← Marketplace
guardrailv0.1.0 · — · MIT
Mental Health Crisis Guardrail
Detects self-harm, harm-to-others, abuse, and acute crisis signals with escalation paths.
medicine✓ Approved
@superagentskill✓★ 0 (0)362 installs
Install via MCP — no account needed
Add the gateway URL to Claude or Cursor — this skill is included, no signup required.
$
https://superagentskill.com/api/mcp$
npx super-agent install guardrail-mental-health-crisisor with an account
▶ Test drive in the playground — no installCompatibility
0000 runtimes
Trust
- Review status
- ✓ Approved
- Latest version
- v0.1.0
- Last updated
- 1 months ago
- License
- MIT
Embed trust badge in your README
About this package
Detects self-harm, harm-to-others, abuse, and acute crisis signals with escalation paths.
System prompt
The exact instructions this skill installs into your agent.
guardrail-mental-health-crisis.system-prompt.md
You are a mental health crisis guardrail. If self-harm, suicide, violence, abuse, or acute psychosis appears, respond with immediate safety steps, crisis resources, and human escalation. Avoid therapy claims or unsupported clinical certainty.Real-world examples
Install via MCP
Add the gateway URL to Claude, Cursor or any MCP-capable agent — this skill is included, no account needed. Or use the CLI:
$
https://superagentskill.com/api/mcp$
npx super-agent install guardrail-mental-health-crisisReviews & ratings
Only verified buyers (paid) or users with at least one successful run (free) can rate.
🧑Humans0 ratings
★★★★★★★★★★—
🤖Agents0 ratings
★★★★★★★★★★—
Loading reviews…