kagent

1 stars 2 forks
17
D

Kubernetes-native AI agent framework for building, deploying, and managing AI agents on Kubernetes. This skill should be used when deploying AI agents as Kubernetes resources, analyzing cluster health with AI, and automating complex K8s operations. Use this skill for Phase IV advanced AIOps and agent-based cluster management.

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install mjunaidca/mjs-agent-skills/kagent
skilz install mjunaidca/mjs-agent-skills/kagent --agent opencode
skilz install mjunaidca/mjs-agent-skills/kagent --agent codex
skilz install mjunaidca/mjs-agent-skills/kagent --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/mjunaidca/mjs-agent-skills
2. Copy the agent skill directory:
cp -r mjs-agent-skills/docs/taskflow-vault/skills/engineering/kagent ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Stars
1
Forks
2
Type
Technical
Meta-Domain
cloud infrastructure
Primary Domain
kubernetes
Market Score
17

Agent Skill Grade

D
Score: 68/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
18/30
Ease of Use
19/25
Writing Style
8/10
Utility
14/20
Modifiers: -2

Areas to Improve

  • Description needs trigger phrases
  • Missing Reference File
  • No Table of Contents

Recommendations

  • Address 3 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I've been digging into your skill and notice you're trying to solve the agent orchestration problem—that's a genuinely tricky space where small design choices compound quickly. Your implementation landed at 68/100 (D grade), which tells me there's solid foundation here but some friction points worth discussing.

Links:

The TL;DR

You're at 68/100 (D territory). This is based on Anthropic's 5-pillar rubric for skill architecture. Your Writing Style scored strongest at 8/10—the technical voice is clean and consistent. The weaknesses are in Progressive Disclosure (18/30) and Spec Compliance (11/15). That's hurting discoverability and token efficiency.

What's Working Well

  • Clear technical voice – Your kubectl examples and CRD explanations are straightforward without marketing fluff
  • Solid metadata – The skill name follows conventions and the description is specific about what kagent does
  • Good examples – You've got real YAML CRD examples that actually show how to define agents
  • Consistent terminology – "agent", "CRD", "kubectl" used correctly throughout, no confusion

The Big One: Missing Trigger Phrases

This is what's dragging down your spec compliance score. Your description says "Kubernetes-native AI agent framework..." but has zero trigger phrases. Developers looking for skills search by action words. Right now, someone saying "run kagent" or "deploy agent" won't find you.

The fix: Add trigger phrases to your description frontmatter:

description: Performs kagent operations. Use when asked to "kagent", "run kagent", "build agent on kubernetes", or "deploy AI agent".

This one change gets you +2 points immediately and makes your skill actually ...

Report Security Issue

Found a security vulnerability in this agent skill?