Browse and Install AI Agent Skills

Parcourez et installez des milliers de compétences pour AI Agents dans le répertoire Killer-Skills. Compatible avec Claude Code, Windsurf, Cursor et plus.

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.

9 compétences disponibles

mflux-cli

Logo of filipstrand
filipstrand

MLX native implementations of state-of-the-art generative image models

mflux-testing

Logo of filipstrand
filipstrand

Run tests in mflux (fast/slow/full), preserve image outputs, and handle golden image diffs safely.

team-review

Logo of catlog22
catlog22

Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review.

1.5k
0
Productivité

team-coordinate

Logo of catlog22
catlog22

Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for orchestration. Triggers on Team Coordinate .

1.4k
0
Productivité

workflow-multi-cli-plan

Logo of catlog22
catlog22

Multi-CLI collaborative planning and execution skill with integrated execution phase. Triggers on workflow-multi-cli-plan.

1.4k
0
Productivité

team-lifecycle

Logo of catlog22
catlog22

Unified team skill for full lifecycle - spec/impl/test. All roles invoke this skill with --role arg for role-specific execution.

1.3k
0
Productivité

ltx2

Logo of digitalsamba
digitalsamba

AI-native video production toolkit for Claude Code

wt

Logo of llama-farm
llama-farm

The wt skill streamlines AI model deployment, enabling developers to work efficiently with isolated environments and parallel coding sessions, perfect for AI coding workflows

generate-subsystem-skills

Logo of llama-farm
llama-farm

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes