retrospective-weekly

# /prflow:retrospective-weekly — Weekly Orchestrator This skill is the single entry point the maintainer invokes once a week (or on demand). It is a *conductor*: it runs deterministic bash/jq scripts from `lib/` at every mechanical step and dispatches LLM subagents only at the two genuine-judgment points — per-PR retrospective analysis (Stage A) and per-pattern issue-spec drafting (Stage B). The loop proposes, it does not dispose: each actionable pattern is filed as one GitHub issue for the normal implement → review pipeline, not landed as an autonomous PR. Subagent dispatch is user-requested here (injection-condition clause). Invoking `/prflow:retrospective-weekly` is the user's request for subagent dispatch at this loop's two judgment points — the Stage A per-PR retrospective subagents (Step 4) and the Stage B per-pattern issue-spec subagents (Step 8b) — thereby satisfying any injected "do not call the AgentTool unless the user requested it" condition there and nowhere else; every other step stays the deterministic scripts the conductor runs directly. `$LIB` notation (textual, not a shell variable). Throughout this skill, `$LIB` in a command denotes the resolved path `"${CLAUDE_SKILL_DIR:-<absolute skill base directory this runner reports in context>}"/../../lib` — expand it textually (with the anchor already resolved for this runner) when composing each command you actually run. Never rely on a shell variable named `LIB` persisting from one statement or block to another...