Skills
The open registry for AI agent skills — structured prompts and workflows with recommended models, example prompts, and compatible tools.
Skills
5
Categories
9
Compatible tools
5
Contributors
1
Showing 1–5 of 5 skills
Generates Docker Compose configurations from application requirements. Handles service dependencies, networking, volumes, health checks, environment variables, and multi-stage builds. Supports development and production profiles.
Builds and explains cron expressions from natural language schedules. Supports standard cron (5-field), extended cron (6-field with seconds), and cloud-specific formats (AWS EventBridge, Google Cloud Scheduler). Validates expressions and shows next run times.
Plans and generates migration strategies for framework upgrades, language versions, database changes, and architecture shifts. Produces step-by-step migration guides with rollback plans, risk assessment, and automated codemods where possible.
Generates .env files, configuration schemas, and environment variable documentation from application requirements. Includes validation rules, default values, required vs optional flags, and example values. Supports multiple environments (dev/staging/prod).
Designs and implements CI/CD pipelines for various platforms (GitHub Actions, GitLab CI, Jenkins, CircleCI). Covers build, test, lint, security scan, deploy stages with proper caching, parallelization, and environment management.
Skills vs MCP servers
what's the difference?Skillsthe “what to do”
A skillA reusable, structured prompt/workflow with recommended models, an example prompt, and compatible tools. packages know-how — instructions, an example promptA ready-to-use prompt template that demonstrates how to invoke the skill., and recommended models — so an agent performs a task consistently. Skills add knowledge, not new connections.
MCP serversthe “how to connect”
An MCP serverModel Context Protocol server — a standard way to expose tools, resources, and prompts to AI agents and IDEs. gives an agent new capabilities by connecting it to real systems (databases, APIs, files) over a transportHow the client talks to the server: stdio (local process), SSE, or HTTP streaming.. MCP adds connections and actions, not task instructions.
Rule of thumb: reach for a skill when you need the model to do a task well, and an MCP server when you need it to reach a tool or system. They compose — a skill can rely on tools an MCP server provides.
Built a useful skill?
Submit a SKILL.md — it's open source and community-maintained.