What problem does it solve? Responding to community issues and discussions is time-consuming and risky when done inconsistently or without full thread context. This Skill provides a structured PAO (Public Affairs Officer) workflow that scans open GitHub issues and discussions, drafts on-brand responses from reusable templates, and enforces a mandatory human review gate so nothing is ever posted autonomously. ## Core Features & Use Cases - Community Scanning: Finds unanswered open issues and discussions from the last 7 days using GitHub MCP tools or the gh CLI, filtering out internal or wontfix items. - Template-Based Drafting: Classifies each thread into one of nine response types (welcome, troubleshooting, feature guidance, redirect, acknowledgment, closing, technical uncertainty, empathetic disagreement, information request) and drafts from the matching template. - Confidence & Risk Gating: Assigns green/yellow/red confidence levels with auto-escalation rules for competitor mentions, pricing questions, and frustrated authors. - Human Review Gate & Audit: Presents drafts in a review table, waits for explicit approval commands, supports a 'banana' safe-word freeze, and logs every action to an audit trail. - Use Case: A maintainer says "PAO, check community" each morning; the Skill scans the repo, drafts three responses with full thread summaries, and the maintainer approves two and edits one before posting. ## Quick Start Ask the agent to check the community by saying "PAO, check community" and it will scan open GitHub issues and discussions, then present drafted responses for your review.
