agent-development
This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.
53
29%
Does it follow best practices?
Impact
96%
1.84xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/toolkit/skills/agent-development/SKILL.mdEvaluation results
90%
40%Development Pipeline Agent Suite
Agent color conventions
YAML frontmatter color field
100%
100%
Explore agent color
0%
100%
Plan agent color
0%
100%
Create agent color
100%
100%
Debug agent color
0%
100%
Clean agent color
0%
0%
No mismatched colors
0%
100%
Color in frontmatter only
100%
100%
Frontmatter name field
100%
100%
Multiple agent files
100%
100%
100%
20%Automated Security Review Agent
Permission denial resilience
Color in frontmatter
0%
100%
Red color for review/reflect agent
0%
100%
Continues after denial
100%
100%
Alternative approach guidance
100%
100%
Does not stop on denial
100%
100%
Handles access restrictions
100%
100%
Frontmatter name and description
100%
100%
100%
72%Agent Fleet Expansion for Release Pipeline
Hot-reload notification and color assignment
Orchestration agent cyan color
0%
100%
Cleanup agent yellow color
0%
100%
Color in YAML frontmatter
0%
100%
No restart needed message
40%
100%
Immediate effect / hot-reload statement
0%
100%
Changelog or ops note produced
100%
100%
Frontmatter name field present
100%
100%
- Repository
- dwmkerr/claude-toolkit
- Commit
ccd0360
- 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.