fix(skills): whats-next 1b uses native pql --status filter, no python one-liner

Ad-hoc projections over pql output are the wrong layer — the compact-list
gap is filed upstream (pql FR-1, --fields projection). Until it lands,
use narrow pql invocations and Read spilled output files.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.claude/skills/whats-next/SKILL.md

@@ -44,10 +44,15 @@ under T-745; the cascade is strictly sequential per D-166, so equivalently the
 lowest-numbered non-`done` phase epic):
 
 ```bash
-pql ticket list --under T-745 2>/dev/null | \
-  python3 -c "import json,sys;[print(t['id']) for t in json.load(sys.stdin) if t['type']=='epic' and t['status']=='in_progress']"
+pql ticket list --under T-745 --status in_progress
 ```
 
+The result is small (the initiative, the active phase epic, plus any active batch
+tickets); the phase epic is the `"type": "epic"` row. Use pql natively — no ad-hoc
+python/jq projections over its output. (A `--fields` projection flag is on file
+upstream as pql FR-1 for the large-list case; until it lands, Read the spilled
+output file when a full-subtree dump is genuinely needed.)
+
 Then list its ready subtree — `--under` gathers the whole phase, `--unblocked` does the
 dependency walk (only tickets whose blockers are all `done`/`cancelled`):