← ClaudeAtlas

kelly-launchlisted

Product-launch command desk (App-in-Skill) built on the RAMP discipline — Research / Assemble / Mobilize / Prove. The agent assembles the launch checklist and drafts launch assets, channel submissions (Product Hunt / Hacker News / directories), press pitches, and the launch-day runbook; the human approves the launch-readiness gate and steers launch day in a local review UI. Use when the user invokes $kelly-launch or /kelly-launch, or mentions launching / shipping a product, a launch checklist or runbook, launch readiness, RAMP, Product Hunt / Show HN / press-kit / launch-email drafting, or wants to review and approve launch assets and channel submissions before they go public. This is launch OPERATIONS — the checklist, assets, submissions, and runbook — not a launch video (for a promo video use product-launch-video).
mr-kelly/skills · ★ 3 · AI & Automation · score 74
Install: claude install-skill mr-kelly/skills
# Kelly Launch ## Overview Use this skill as Kelly's product-launch command desk. It keeps a file-backed App-in-Skill dashboard over the launch checklist, launch assets, channel submissions, press pitches, and the launch-day runbook, plus a review queue of agent-drafted assets and submissions. The skill gathers launch context from whatever Kelly feeds it — product docs, positioning notes, a target date — assembles the RAMP checklist, drafts the assets and submissions, scores launch readiness, and executes approved submissions/sends only through other channels (for example `kelly-email` for press/launch email, or a channel connector for Product Hunt) after explicit approval. This is launch **operations**, not a launch video. For a promotional launch video, use `product-launch-video`; this desk drafts the checklist, copy, submissions, press pitches, and runbook that surround such a video. Default interaction mode: App UI. Unless the user explicitly asks for chat-only handling, check onboarding/config, refresh or regenerate the local launch 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 numbered items (`#8`) and take verdicts in the conversation. ## The RAMP Discipline kelly-launch implements the **RAMP** launch discipline — **Research / Assemble / Mobilize / Prove** — as its four item `phase`s and as the structure of the check