FINDING #2874 · UNIT ID 1290410846
oxbshw/watch-skill
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
19% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
3.13
ACCEL
+0.02
RETENTION
18.8%
PEAK 2026-10-04 · FORK-RETENTION 50.0% · 94 STARS / WINDOW
Author Audience
AUDIENCE
295
FOLLOWERS
112
OWNER ★
1,829
Engagement Signals
FORKS
71
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 94 / 94 (DIVERSITY 1.00)
Why This Is A Finding
oxbshw/watch-skill собрал 94 звёзд за окно, тогда как у автора всего 112 подписчиков — эффективная аудитория ≈ 295. Это даёт surprise-индекс 0.00936 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 50.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.
Related Findings
RANKS ABOVE 70% OF 9675 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9675 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.010.00+0.00ABOVE 70%
VELOCITY3.133.80-0.67ABOVE 42%
RETENTION18.8%20.3%-1.5 PPABOVE 46%
FORKS71138-67ABOVE 35%
SURPRISE0.010.01+0.00ABOVE 55%