spectra-analyze

<!-- 🔒 LOCKED — managed by clade Source: plugins/hub-core/skills/spectra-analyze/ Edit at: $CLADE_HOME Local edits will be reverted by the next sync. --> ## Claude fork context This generated Claude Code skill runs with `context: fork`. The rules in this section take precedence over the shared `analyze` body below. When no change name is provided, run `spectra list --json`. Auto-select only when there is exactly one active change. If there are zero active changes or more than one active change, return the candidate list or empty-state message and ask the main thread to rerun `/spectra-analyze <change-name>`. Do NOT ask an interactive selection question inside the fork. --- Analyze artifact consistency for a change. Can be invoked directly or triggered automatically when all artifacts are complete. **Input**: Optionally specify a change name (e.g., `/spectra-analyze add-auth`). If omitted, infer from conversation context or auto-select if only one active change exists. **Prerequisites**: This skill requires the `spectra` CLI. If any `spectra` command fails with "command not found" or similar, report the error and STOP. **Steps** 1. **Determine change name** If not provided, infer from context or run `spectra list --json` to auto-select. 2. **Run programmatic analysis** ```bash spectra analyze <change-name> --json ``` This returns structured JSON with: - `dimensions`: Array of `{ dimension, status, finding_count }` for Coverage, Consistency, Amb...