datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction — GitHub trend

FINDING #5841 · UNIT ID 1141336664

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

221 AI skills for construction: BIM analysis, cost estimation, scheduling, document control, and automation with Claude Code

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00312

ENGAGEMENT0.20

FRESHNESS1.38

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

26% OF STARS IN ARCHIVE

[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:

S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS

S10 · S10

Growth Telemetry

VELOCITY /D

2.13

ACCEL

-0.02

RETENTION

41.5%

PEAK 2026-06-19 · FORK-RETENTION 0.0% · 64 STARS / WINDOW

Author Audience

AUDIENCE

644

FOLLOWERS

478

OWNER ★

1,663

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 64 / 64 (DIVERSITY 1.00)

Why This Is A Finding

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction собрал 64 звёзд за окно, тогда как у автора всего 478 подписчиков — эффективная аудитория ≈ 644. Это даёт surprise-индекс 0.00312 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 7% OF 6295 FINDINGS

#01shy3130/tickflow-stock-panel[ PYTHON ]0.46 #06Panniantong/Agent-Reach[ PYTHON ]0.29 #10sums001/Windows-Copilot-API[ PYTHON ]0.27 #12HUANGCHIHHUNGLeo/claude-real-video[ PYTHON ]0.24 #14realiti4/claude-swap[ PYTHON ]0.21

METRICS IN CONTEXT

MEDIAN ACROSS ALL 6295 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 7%

VELOCITY2.134.23-2.10ABOVE 20%

RETENTION41.5%29.4%+12.1 PPABOVE 73%

FORKS5992-33ABOVE 38%

SURPRISE0.000.01-0.01ABOVE 24%