gh-aw-safe-outputs

Installation
SKILL.md

πŸ›‘οΈ GitHub Agentic Workflows - Safe Outputs Skill

πŸ“‹ Purpose

Master the safe outputs pattern in GitHub Agentic Workflows - the foundational security mechanism that enables AI agents to perform write operations safely through explicit, human-approved outputs. This skill provides comprehensive expertise in designing, implementing, and operating safe output patterns for controlled AI automation.

🎯 Core Concept

What Are Safe Outputs?

Safe outputs are the only way AI agents can perform write operations (create/update files, issues, PRs) in GitHub Agentic Workflows. Unlike direct tool access, safe outputs require explicit approval and sanitization before execution.

Key Principles:

  • πŸ”’ Write Isolation: All write operations go through safe outputs
  • βœ… Explicit Approval: Outputs must be explicitly declared in workflow
  • οΏ½οΏ½ Automatic Sanitization: All outputs sanitized before execution
  • πŸ“Š Auditable: All actions logged and traceable
  • 🚫 No Direct Writes: AI cannot write files/issues/PRs directly
Related skills
Installs
3
GitHub Stars
7
First Seen
Mar 4, 2026