Whether you ask the assistant to grade a requirement in chat, or the background grader runs automatically after an edit, the criteria are identical — so interactive advice and saved grades always agree.

Skills and AI Chat Tools

Skills change the AI’s expertise and communication style, not what it can do. Every skill has access to the same set of tools — Product Manager can still navigate you to a form, Technical Architect can still create a capability. Skills govern how the AI thinks; tools determine what the AI can act on.

Best Practices

Write naturally. Trigger words are designed around how people actually speak. You do not need to memorize phrases — just describe what you need.

Be specific about the domain. “Help me think through test coverage for the payment flow” cleanly activates QA over General Assistant. Specificity produces better skill selection and better responses.

Use Initiative context for scope. When you open chat from inside an Initiative, the Initiative Management skill has context about that Initiative’s scope, intent, and connected entities — so responses are automatically more relevant.

Re-ask if the response feels wrong. If the AI seems to be using a different mental model than you expected, rephrase with a clearer domain signal.

Relationships at a Glance

Entity Relationship
AI Chat Skills are selected per message and govern the assistant’s expertise
AI Grader Shares the Requirement Grader skill’s rubric for automatic background grading
Requirements Primary artifact for Product Manager and Requirement Grader skills
Initiatives Primary artifact for the Initiative Management skill

Next Steps

  • See AI Chat for what the assistant can do and how conversations work
  • Read AI Grader to understand how the grading rubric works in detail
  • Explore Initiatives to understand the scope that the Initiative skill manages

Support

If skill selection seems wrong, try restating your question with a clearer domain signal. If the AI’s response style still does not match what you need, contact support@catalio.ai.