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

# User Intuition Skills

> Pre-built Claude Code skills that wrap the User Intuition CLI and MCP server for common research workflows — drop in, no glue code required.

User Intuition **skills** are short, copy-pasteable instruction files that teach an AI agent (Claude Code, Cursor, Claude Desktop) *how* to drive the [CLI](/cli/overview) or [MCP server](/mcp-server/overview) for a specific research workflow.

Where the MCP server gives an agent the *tools*, a skill gives it the *play*. The skill is the difference between "the agent can call `ask_humans`" and "the agent knows to ask three clarifying questions, then run `ask_humans` in `claim` mode with a sensible default N, then poll `get_results` until the study completes."

## When skills help

* **Repeatable workflows.** Validating positioning copy, screening Panel respondents, generating an insights report — anything you do more than twice.
* **Cross-team consistency.** Two PMs on different machines run the same workflow the same way because the skill ships the playbook.
* **Onboarding.** A new teammate installs the skills and immediately runs the team's standard research patterns.

## How skills work

A skill is a Markdown file with YAML frontmatter. The frontmatter tells the agent *when* the skill applies; the body tells it *how* to execute. Example shape:

```markdown theme={null}
---
name: validate-claim-with-humans
description: Use when the user wants to test whether a marketing claim, headline, or value-prop is believable with real respondents.
---

When the user describes a claim they want to validate:

1. Confirm the exact claim text and target audience.
2. Call `ask_humans` in `claim` mode with `dry_run: true` to preview cost.
3. After user approves cost, run without dry_run.
4. Poll `get_results` until status is `complete` or `partial`.
5. Summarize believability + top 3 themes from open-ended responses.
```

Agents that support skills load the frontmatter at session start, then read the body when the description matches the user's request.

## Two ways to install

<Tabs>
  <Tab title="Claude Code">
    Drop the skill file into your project's `.claude/skills/` directory (or `~/.claude/skills/` for global use):

    ```bash theme={null}
    mkdir -p ~/.claude/skills
    curl -o ~/.claude/skills/validate-claim-with-humans.md \
      https://docs.userintuition.ai/skills/library/validate-claim.md
    ```

    Claude Code auto-discovers skills on next session start. Verify with `/skills`.
  </Tab>

  <Tab title="Cursor">
    Cursor uses `.cursorrules` or per-project `.cursor/rules/*.md` files. Paste the body of any skill (drop the frontmatter) into a new rules file:

    ```bash theme={null}
    mkdir -p .cursor/rules
    # paste skill body into .cursor/rules/userintuition-validate-claim.md
    ```
  </Tab>

  <Tab title="Claude Desktop">
    Claude Desktop doesn't natively support skill files yet — paste the body of the skill into a custom **Project** instructions field. The agent will follow it for the duration of that project's chats.
  </Tab>
</Tabs>

## What's in the library

The [skills library](/skills/library) ships ready-to-use skills for the most common User Intuition workflows:

<CardGroup cols={2}>
  <Card title="validate-claim-with-humans" href="/skills/library#validate-claim-with-humans">
    Test whether a marketing claim is believable to real respondents.
  </Card>

  <Card title="run-preference-study" href="/skills/library#run-preference-study">
    Compare 2-5 options (taglines, designs, value props) head-to-head.
  </Card>

  <Card title="recruit-with-screeners" href="/skills/library#recruit-with-screeners">
    Build screener questions to recruit a specific Panel segment.
  </Card>

  <Card title="analyze-fielded-study" href="/skills/library#analyze-fielded-study">
    Pull results, summarize themes, surface verbatim quotes.
  </Card>

  <Card title="watch-running-studies" href="/skills/library#watch-running-studies">
    Daily digest of fielding studies — runs in cron via the CLI.
  </Card>
</CardGroup>

## Skill vs MCP vs CLI — which goes where

| You want…                                                                | Use                      |
| ------------------------------------------------------------------------ | ------------------------ |
| An agent to *autonomously* run a research workflow from a vague prompt   | **Skill** (built on MCP) |
| An agent to call User Intuition tools when you ask, with you in the loop | **MCP** alone            |
| To run a tool from a shell script, CI job, or cron                       | **CLI**                  |
| To call User Intuition from your own backend code                        | **REST API**             |

Skills sit on top of MCP, MCP and CLI sit on top of the same tool surface, and everything sits on top of the REST API. Pick the highest level that gets the job done.

## Next steps

<CardGroup cols={2}>
  <Card title="Skills library" icon="book" href="/skills/library">
    Browse and copy ready-to-use skills.
  </Card>

  <Card title="MCP quickstart" icon="rocket" href="/mcp-server/quickstart">
    Skills require an MCP-connected client. Wire one up first.
  </Card>
</CardGroup>