kelly-feedbacklisted

# Kelly Feedback ## Overview Use this skill as Kelly's voice-of-customer desk. It aggregates raw user feedback from every channel (support email, Discord, Slack, X replies, app-store reviews, in-app surveys, interviews) into one file-backed App-in-Skill dashboard, where the agent's dedupe/clustering work becomes feature requests with frequency and user weight, and agent-proposed roadmap changes wait in a decision queue for Kelly's verdict. Division of labor: the skill (scripts + agent) collects, clusters, and drafts; the app is where Kelly triages feedback and decides on proposals; approved roadmap changes are exported/executed by the agent outside the app (updating a roadmap doc or changelog, handing decline replies to kelly-messenger or kelly-email). Kelly Feedback sits downstream of kelly-email, kelly-messenger, and kelly-social: those skills' agents hand feedback payloads to this skill's ingest script. Default interaction mode: App UI. Unless the user explicitly asks for chat-only handling, check onboarding/config, refresh or load the local feedback snapshot, start/reuse the local app with `app/start.sh`, and give the actual local URL. Use chat-only mode only when the user says "纯聊天", "chat only", "不要打开 UI", or similar; in that mode present proposals as numbered items (`Proposal #1`, `#2`, ...) and record verdicts in `decisions.json`. ## App UI Screenshots <table> <tr> <td width="50%"><img src="assets/screenshots/overview.webp" alt="Kelly Feedback overview"></