spawn
Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis.
90
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
92%
25%Kubernetes Expert Agent for Platform Team
Agent file structure and YAML compliance
YAML frontmatter present
100%
100%
Lowercase-hyphen name
100%
100%
Filename matches name field
100%
100%
Correct project-level path
100%
100%
Tools field restricted
0%
0%
10+ authoritative URLs
100%
100%
Agent length 500+ lines
0%
100%
10-part structure headers
58%
100%
10+ code blocks
0%
100%
description field specificity
100%
100%
Without context: $0.2730 · 1m 25s · 15 turns · 63 in / 4,703 out tokens
With context: $0.7469 · 3m 11s · 23 turns · 399 in / 12,973 out tokens
100%
62%FastAPI Expert Agent for Backend Engineering Team
10-part agent content structure
Configuration dev+prod
20%
100%
Testing with actual code
70%
100%
Error handling hierarchy
20%
100%
Anti-patterns count
100%
100%
Essential patterns count
0%
100%
Pattern implementation depth
40%
100%
Quick reference cheat sheet
12%
100%
Security section present
62%
100%
Performance section present
50%
100%
Integration patterns present
0%
100%
All 10 parts present
30%
100%
Without context: $0.4500 · 2m 25s · 15 turns · 22 in / 10,063 out tokens
With context: $0.9788 · 4m 21s · 25 turns · 33 in / 17,475 out tokens
92%
42%PostgreSQL Expert Agent for a Data Engineering Team
Agent description quality and code example standards
PROACTIVELY or MUST BE USED in description
0%
100%
Description includes use cases
100%
100%
10+ code blocks in agent body
100%
100%
Production-ready code quality
100%
100%
model field valid value
100%
100%
color field present
0%
100%
Global path used
0%
100%
Post-generation reminder
100%
100%
10+ authoritative URLs
0%
100%
Tools field restricted
0%
0%
Without context: $0.4338 · 2m 25s · 19 turns · 67 in / 7,576 out tokens
With context: $1.0040 · 5m 27s · 23 turns · 703 in / 19,087 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.