What problem does it solve? Turning a raw GitHub issue into an actionable engineering specification requires manual triage, codebase investigation, and root-cause analysis. This Skill automates that intake pipeline so a bug report or feature request becomes a testable spec without ad-hoc exploration. ## Core Features & Use Cases - Structured Issue Intake: Fetches the issue via the GitHub CLI and normalizes it into an Intake Note with observed behavior, expected behavior, reproduction steps, and environment, flagging gaps as [NEEDS REPRO]. - Root Cause Localization: Builds 2-5 falsifiable hypotheses with confidence scores, validates the top candidates against the codebase, and prunes to a single root cause with at least 70% confidence. - Spec Generation and Transition: Produces a WHAT/WHY-focused spec with FR/SC numbering and Given/When/Then scenarios, then optionally transitions to planning or a full fix-and-PR workflow via plan and trace flags. - Use Case: A maintainer runs /swarm issue on a reported crash; the Skill fetches the issue, pinpoints the faulty function with supporting evidence, and writes .swarm/spec.md ready for implementation planning. ## Quick Start Invoke the issue ingest mode with a GitHub issue URL, for example by asking the agent to run /swarm issue followed by the issue link, optionally adding plan or trace flags.
