> ## Documentation Index
> Fetch the complete documentation index at: https://docs.51ultron.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Using Skills

> How to invoke skills from chat, what to expect during execution, and how results are saved.

## Invoking a skill

You don't need a command or syntax. Describe what you need in plain language and Ultron routes to the right skill:

```text theme={null}
Run a competitive analysis on HubSpot.
```

```text theme={null}
Write a cold email to the VP of Engineering at Stripe referencing their recent infrastructure blog post.
```

```text theme={null}
Create a LinkedIn post about why most B2B cold emails fail.
```

The more specific the objective, the better the output. Vague objectives produce vague results.

## Good vs. vague objectives

| Too vague            | Specific                                                                                 |
| -------------------- | ---------------------------------------------------------------------------------------- |
| "Write an email"     | "Write a cold email to the Head of Growth at Linear referencing their recent Series B"   |
| "Research a company" | "Deep dive on Notion — I'm pitching their CTO next Thursday"                             |
| "Create content"     | "Write a LinkedIn post about why most SDR-to-AE handoffs fail, for a sales ops audience" |

## What you see during execution

Tool activity streams in real-time as the skill runs:

```text theme={null}
[skill]  competitive-analysis: starting
[tool]   web_search("HubSpot pricing 2026")
[tool]   web_search("HubSpot vs competitors features")  ← parallel
[tool]   scrape_website("hubspot.com/pricing")           ← parallel
[tool]   search_memories("competitor research hubspot")
[result] 4 sources processed
[tool]   save_memory({ tags: ["cortex", "competitive", "hubspot"] })
[skill]  competitive-analysis: complete
```

You can follow along with exactly what Ultron is doing and why.

## After execution

Every skill run automatically:

1. **Saves results to memory** — tagged with skill category and the entity researched
2. **Logs activity** — timestamped entry in the activity feed
3. **Returns the result inline** — text, table, or canvas in the chat thread

You don't need to save anything manually.

## Cancelling a skill

Type "stop" or "cancel" at any point to interrupt a running skill. Partial results are still returned if any tool calls completed.

<Tip>
  If a skill produces output that's close but not quite right, follow up directly in chat: "Make the email shorter" or "Add a SWOT section to that analysis." Ultron updates in the same thread.
</Tip>