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.
Comprehensive visual design audit using agent-browser. Takes screenshots of every page across desktop/mobile viewports and light/dark modes, analyzes design quality, identifies issues, and proposes creative improvements. Use when reviewing design, checking dark mode, or auditing UI quality.
BattleChain is a ZKSync-based L2 blockchain that enables secure protocol deployment. This AI agent skill helps developers streamline their workflow and enhance security.
Un créateur de sous-agents est un outil qui permet de définir et d'améliorer les sous-agents spécialisés de Claude
Generate professional git commit message based on changes
La compétence doey-add-team est un outil CLI pour créer des équipes d'agents multiples basées sur Tmux
Agent Skills suite for researching US credit cards — works with Claude Code, Codex, Cursor, Gemini CLI, and any Agent Skills-compatible tool
Kubernetes cluster operations on minikube including observability (Grafana, Prometheus, Alertmanager, Loki, Tempo), debugging (kubectl debug, ephemeral containers), and cluster management (ArgoCD). Use when working with cluster/manifests/, Kubernetes workloads, pods, deployments, operators, controllers, or cluster components.
Interface design with craft and consistency. For dashboards, apps, tools — not marketing sites. Uses Subcog for persistent design memory.
Generate TDD task breakdown for SDD workflow. Use when breaking down design into implementable tasks with test-first approach. Invoked via /sdd-tasks <feature-name>.
Use when retail prices are failing for a vendor — wrong prices, fractional_weight warnings, all-zeros for a provider, page-loaded-no-price errors, or after suspecting a dealer changed their site structure. Covers live Firecrawl diagnostics, interpreting extraction failures, and updating price-extract.js and providers.json.
Debug a users bug by instrumenting their code with clog log statements, having them reproduce the issue, then analyzing the logs to find root cause
Symbol-level refactoring with automatic reference updates using Serena MCP