agent-swarm
Agent skill for swarm - invoke with $agent-swarm
35
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
100%
75%Multi-Source Market Intelligence System
Collaborative swarm topology and agent deployment
swarm_init called
0%
100%
Mesh topology selected
100%
100%
strategy parameter present
0%
100%
maxAgents parameter present
0%
100%
agent_spawn called
0%
100%
Multiple agents spawned
0%
100%
Researcher agent spawned
0%
100%
Analyst agent spawned
0%
100%
Agent capabilities specified
77%
100%
Agent name specified
80%
100%
Without context: $0.4781 · 2m 1s · 30 turns · 95 in / 6,060 out tokens
With context: $0.3627 · 1m 21s · 21 turns · 26 in / 4,371 out tokens
100%
92%Automated Contract Review Pipeline
Sequential orchestration strategy and task routing
swarm_init called
0%
100%
Ring topology selected
0%
100%
task_orchestrate called
0%
100%
Sequential strategy used
27%
100%
priority parameter present
40%
100%
maxAgents in orchestrate
0%
100%
agent_spawn called
0%
100%
Analyst agent spawned
0%
100%
task string provided
20%
100%
Agent capabilities specified
0%
100%
Without context: $0.5175 · 1m 44s · 32 turns · 628 in / 5,157 out tokens
With context: $0.3428 · 1m 18s · 20 turns · 432 in / 3,922 out tokens
100%
E-Commerce Platform Build with Swarm Oversight
Swarm lifecycle management
swarm_init called
100%
100%
Hierarchical topology selected
100%
100%
strategy in swarm_init
100%
100%
maxAgents in swarm_init
100%
100%
agent_spawn called
100%
100%
Coder agent spawned
100%
100%
Coordinator agent spawned
100%
100%
swarm_status called
100%
100%
swarm_scale called
100%
100%
swarm_destroy called
100%
100%
Without context: $1.0921 · 3m 36s · 40 turns · 2,468 in / 11,091 out tokens
With context: $0.2636 · 1m 15s · 13 turns · 16 in / 4,488 out tokens
- Evaluated
- Agent
- Claude Code
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.