prompt-packlisted

Author and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippable prompts, each run in its own fresh chat so a single change never dies to a context/token limit. Also writes paste-ready handoff briefings to resume a dying chat or relay work to another tool (e.g. Codex). ALWAYS invoke when the user says any of "make a prompt pack", "turn this into prompts", "break this into phases", "prompts I can run in separate chats", "I'm running out of tokens/context", "write me a handoff", "a prompt I can paste into a new chat", "this is too big for one chat", "build plan I can hand off", or "execute Pxx / phase X from the pack". Also invoke proactively when a requested change is too large or too risky to finish safely in one session and should be decomposed into ordered, verifiable steps.
nelsonwerd/idea-to-ship-skills · ★ 83 · AI & Automation · score 80

Install: claude install-skill nelsonwerd/idea-to-ship-skills

# Prompt-Pack — Sequenced, Self-Contained Prompts for Big Work Across Chats A prompt pack turns one large, risky job into an ordered set of **small, self-contained prompts**. Each prompt is pasted into a *fresh* chat, does exactly one shippable unit of work, verifies itself, and stops for review. The pack file lives in the repo and is the durable source of truth — so work survives context limits, spans multiple chats and tools, and never leaves the app half-broken. This skill encodes a battle-tested format (refined across many real packs) so every pack you author is consistent, safe, and resumable, and every pack prompt you execute follows the same disciplined loop. ## Why this exists (the problem it solves) - **Big changes are risky.** Decomposing into ordered, independently-shippable steps with explicit guardrails keeps the app working — and reviewable — between every step. This is the core win, and it holds even with unlimited context. - **Work relays across chats and tools.** A self-contained prompt can go to a new Claude chat or be pasted into another agent (e.g. Codex via `AGENTS.md`) with no loss — so a build can move across sessions, tools, or people. - **Plans evaporate.** Writing the pack to a file in `docs/` means a future session — or a confused one — can be pointed at the source of truth. - **Long jobs can outrun a single chat.** You can run a whole pack in one thread; but if a chat fills up mid-build, each self-contained unit moves to a fresh one with no amn