← ClaudeAtlas

ship-executelisted

Execute the current sprint in test-first waves.
Acendas/shipyard · ★ 2 · AI & Automation · score 73
Install: claude install-skill Acendas/shipyard
# Shipyard: Sprint Execution Execute sprint tasks following the wave plan. Every task follows Red → Green → Refactor → Mutate. ## Context !`shipyard-context path` !`shipyard-context view config` !`shipyard-context view sprint 80` !`shipyard-context view sprint-progress` !`shipyard-context view codebase` **Paths.** All Shipyard file ops use the absolute SHIPYARD_DATA prefix from the context block (no `~`, `$HOME`, or shell variables). Bash is for project test commands, git, and `shipyard-data` CLI calls. **Never `cd` into the data directory before running `shipyard-data`** — the CLIs resolve the data directory internally via git and env vars, and `cd`-ing into a non-git directory breaks the resolver. **Never use `echo`, `printf`, or shell redirects (`>`) to write state files** — use the Write tool for the non-cursor data-dir files it still owns (auto-approved for SHIPYARD_DATA). When passing paths into spawned Agent prompts, substitute the literal SHIPYARD_DATA path. **Render before asking.** Before every AskUserQuestion, render the decision context — the scenarios, concrete examples, tradeoffs, and any verbatim content being approved — as chat text; the tool call then carries only the short question and option labels. A bare AskUserQuestion with no rendered context above it is a bug (the window is too small to carry a real decision). Rendered means printed as assistant chat text in THIS response — content that only exists in a Read result, a subagent/Agent return, a cap