Add rpa-bot-handoff skill: ops guide for bot handover

The skill scans a bot with subagents (never runs it) and writes
HANDOVER.md, an 11-section ops guide in the operator's order: where is
what, how to run, how long to wait, after the run, how to see an
exception, exception list, how you will know, how to tell us, don'ts,
issues seen before. Dev material (check against 12 failure classes from
Tebra Auto Post, gaps with file:line, incidents) goes to HANDOVER-DEV.md.

Also adds ADR-0004, glossary terms, five fixture bots and a handoff eval
runner (--resume, --regrade) with results from 47 runs of the earlier
13-section version. The grader still expects that structure and must be
updated before the next eval run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/fixtures/h-desktop-poster/report_screen.py

@@ -0,0 +1,13 @@
+"""Report screen of the ClaimDesk Poster launcher: a table over the report table, filtered by batch."""
+import sqlite3
+from pathlib import Path
+
+DB = Path(__file__).parent / "data" / "poster.db"
+COLUMNS = ["clinic", "check_no", "file_status", "comments"]  # what ops sees
+COLOURS = {"Completed": "green", "Deferred": "grey", "Error": "red", "Pending": "amber"}
+VERSION = "1.4.2"  # shown in the launcher title bar
+
+
+def rows(batch_id):
+    db = sqlite3.connect(DB)
+    return db.execute(f"SELECT {', '.join(COLUMNS)} FROM report WHERE batch_id=?", (batch_id,)).fetchall()