/story

Load project context in one command.

You closed Claude Code yesterday. Or last week. Or a month ago. You don't want to re-explain the project from scratch. This is where /story earns its keep: one invocation, recorded project context, and suggestions for what to work on next. Picking up from our storybook example.

Written guide available · Video coming soon

Follow along

  1. 1.

    Come back to your project folder

    Open Claude Code inside the storybook folder you set up in the last tutorial. The .story/ directory is already there, committed, waiting. No warm-up, no re-onboarding, no recap.

  2. 2.

    Run /story

    Type the slash command and press Return. That's the only thing you need to type. Everything else is reading.

    $/story
  3. 3.

    Watch what it loads

    Claude reads your project spec (CLAUDE.md), your rules (RULES.md), your lessons (WORK_STRATEGIES.md), and the last handover if there is one. Then it looks at your open stories, active issues, and current phase. For storybook, that is the scaffolding phase, with a handful of stories ready to start.

  4. 4.

    Read the snapshot

    Claude comes back with a short summary: where you are, what's blocked, what's in progress, what's next. The summary uses your .story/ records. Check it against the current code before continuing.

  5. 5.

    Pick from the three recommendations

    The skill proposes next work from the project record. Read the reasons, check the scope, and choose a story. Recommendations can account for blockers, unfinished work, and what would unblock other stories.