Ready-to-use skills that enhance AI coding agents with minimal setup—just add SKILL.md and deploy.
Analyzes git commit and PR history to generate structured release notes (RELEASE_NOTES.md). Automatically categorizes changes, identifies contributors, and produces a polished release document through a brief confirmation interview.
Conducts a deep, multi-round interview to clarify ambiguous requirements and produces a structured specification document. Automatically discovers requirement files and asks probing, non-obvious questions across technical implementation, UX/UI, trade-offs, edge cases, and architectural decisions.
A collection of reusable skills for AI coding agents. Share, discover, and compose skills that make your agent smarter.
Compatible with SkillsMP | Claude Code | Codex CLI | ChatGPT
This project follows the official Anthropic Agent Skills Specification and is registered as a Claude Code plugin marketplace.
Skills are defined as SKILL.md files — structured markdown documents that AI agents automatically recognize and execute. Each skill encodes a specific workflow (e.g., conducting a requirements interview and producing a specification document), turning a multi-step process into a single command.
| Skill | Description | Status |
|---|---|---|
| spec-interview | Transforms vague requirements into actionable specifications (SPEC.md) through structured multi-round interviews | ✅ |
| release-notes | Analyzes git history to generate structured release notes (RELEASE_NOTES.md) with categorized changes and contributors | ✅ |
✅ Ready | 🚧 In Progress | 📋 Planned
Agents are autonomous task executors that can be invoked via the Task tool in Claude Code. They are defined in .claude/agents/ directory.
| Agent | Description | Tools | Status |
|---|---|---|---|
| load-test | k6 load test execution and automated report generation with performance metrics | Bash, Read, Write, Glob | ✅ |
Usage:
"Run API load test"
"Execute k6 performance test"
Trigger Keywords: load test, performance test, k6, stress test
Usage:
/spec-interview
The skill will automatically discover requirement files (SPEC.md, PRD.md, REQUIREMENTS.md, etc.) in your project and begin the interview process.
# 1. Clone the repository
git clone https://github.com/kangminhyuk1111/agent-skill-kit.git
# 2. Copy the skills you want into your project
cp -r agent-skill-kit/skills/spec-interview /your-project/skills/
# 3. Invoke the skill from your agent
/spec-interview
Alternatively, clone the entire repository and symlink individual skill directories into your projects as needed.
New skill contributions are welcome. To add a skill:
Create a new directory under skills/:
skills/
└── your-skill-name/
└── SKILL.md
Write your SKILL.md with the following structure:
---
name: your-skill-name
description: A short one-line description of what the skill does.
---
# Skill Title
## Overview
What the skill does and when to use it.
## Instructions
Step-by-step instructions the agent will follow.
## Examples
Input/output examples demonstrating the skill.
## Guidelines
Best practices and constraints.
Register the skill in .claude-plugin/marketplace.json by adding it to the appropriate plugin group:
{
"name": "your-plugin-group",
"description": "Group description",
"source": "./",
"strict": false,
"skills": [
"./skills/your-skill-name"
]
}
Submit a pull request.
Apache 2.0
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin kangminhyuk1111-agentsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.