sdd

Use when the user invokes `/sdd:explain <subject>`, asks to "explain how X works", "document X", "write an explanation of X", or wants a deep-dive document on a component, concept, or subsystem in the current project. Spawns a dedicated sdd-explainer agent that writes to `.sdd/projections/<subject>.md` and can work interactively (asking what to explore next) or autonomously (full document without prompts).

This skill should be used when the user invokes `/sdd:gap-to-work-items`, says "decompose gaps into work items", "create work items for GAP-auth", "generate work items from gap report", "break down gaps for authentication", or wants to turn open gap files into actionable work items. Takes a domain or specific gap ID as input and produces scoped work-item files.

This skill should be used when the user invokes `/sdd:install-statusline` or asks to "install the SDD statusline", "set up the statusline", or "add SDD statusline to Claude Code". Appends a minimal SDD delegation block to the user's global statusline script so that an SDD line appears when inside a repo with a .sdd/ directory.

This skill should be used when the user invokes `/sdd:next`, says "what should I do next", "what's the next step", "recommend a next action", "prioritise SDD work", or wants a ranked list of candidate next actions across all domains with priority, recommendation, and size signals, and then routes the chosen action to the appropriate skill.

Use when the user invokes `/sdd:projection-comments <name>`, says "address projection comments for <name>", "process comments on <name>", or wants to apply and prune pending comments on a projection document. Reads the co-located .comments.json, applies clarify/re-evaluate/expand/condense edits to the projection markdown, removes addressed entries, and leaves unaddressable entries in place.