FINDING #7521 · UNIT ID 1329272295
Leonxlnx/unlazy
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
2% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
10.57
ACCEL
+0.07
RETENTION
56.9%
PEAK 2026-10-07 · FORK-RETENTION 60.0% · 74 STARS / WINDOW
Author Audience
AUDIENCE
12,456
FOLLOWERS
2,224
OWNER ★
102,324
Engagement Signals
FORKS
289
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 74 / 74 (DIVERSITY 1.00)
Why This Is A Finding
Leonxlnx/unlazy собрал 74 звёзд за окно, тогда как у автора всего 2,224 подписчиков — эффективная аудитория ≈ 12,456. Это даёт surprise-индекс 0.000846 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 60.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.
Related Findings
RANKS ABOVE 23% OF 9757 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9757 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 23%
VELOCITY10.573.57+7.00ABOVE 79%
RETENTION56.9%40.0%+16.9 PPABOVE 77%
FORKS289112+177ABOVE 72%
SURPRISE0.000.01-0.01ABOVE 14%