Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
70,704 results · page 648 of 2,357
- View details
golem-interrupt-resume-agentSkillAI & models
Pause and later restart a running Golem agent using simple command-line commands.
Ready to connect★ 2k
- View details
golem-invoke-agent-effectSkillCloud & infra
Lets your agent call methods on a deployed Golem agent from the command line and see the results.
Ready to connect★ 2k
- View details
golem-invoke-agent-moonbitSkillCloud & infra
Lets your agent call a method on a deployed Golem agent from the command line and see its results.
Ready to connect★ 2k
- View details
golem-invoke-agent-rustSkillCloud & infra
Lets your agent call a method on a deployed Golem agent from the command line.
★ 2k
- View details
golem-invoke-agent-scalaSkillCloud & infra
Runs a method on a deployed Scala Golem cloud agent straight from the command line.
Ready to connect★ 2k
- View details
golem-invoke-agent-tsSkillCloud & infra
Lets your agent call a specific method on a deployed Golem cloud agent straight from the command line.
★ 2k
- View details
golem-js-runtimeSkillWeb & browsing
Lets your agent run and inspect JavaScript in a sandboxed WebAssembly runtime with web and Node-style APIs.
Ready to connect★ 2k
- View details
golem-list-and-filter-agentsSkillAI & models
Lets your agent list Golem agents and filter them by name, status, revision, creation time, or env vars.
Ready to connect★ 2k
- View details
golem-local-dev-serverSkillCloud & infra
Lets your agent start, configure, and debug a local Golem development server for building and testing agents.
Ready to connect★ 2k
- View details
golem-logging-effectSkillCommunication
Shows your agent how to add structured logs, log levels, and tracing spans to an Effect-based Golem agent.
Ready to connect★ 2k
- View details
golem-logging-moonbitSkillCommunication
Lets your agent add logging and debug output to MoonBit Golem agents.
Ready to connect★ 2k
- View details
golem-logging-rustSkillCommunication
Guides your agent to add logging with levels like debug, info, and error to Rust code.
Ready to connect★ 2k
- View details
golem-logging-scalaSkillCommunication
Adds logging so your Scala Golem agent can print debug, info and error messages while running.
Ready to connect★ 2k
- View details
golem-logging-tsSkillMonitoring & ops
Adds logging to a TypeScript Golem agent so it prints debug, info, and error output.
Ready to connect★ 2k
- View details
golem-make-http-request-effectSkillAI & models
Lets your agent make outgoing HTTP requests to external APIs from Effect-based Golem code.
Ready to connect★ 2k
- View details
golem-make-http-request-moonbitSkillAI & models
Lets your agent make HTTP requests to external APIs and fetch data from URLs in MoonBit Golem code.
Ready to connect★ 2k
- View details
golem-make-http-request-rustSkillAI & models
Lets your agent make outgoing HTTP requests to external APIs from Rust code.
Ready to connect★ 2k
- View details
golem-make-http-request-scalaSkillAI & models
Lets your agent make outgoing HTTP requests to external APIs using Scala code.
Ready to connect★ 2k
- View details
golem-make-http-request-tsSkillAI & models
Lets your agent written in TypeScript make HTTP requests to call external APIs.
Ready to connect★ 2k
- View details
golem-manage-pluginsSkillDev tools
Lets your agent list, install, and configure Golem plugins, including built-in ones like the OTLP exporter.
Ready to connect★ 2k
- View details
golem-mark-read-only-moonbitSkillAI & models
Lets your agent mark MoonBit agent methods as read-only so they can't write data and their results can be cached.
Ready to connect★ 2k
- View details
golem-mark-read-only-rustSkillAI & models
Lets your agent mark Rust agent methods as read-only so they can't cause side effects and their results can be cached.
Ready to connect★ 2k
- View details
golem-mark-read-only-scalaSkillAI & models
Marks Scala agent methods as read-only so results can be cached safely.
Ready to connect★ 2k
- View details
golem-mark-read-only-tsSkillAI & models
Marks your agent's TypeScript methods as read-only so they cannot cause side effects and their results get cached.
Ready to connect★ 2k
- View details
golem-multi-instance-agent-effectSkillAI & models
Lets your agent create and reconnect multiple independent instances of the same agent, each with its own state.
Ready to connect★ 2k
- View details
golem-multi-instance-agent-moonbitSkillAI & models
Lets your agent create multiple independent AI agent instances that share the same setup parameters in MoonBit.
Ready to connect★ 2k
- View details
golem-multi-instance-agent-rustSkillAI & models
Lets your agent create multiple distinct AI agent instances in Rust that share the same constructor values.
Ready to connect★ 2k
- View details
golem-multi-instance-agent-scalaSkillAI & models
Lets your agent write Scala code that creates many separate agent instances sharing the same setup values.
Ready to connect★ 2k
- View details
golem-multi-instance-agent-tsSkillAI & models
Lets your agent write TypeScript that creates many agent instances sharing the same constructor settings.
Ready to connect★ 2k
- View details
golem-new-projectSkillDev tools
Scaffolds a new Golem application project in Rust, TypeScript, Effect, or Scala using the golem CLI.
Ready to connect★ 2k
Popular skills lists
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
- Best Claude skills for superpowers
- Best Claude skills for obsidian
- Best Claude skills for frontend design
- All best lists
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
68,574 of the 70,704 skills listed here can be served through Ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your workspace and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.