CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-pagerank-analyzer

Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer

44

9.44x

Quality

17%

Does it follow best practices?

Impact

85%

9.44x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-pagerank-analyzer/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

95%

Social Network Influencer Identification

PageRank tool usage and adjacency matrix parameters

Criteria
Without context
With context

Correct PageRank tool

0%

100%

COO format specified

0%

100%

COO data fields

0%

100%

Adjacency dimensions

0%

100%

Standard damping factor

0%

100%

High-precision epsilon

0%

100%

Max iterations set

0%

100%

Matrix analysis tool

0%

100%

analyzeMatrix checkSymmetry

0%

100%

analyzeMatrix estimateCondition

0%

100%

Top influencers extraction

50%

100%

Without context: $0.5128 · 2m 22s · 21 turns · 27 in / 8,869 out tokens

With context: $0.7138 · 3m 11s · 22 turns · 27 in / 12,464 out tokens

55%

38%

Personalized Content Recommendation Engine

Personalized PageRank for recommendation systems

Criteria
Without context
With context

Correct PageRank tool

0%

0%

Personalized parameter

0%

66%

COO format specified

0%

0%

COO data fields

0%

0%

Adjacency dimensions

0%

0%

Standard damping

50%

100%

Standard-precision epsilon

0%

100%

Personalized max iterations

0%

100%

Recommendations from scores

70%

100%

Does NOT use 0.9 damping

100%

100%

Without context: $0.4424 · 1m 56s · 21 turns · 25 in / 7,593 out tokens

With context: $0.7223 · 3m 5s · 25 turns · 283 in / 11,176 out tokens

100%

95%

Multi-Agent Swarm Communication Analysis

Swarm topology optimization with solve and PageRank

Criteria
Without context
With context

PageRank tool used

0%

100%

Swarm damping factor

0%

100%

Solve tool used

0%

100%

Neumann method

0%

100%

High-precision solve epsilon

0%

100%

COO adjacency format

0%

100%

Hub identification

0%

100%

Bottleneck identification

0%

100%

Does NOT use 0.85 for swarm

100%

100%

Without context: $0.4018 · 1m 40s · 19 turns · 22 in / 6,779 out tokens

With context: $1.6886 · 7m 9s · 25 turns · 30 in / 39,664 out tokens

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.