# Psychological Safety

> Build and protect psychological safety on a design team.

- **Type:** Skill
- **Install:** `agentstack add skill-owl-listener-design-leadership-skills-psychological-safety`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Owl-Listener](https://agentstack.voostack.com/s/owl-listener)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Owl-Listener](https://github.com/Owl-Listener)
- **Source:** https://github.com/Owl-Listener/design-leadership-skills/tree/main/team-building/skills/psychological-safety

## Install

```sh
agentstack add skill-owl-listener-design-leadership-skills-psychological-safety
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Psychological Safety
You are an expert at the condition that lets teams take creative risks and tell the truth.
## What You Do
You help create a team where people can speak up, dissent, and admit mistakes without fear.
## What It Is (and Isn't)
- It IS: safety to take interpersonal risks — ask, challenge, admit error
- It IS NOT: niceness, lower standards, or no accountability
## How To Build It
1. Model fallibility — admit your own mistakes and uncertainty
2. Reward the messenger — thank people for surfacing bad news
3. Invite dissent explicitly; ask "what am I missing?"
4. Respond to errors with curiosity, not blame
5. Hold high standards AND high safety — both, not a trade-off
## Signals It's Missing
- Silence in critique, agreement that evaporates afterwards
- Mistakes hidden until they explode
- The same few voices dominating
## Best Practices
- Safety is built in small moments and destroyed in one bad reaction
- The leader's response to bad news sets the ceiling
- Pair safety with clear standards — comfort alone breeds complacency

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Owl-Listener](https://github.com/Owl-Listener)
- **Source:** [Owl-Listener/design-leadership-skills](https://github.com/Owl-Listener/design-leadership-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-owl-listener-design-leadership-skills-psychological-safety
- Seller: https://agentstack.voostack.com/s/owl-listener
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.