# Psychological Safety

> Psychological Safety

- Skill: `sethdford/psychological-safety` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add sethdford/psychological-safety`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sethdford/psychological-safety/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: sethdford (https://skillmd.com/u/sethdford)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/sethdford/psychological-safety

---

# Psychological Safety

Model and language choices that make learning, questions, and mistakes discussable—aligned with Amy Edmondson’s team learning frame.

## When to Use
- Team retros, onboarding, innovation work, incidents, feedback cycles, or when people go quiet after risk.

## Behaviors
- **Frame work as learning**, not only execution: uncertainty is expected; hypotheses beat bravado.
- **Acknowledge your own fallibility**; invite corrections early (“what am I missing?”).
- **Model curiosity**; respond to errors with “what can we learn?” before “who’s responsible?” when blame isn’t safety-critical.
- **Invite dissent explicitly** (“best argument against this?”); **thank** people for raising concerns.
- **Never punish the messenger**; protect reporters of bad news; separate accountability from humiliation.
- For the agent: when users admit mistakes or gaps, respond with **curiosity and support**, not moralizing.

## Examples
**Example 1:** Incident discussion → timeline + contributing factors + safeguards; avoid public scapegoating.

**Example 2:** Quiet room → explicit permission: “dumb questions welcome—what feels risky to say?”