Network analytics
Skill dzhokhov/markdown-agent-vault/skills/network-analytics
Agent-ready Markdown vault methodology with AGENTS.md, templates, skills, logs, and file-safe workflows.
npx -y skills add dzhokhov/markdown-agent-vault --skill network-analyticsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
SKILL.md
2.3 KB, as published. Nobody here has run it
Network Analytics
Navigation: Skill index
Overview
Transform chaotic mentions and interactions into a working map of the network of influence.
Skill is responsible for the normalize entities -> update graph -> compute metrics -> outreach plan phase.
Workflow
1) Normalize Entities
Use the circuit from graph-schema.
Substances:
PersonOrganizationEventTopic
2) Update Edges
Maintain typed connections:
co-speakerco-organizermentioned_withworks_atintroduced_byattended
For each rib, fix:
sourcedateconfidence
3) Compute Metrics
If you have graph analytics tools, consider:
degree centralitybetweenness centralityeigenvector centralitycommunities(Louvain/equivalent)
If tools are not available, use heuristics and explicitly mark
method=heuristic.
4) Interpret
Use the rules of metrics-and-prioritization:
- bridges between clusters,
- the core of each domain,
- New growing clusters.
5) Build Outreach Plan
Give me:
- 5 key bridges
- 3 clusters/domains
- 10 priority outreach steps (to whom, through whom, why)
Output
- Graph update summary
- Top bridges (betweenness)
- Community map
- Outreach backlog (10 items)
Each outreach item:
target_personviareasonsuggested_message_angleexpected_outcome
Quality Gates
- No rib without a source or date.
- There are no central conclusions without specifying the method of calculation.
- Outreach recommendations are tied to a specific goal, not a general “get to know.”
Anti-Patterns
- Do not mix names without proof of identity.
- Do not confuse frequent mentions with real influence.
- Do not draw conclusions about the cluster based on 1-2 connections.