community

Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.

This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.

3134 available skills

production

Logo of WynterJones
WynterJones

Chat with AI agents to build, manage, and orchestrate custom tools, dashboards, and it's all powered by cats.

2
0
AI

manage

Logo of Borda
Borda

A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

2
0
AI

skill-stocktake

Logo of T-rav
T-rav

HydraFlow is a delivery kernel for GitHub repositories: it accepts intent, compiles it through a staged pipeline, enforces quality gates, and produces merged software changes.

2
0
AI

ck:skill-creator

Logo of ngocsangyem
ngocsangyem

My personal blog

2
0
Developer

openspec-continue-change

Logo of ruan-cat
ruan-cat

01星球的第11次大项目。智慧社区项目。

2
0
Developer

raven-investigate

Logo of AutumnsGrove
AutumnsGrove

A forest of voices. Writing and community tools for a quieter corner of the internet.

2
0
Developer

reproduce

Logo of ferrucc-io
ferrucc-io

A CLI + Skill for debugging with Claude Code

2
0
Developer

implement-feature

Logo of lazyoft
lazyoft

An example of an invoicing system written by Raymond

2
0
Developer

sns

Logo of NobleDarkGames
NobleDarkGames

Godot-based tactical RPG creation platform

2
0
Developer

create-domain-story

Logo of wfukatsu
wfukatsu

Legacy system analysis and microservices refactoring agent system for Claude Code

2
0
Developer

commit

Logo of zachsnoek
zachsnoek

My personal website. Built with Next.js, TypeScript, and MDX

2
0
Developer

committing-staged-with-message

Logo of qte77
qte77

A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.

2
0
Developer