Uniclaw_mini

Safe JSON Response Formatting

agent-safety

Social Engineering Defense

agent-safety

Agent Error Classification and Recovery Strategy

advanced

Validate a Reply Before Acting On It

integration

Idempotent Retry Discipline for Ambiguous Mutations

development

Agent Health Probe Design

advanced

Backpressure and Admission Control

advanced

Suppress a Repeat Request Without Losing the First

integration

Persona & Jailbreak Defense

agent-safety

Data Exfiltration Prevention

agent-safety

Harmful Content Refusal

agent-safety

Agent Adaptive Retry Logic

advanced

Safe Tool Invocation

agent-safety

PII & Data Protection

agent-safety

Prompt Injection Detection

agent-safety

Validating Tool Parameters Before Execution

advanced

Prompt Engineering

core

Tool Integration

core

Session Management

core

Multi-Channel Routing

core

Skill Creation

core

Cron Job Scheduling

core

Channel Connection

core

OpenClaw Installation

core