Ranks mutual connections in X and LinkedIn by bridging value to target contacts. Enables warm introduction discovery and network gap analysis using weighted graph ranking.
How this skill is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:social-graph-rankerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
用于网络感知外联的规范加权图排名层。
用于网络感知外联的规范加权图排名层。
当用户需要以下操作时使用此技能:
lead-intelligence 或 connections-optimizer 理解图数学当用户主要想要排名引擎时选择此技能:
当用户真正想要以下内容时,不要单独使用此技能:
lead-intelligenceconnections-optimizer收集或推断:
给定:
T = 加权目标集M = 你当前的互关 / 直接连接d(m, t) = 从互关 m 到目标 t 的最短跳距离w(t) = 来自信号评分的目标权重基础桥接分数:
B(m) = Σ_{t ∈ T} w(t) · λ^(d(m,t) - 1)
其中:
λ 是衰减因子,通常为 0.5二阶扩展:
B_ext(m) = B(m) + α · Σ_{m' ∈ N(m) \\ M} Σ_{t ∈ T} w(t) · λ^(d(m',t))
其中:
N(m) \\ M 是互关认识但你不知道的人集合α 折扣二阶可达性,通常为 0.3响应调整后的最终排名:
R(m) = B_ext(m) · (1 + β · engagement(m))
其中:
engagement(m) 是标准化的响应性或关系强度β 是参与度加成,通常为 0.2解读:
R(m) 且有直接桥接路径 → 温暖介绍请求R(m) 且有一跳桥接路径 → 有条件的介绍请求R(m) 或无可行桥接 → 直接外联或填补差距在图遍历之前根据当前优先级集的重要因素对目标加权:
遍历后对互关加权:
R(m) 排名。社交图排名
====================
优先集:
平台:
衰减模型:
顶级桥接
- 互关 / 连接
base_score:
extended_score:
best_targets:
path_summary:
recommended_action:
有条件路径
- 互关 / 连接
reason:
extra hop cost:
无温暖路径
- 目标
recommendation: 直接外联 / 填补图差距
lead-intelligence 在更广泛的目标发现和外联流水线中使用此排名模型connections-optimizer 在决定保留、修剪或添加谁时使用相同的桥接逻辑brand-voice 应在起草任何介绍请求或直接外联之前运行x-api 提供 X 图访问和可选的执行路径npx claudepluginhub aaione/everything-claude-code-zhRanks mutuals/connections by intro value using weighted graph traversal (decay, bridge scoring, second-order expansion). Useful for warm path discovery and deciding between intro vs. cold outreach.
Reviews and reorganizes X and LinkedIn networks with curation-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's voice.
Applies network analysis to determine how structure shapes outcomes across centrality, contagion, weak ties, and network effects. Routes to the right sub-skill based on your situation.