From csdlc
Run all stories in an epic autonomously — the Hurricane Pattern. Read the dependency graph, dispatch stories to sub-agents in order, review PRs, merge, report back. Use when the user says "shipit", "run the whole epic", "full send", "hurricane", or "lightning strike this".
npx claudepluginhub danhannah94/claymore-plugins --plugin csdlcThis skill uses the workspace's default tool permissions.
Ship this epic: **$ARGUMENTS**
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
Ship this epic: $ARGUMENTS
/shipit is the Hurricane Pattern from PROCESS.md made into a command. The AI Lead becomes the "eye of the hurricane" — spawning batches of sub-agents, coordinating merges, resolving conflicts, and verifying builds.
Read the epic doc. $ARGUMENTS is a Foundry path to an epic design doc with stories already broken down (via /breakdown). If no stories exist, suggest running /breakdown first.
Build the dependency graph. From the stories' dependency fields:
Confirm the plan. Present:
Execution Plan for {Epic}:
Batch 1 (foundation): S1
Batch 2 (parallel): S2, S3, S4
Batch 3 (serial): S5 (depends on S2)
Batch 4 (parallel): S6, S7
Total: {N} stories, {M} batches
Estimated: {complexity-based rough guess}
Full send? Or adjust the plan?
Execute in batches. For each batch:
csdlc-intern skill workflow/review on each completed storyBetween batches:
After all batches complete:
/qa on the full epic (integration-level, not per-story)/present to package for human reviewStop execution and report to the user if: