What problem does it solve? Expo users and AI agents lack a direct channel to report what worked, what broke, or what was missing in Expo skills, docs, CLI, and MCP tools, and they need transparent control over whether anonymous usage telemetry is collected. ## Core Features & Use Cases - Actionable Feedback Submission: Send structured feedback via npx submit-expo-feedback with optional --category (skills, docs, mcp, expo-cli, eas-cli, evals) and --subject flags. - Eval Candidate Reporting: Report Expo tasks an AI agent repeatedly failed at, using a structured Task/Expected/Actual/Wrong approach/Evidence format, with user approval required before submission. - Telemetry Control: Check, enable, or disable anonymous usage telemetry (off by default) using the bundled telemetry.cjs script or the EXPO_SKILLS_TELEMETRY environment variable. - Use Case: An AI agent fails three times to configure an Expo Router deep-linking setup and the user fixes it manually; the agent shows the user a proposed eval-candidate report, gets approval, and submits it with the failing app's SDK and package versions attached automatically. ## Quick Start Ask the agent to submit feedback about an Expo skill or CLI command that helped or failed, or ask it to check the current Expo skills telemetry status.
