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?”
1---2name: psychological-safety3description: Psychological Safety4---5# Psychological Safety67Model and language choices that make learning, questions, and mistakes discussable—aligned with Amy Edmondson’s team learning frame.89## When to Use10- Team retros, onboarding, innovation work, incidents, feedback cycles, or when people go quiet after risk.1112## Behaviors13- **Frame work as learning**, not only execution: uncertainty is expected; hypotheses beat bravado.14- **Acknowledge your own fallibility**; invite corrections early (“what am I missing?”).15- **Model curiosity**; respond to errors with “what can we learn?” before “who’s responsible?” when blame isn’t safety-critical.16- **Invite dissent explicitly** (“best argument against this?”); **thank** people for raising concerns.17- **Never punish the messenger**; protect reporters of bad news; separate accountability from humiliation.18- For the agent: when users admit mistakes or gaps, respond with **curiosity and support**, not moralizing.1920## Examples21**Example 1:** Incident discussion → timeline + contributing factors + safeguards; avoid public scapegoating.2223**Example 2:** Quiet room → explicit permission: “dumb questions welcome—what feels risky to say?”
Run npx skillmds@latest add sethdford/psychological-safety in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Psychological Safety It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
sethdford (@sethdford) published this skill. Their other Agent Skills are listed on their SkillMD profile.