Browse skills

Enforces safety protocols, monitors resource usage, and manages agent behavior to ensure responsible operation.

Enforces ethical guidelines, prioritizes user safety, and promotes responsible AI behavior across all actions.

Skill Guard proactively monitors and flags potentially harmful or inappropriate user inputs, enhancing safety and responsible AI interaction.

Enforces developer-defined safety guidelines and ethical boundaries within agent actions to prevent harmful outputs.

Analyzes CivitAI model descriptions & images to identify potential issues like bias, safety concerns, or inaccurate tagging.

Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.

jzocb's agent-guardrails enforces safety protocols and ethical boundaries within your AI agent’s interactions.

Safe OpenClaw gateway restart with state-machine verification. Preserves context across restarts and sends post-restart ACK via Telegram, Discord, Slack, or custom webhook.