# Skills Catalog

Give any AI employee a step-by-step playbook for a specific type of work: how you want blog posts researched, how outreach emails get structured, how a report should be formatted. The employee reads the full skill only when a task actually matches it, so you can attach as many as you want without slowing anything down.

Skills define what your employee can do, and you manage them by talking. Say "learn how to write blog posts" and it searches the skill catalog, finds the content writing skill, and assigns it to itself. Say "I need you to do competitor analysis every week" and it creates a custom skill with the right steps, tools, and output format. No settings page, no drag-and-drop configuration.

The skill catalog comes loaded with dozens of industry-standard templates across marketing, sales, support, research, writing, data analysis, and more. Each skill includes a detailed prompt, required tools, and quality criteria. Your employee picks the right one based on what you describe, or builds a new one if nothing fits.

Skills are composable. An employee can have 5 skills or 50. They activate the right skill for each task automatically. Ask it to "write a blog post about our new feature," and it activates the content writing skill. Ask it to "research what competitors are charging," and it switches to the research skill. You describe the work. The employee picks the right approach.

You can also browse, edit, or remove skills manually from the employee profile. But most users never need to. The conversational interface handles it.

## Configure Your AI Employee Skills Through Natural Conversation

Sistava eliminates the admin overhead of managing agent capabilities through menus and configuration panels. Instead, you tell your AI employee what to learn in plain language and it self-configures the relevant skills. Say "learn advanced SEO research" and the agent activates, adjusts, and confirms.

This conversational configuration model keeps skill management inside the same interface where you already work. There is no separate admin panel to navigate, no documentation to read before making changes. The AI employee is its own configuration interface.

## A Growing Catalog of Skills Across Every Work Function

The skills catalog covers functions across sales, marketing, operations, research, customer support, finance, and technical domains. Each skill is a defined capability set: a combination of knowledge, behavior patterns, and tool usage tuned for a specific type of work.

Skills are not just prompts. Each skill in the catalog shapes how the agent approaches problems in that domain, what information it surfaces, how it structures its outputs, and how it uses connected tools. Assigning a skill meaningfully changes what the agent can do, not just what it will say.

New skills are added to the catalog continuously. When a new skill becomes available, you can assign it to relevant AI employees through conversation, the same way you assigned their first skills.

## Skill Progression That Matches Real Employee Development

AI employees do not just have or lack a skill. They develop proficiency within a skill over time based on practice, feedback, and the knowledge you provide. This mirrors how real employee development works: someone can be a beginner or an expert at the same skill category.

You can monitor which skills each agent has active, which are developing, and where gaps exist for the work they are doing. If a task requires a skill the agent does not have, the agent will flag it rather than attempting the work without the right capability.

## How It Works

**Add, remove, and adjust skills through conversation and the workspace, and the agent absorbs them immediately.**

Skills define what an agent knows how to do. Each skill is a set of instructions that shapes how the agent approaches a specific type of task, such as writing blog posts, triaging support tickets, or running competitive analysis. You manage skills from the employee profile or by telling the agent directly in chat. Changes take effect in the next conversation.

You can see every skill an agent has, toggle them on or off, and edit the content of any skill to match your exact process. If the agent is not doing something the way you want, you adjust the relevant skill instead of rewriting a system prompt. Skills are versioned and auditable, so you always know what the agent was working from when it produced a given output.

## Use Cases

### HR manager assigning communication skills to a recruiting agent

Add the skills that match the role. The AI employee knows exactly what it is capable of and operates within that scope.

### Ops lead tuning a task management agent for a specific workflow

Assign only the skills relevant to the workflow. The agent stays focused and does not drift into irrelevant areas.

### Team lead removing outdated skills from an existing agent

Revoke skills the agent no longer needs. Capabilities stay current without rebuilding the agent from scratch.

### Manager comparing skill sets across the team's AI employees

See what every AI agent on the team knows and does at a glance. Gaps and overlaps become immediately visible.

## Comparison

| Before | After |
|---|---|
| AI agents either do too much or too little because their scope is unclear. | Assign exactly the skills the agent needs for its role, nothing more. |
| Changing what an agent can do means rebuilding it entirely. | Add or remove skills at any time without touching the rest of the configuration. |
| No visibility into what each agent on the team is capable of. | Skills are explicit and visible, making team coverage easy to manage. |
| Agents attempt tasks they were never meant to handle. | Skills define the boundaries, the AI employee works within them. |

## FAQ

### Can I remove a skill from an AI employee after assigning it?

Yes. Tell the agent to stop using a skill or remove it from the skills panel, and it is deactivated immediately. The agent retains the memory of work it did while that skill was active, but the skill no longer shapes its behavior.

### What is the difference between a skill and a duty?

A skill is a capability the agent has mastered, defining what it can do well. A duty is a behavioral rule that governs how the agent must behave on every interaction. An agent can have the skill to write code and the duty to always add inline comments to any code it produces.

### How many skills can one AI employee have at a time?

There is no hard cap, but assigning too many unrelated skills to a single agent reduces clarity and focus. Best practice is to assign skills that align with the agent defined role and primary responsibilities, and use the team structure to distribute specialized skills across multiple agents.

### Can AI employees suggest skills they think they need?

Yes. When an AI employee encounters a task that would benefit from a skill it does not have, it can proactively suggest activating that skill. You review the suggestion and approve or decline.

### How do I customize what my AI employee knows how to do?

You assign skills through a conversational interface, no code required, and each skill shapes how the agent approaches specific types of work. Skills can be added, adjusted, or removed at any time.

> I updated the blog writing skill to follow our new brand voice. Every piece the agent wrote after that matched perfectly. It took two minutes to change and the results were immediate.
>
> Nadia V., Content Director · SaaS company

## Where Skills Catalog fits

Skills Catalog is part of Things that control how they behave.

Skip the settings panels. Tell your AI employee what skills to learn, what rules to follow, and what personality to use, all through natural conversation. They can even browse the skill catalog and configure themselves as work evolves.

- [Things that control how they behave](/en/features/behavior): Just ask. It configures itself.

## Read the guide

- [Guide: Skills Catalog](/en/guide/equip/skills)

## More in Behavior

- [Shape Your Employee's Personality](/en/features/behavior/employee_persona): Write a short persona prompt to set how each AI employee talks: formal or casual, brief or detailed, warm or blunt. Every employee starts with a role-based default, and you can rewrite it any time from the Profile tab. The change applies to the employee's next message, no restart needed.
- [Customize Employee Profile](/en/features/behavior/employee_profile_customization): Every hire's Profile tab is fully editable: name, role, team, avatar, persona, language, and tone of voice, all changed in place without a rehire. Updates apply from the next message onward, across every channel the employee uses. A change history on the same tab shows who edited what and when, including edits the employee made to its own persona.
- [Credits Saver](/en/features/behavior/credits_saver): Credits Saver watches every message and quietly hands the easy ones (greetings, quick acknowledgements, 'make that shorter') to a lighter, cheaper model, while real work still runs on the model you picked. On everyday back-and-forth that often means 40 to 50% fewer credits, with no drop in quality where it counts. It is on by default and fully in your control: turn it on or off anytime, and see tracked credits saved, its router cost, and the net benefit on its own page.
- [Ask Your Employee About Sistava](/en/features/behavior/platform_awareness): Ask your employee about Sistava itself and get a real answer: what plan you're on, what a feature costs to unlock, what your limits are, or who else you could hire. Your employee reads the live plan and feature data at the moment you ask, so the answer matches what your account actually has right now, not a guess from training data.
- [Choose How Deeply Your Employee Thinks](/en/features/behavior/reasoning_effort_control): Set how much an employee thinks before it answers, from Off through Minimal, Light, Medium, and Deep, or leave it on Auto so the platform picks the right depth per message on its own. It applies workspace-wide from the AI Behavior settings page, with a per-employee override when one employee's work genuinely needs a different depth than the rest of the team.
- [Set a Per-Task Action Limit](/en/features/behavior/max_actions_override): Set exactly how many actions one employee can take while working on a single task, from 50 up to 1,000. Give a research-heavy employee more room to search, read, and delegate before it has to stop and report back, or cap a simple support employee tighter so it never wanders past what the task needs.
- [Duties Catalog](/en/features/behavior/duties_catalog): Give any employee a set of standing rules they follow on every single interaction, no exceptions: respond within the hour, always CC you on sales emails, never discuss pricing without approval. Pick from the built-in catalog or write your own in plain English, and the employee carries the full text of every active duty in mind on every turn.
- [Personal Preferences Memory](/en/features/behavior/founder_personal_profile): Tell your team leader once how you want to be addressed, when you're working, and how you like answers written, and every employee on your team picks it up automatically. No settings form to fill out: just say it in chat and it sticks.
- [Skills They Can Master](/en/features/behavior/custom_skills): Teach any AI employee your own step-by-step process, from a blog-writing checklist to a lead-qualification script, and it follows those exact steps whenever a matching request comes in. Write it yourself in the Skills tab, or just describe your process in chat and the employee turns it into a skill. Skills load only when the task matches, so you can add as many as you want without slowing anything down.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)