Help us improve
Share bugs, ideas, or general feedback.
From ecc
Weighted social-graph ranking for warm intro discovery, bridge scoring, and network gap analysis across X and LinkedIn. Use when the user wants the reusable graph-ranking engine itself, not the broader outreach or network-maintenance workflow layered on top of it.
npx claudepluginhub affaan-m/ecc --plugin eccHow this skill is triggered — by the user, by Claude, or both
Slash command
/ecc:social-graph-rankerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Canonical weighted graph-ranking layer for network-aware outreach.
Reorganizes X and LinkedIn networks with review-first pruning, add/follow recommendations, and warm outreach drafts in user's voice. For cleaning follows, aligning with priorities, rebalancing social graphs.
Analyzes X/Twitter follower/following networks using graph algorithms like PageRank, betweenness, community detection, and influencers to find clusters, bridges, and segments. Use for audience or competitor network structure insights.
Identifies networking targets and drafts value-add outreach emails and LinkedIn requests for job searches, career pivots, or partnerships.
Share bugs, ideas, or general feedback.
Canonical weighted graph-ranking layer for network-aware outreach.
Use this when the user needs to:
lead-intelligence or connections-optimizerChoose this skill when the user primarily wants the ranking engine:
Do not use this by itself when the user really wants:
lead-intelligenceconnections-optimizerCollect or infer:
Given:
T = weighted target setM = your current mutuals / direct connectionsd(m, t) = shortest hop distance from mutual m to target tw(t) = target weight from signal scoringBase bridge score:
B(m) = Σ_{t ∈ T} w(t) · λ^(d(m,t) - 1)
Where:
λ is the decay factor, usually 0.5Second-order expansion:
B_ext(m) = B(m) + α · Σ_{m' ∈ N(m) \\ M} Σ_{t ∈ T} w(t) · λ^(d(m',t))
Where:
N(m) \\ M is the set of people the mutual knows that you do notα discounts second-order reach, usually 0.3Response-adjusted final ranking:
R(m) = B_ext(m) · (1 + β · engagement(m))
Where:
engagement(m) is normalized responsiveness or relationship strengthβ is the engagement bonus, usually 0.2Interpretation:
R(m) and direct bridge paths -> warm intro asksR(m) and one-hop bridge paths -> conditional intro asksR(m) or no viable bridge -> direct outreach or follow-gap fillWeight targets before graph traversal with whatever matters for the current priority set:
Weight mutuals after traversal with:
R(m).SOCIAL GRAPH RANKING
====================
Priority Set:
Platforms:
Decay Model:
Top Bridges
- mutual / connection
base_score:
extended_score:
best_targets:
path_summary:
recommended_action:
Conditional Paths
- mutual / connection
reason:
extra hop cost:
No Warm Path
- target
recommendation: direct outreach / fill graph gap
lead-intelligence uses this ranking model inside the broader target-discovery and outreach pipelineconnections-optimizer uses the same bridge logic when deciding who to keep, prune, or addbrand-voice should run before drafting any intro request or direct outreachx-api provides X graph access and optional execution paths