# idea-to-ship

**Composable Agent Skills — for Claude and OpenAI Codex — that take an idea from *fuzzy* → *validated* → *sequenced build* → *shipped*: by hand, or on autopilot.**

Most "build with AI" workflows skip the hard half. They jump straight to code — and skip *deciding what's actually worth building*, *validating it honestly*, and *planning the build so it ships in safe, verifiable steps*. `idea-to-ship` is that missing front half — plus the autonomous build loop on the far side of it: a small, sharp suite of Agent Skills (they run in **Claude** and **OpenAI Codex**), reverse-engineered from real idea→ship journeys (including the mistakes those journeys made), so you don't repeat them.

<p align="center"> <img src="assets/pipeline.svg" alt="The idea-to-ship pipeline — ideate → deep-dive → prompt-pack → build-loop — run by hand (manual tier), or flown by the autonomous tier: autopilot flies the whole line from an idea, while audit-and-fix re-enters at deep-dive on a codebase that already exists (including the one autopilot just built), skipping ideation because the code is the grounding." width="760"> </p>

<p align="center"> <img src="assets/countershape-run.png" alt="The proof ate the project: 18+ days of autopilot running autonomously on Codex 5.6 — every sealed commit plotted from the run's own log, verification milestones towering over product milestones." width="760"> <br> _{Live right now: <code>autopilot</code>'s second stress test — <strong>18+ days autonomous on Codex 5.6</strong>, every claim backed by a recorded receipt. See <a href="https://github.com/nelsonwerd/proof-ate-the-project">the mid-run debrief</a>, failures included.} </p>

They're **separate, composable** skills on purpose — sharp triggers, lean context, independent use. Run them **by hand** (the manual tier), or let **`autopilot`** fly the whole line for you (the autonomous tier).

**Who it's for.** Solo and small-team builders who tend to start coding before decidi