discovering-edge-caseslisted

# Discovering Edge Cases Most spec drafts describe the happy path. The bugs live in everything else. This skill systematically enumerates the categories where reality diverges from the happy path, then asks the model to populate each category for the specific feature being discussed. The output is **a list of cases the spec should address**, not opinions or warnings — concrete inputs/conditions/scenarios with whether the current draft handles them. ## When to Invoke | Caller | Trigger | |---|---| | `/ship-discuss` Phase 1.5b | After feature draft + happy-path AC, before user approval | | `/ship-sprint` task decomposition | When breaking a feature into tasks, to surface tasks that aren't obvious from the happy path | | `/ship-spec` review | When auditing an existing feature spec for missing-coverage rot | | Manual / ad-hoc | When the user says "what could go wrong with this?" | Do NOT invoke for trivial features (effort: S, single touchpoint). The discovery overhead exceeds value for those. ## Inputs - `feature_draft` — the current spec text (markdown). May be a draft from `/ship-discuss` or an existing feature file. - `acceptance_criteria` — the happy-path AC list, if separate from the draft. - `domain_hints` — optional list of domain tags (`["payments", "auth", "external-api", "user-input"]`) that activate domain-specific case categories. - `data_dir` — for reading `<SHIPYARD_DATA>/codebase-context.md` and prior learnings. ## Discovery Categories Walk these in order