CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-agent

Agent skill for agent - invoke with $agent-agent

42

4.65x

Quality

13%

Does it follow best practices?

Impact

93%

4.65x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Evaluation results

93%

78%

Autonomous CI/CD Deployment Planner

GOAP state-space modeling and action graph construction

Criteria
Without context
With context

current_state as Map

0%

100%

goal_state as Map

0%

100%

Action cost field

100%

100%

Preconditions as Map

0%

100%

Effects as Map

0%

100%

Inverse-cost weighting

0%

100%

analyzeMatrix checkDominance

0%

100%

analyzeMatrix checkSymmetry

0%

100%

analyzeMatrix estimateCondition

0%

100%

A* open set

0%

100%

A* closed set

100%

100%

Goal structure fields

0%

0%

Without context: $0.8625 · 3m 22s · 47 turns · 150 in / 10,253 out tokens

With context: $0.6515 · 2m 29s · 22 turns · 273 in / 9,218 out tokens

100%

79%

AI Research Platform: Goal Prioritization and Agent Coordination Layer

Multi-agent swarm coordination and consensus decision-making

Criteria
Without context
With context

Swarm topology

0%

100%

Swarm maxAgents

0%

100%

Swarm strategy

0%

100%

Coordinator agent capabilities

0%

100%

Analyst agent capabilities

0%

100%

Optimizer agent capabilities

0%

100%

Orchestrate strategy

0%

100%

Orchestrate priority

0%

100%

PageRank damping

100%

100%

PageRank epsilon

0%

100%

Goals sorted descending

100%

100%

Consensus solver method

100%

100%

Proposal selection pattern

0%

100%

Without context: $1.4204 · 6m 46s · 74 turns · 3,167 in / 16,199 out tokens

With context: $0.5746 · 2m 10s · 20 turns · 272 in / 7,485 out tokens

88%

64%

Adaptive Logistics Route Monitor

OODA loop dynamic replanning with memory and error recovery

Criteria
Without context
With context

observe() method

80%

100%

orient() method

80%

100%

decide() method

60%

100%

act() method

80%

100%

1-second cycle

0%

100%

Confidence threshold 0.8

0%

100%

Confidence from residual

0%

0%

MATRIX_SINGULAR handling

25%

100%

NO_CONVERGENCE handling

62%

100%

TIMEOUT handling

25%

100%

Memory namespace

0%

100%

Memory key pattern

0%

100%

Memory search limit

0%

100%

Without context: $0.4087 · 2m 26s · 16 turns · 22 in / 9,122 out tokens

With context: $0.9569 · 3m 52s · 26 turns · 390 in / 15,777 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.