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
63,139 results · page 513 of 2,105
- View details
golem-mark-read-only-rustSkillAI & models
Marking Rust agent methods as read-only for a side-effect-free guarantee and result caching. Use when the user wants a cacheable query method, a method that must not write to the oplog, or HTTP GET endpoints that emit cache headers.
Ready to connect
- View details
golem-mark-read-only-scalaSkillAI & models
Marking Scala agent methods as read-only for a side-effect-free guarantee and result caching. Use when the user wants a cacheable query method, a method that must not write to the oplog, or HTTP GET endpoints that emit cache headers.
Ready to connect
- View details
golem-mark-read-only-tsSkillAI & models
Marking TypeScript agent methods as read-only for a side-effect-free guarantee and result caching. Use when the user wants a cacheable query method, a method that must not write to the oplog, or HTTP GET endpoints that emit cache headers.
Ready to connect
- View details
golem-multi-instance-agent-effectSkillAI & models
Creating and reconnecting multiple Effect-based agent instances with identical agent id fields. Use for phantom agents, newPhantom/getPhantom, phantom IDs, or independent per-instance state with @golemcloud/effect-golem.
Ready to connect
- View details
golem-multi-instance-agent-moonbitSkillAI & models
Creating multiple agent instances with the same constructor parameters using phantom agents in MoonBit. Use when the user needs multiple independent instances sharing the same identity parameters.
Ready to connect
- View details
golem-multi-instance-agent-rustSkillAI & models
Using phantom agents in Rust to create multiple agent instances with the same constructor parameters. Use when the user needs multiple distinct agents sharing constructor values, or asks about phantom agents, phantom IDs, getPhantom/newPhantom, or multi-instance agents in Rust.
Ready to connect
- View details
golem-multi-instance-agent-scalaSkillAI & models
Using phantom agents in Scala to create multiple agent instances with the same constructor parameters. Use when the user needs multiple distinct agents sharing constructor values, or asks about phantom agents, phantom IDs, getPhantom/newPhantom, or multi-instance agents in Scala.
Ready to connect
- View details
golem-multi-instance-agent-tsSkillAI & models
Using phantom agents in TypeScript to create multiple agent instances with the same constructor parameters. Use when the user needs multiple distinct agents sharing constructor values, or asks about phantom agents, phantom IDs, getPhantom/newPhantom, or multi-instance agents in TypeScript.
Ready to connect
- View details
golem-new-projectSkillDev tools
Creating a new Golem application project. Use when scaffolding a new Golem project with golem new, selecting a language template, and setting up the initial project structure.
Ready to connect
- View details
golem-parallel-workers-effectSkillAI & models
Fans out work to multiple durable agents and collects results with Effect structured concurrency. Use for parallel execution, fan-out/fan-in, bounded concurrency, child fibers, agent forks, or aggregating remote agent results in an @golemcloud/effect-golem project.
Ready to connect
- View details
golem-parallel-workers-moonbitSkillAI & models
Fan out work to multiple parallel agents and collect results in a MoonBit Golem project. Use when the user asks about parallel execution, fan-out/fan-in, spawning child agents for parallel work, forking, or aggregating results from multiple agents.
Ready to connect
- View details
golem-parallel-workers-rustSkillAI & models
Fan out work to multiple parallel agents and collect results in a Rust Golem project. Use when the user asks about parallel execution, fan-out/fan-in, spawning child agents for parallel work, forking, or aggregating results from multiple agents.
Ready to connect
- View details
golem-parallel-workers-scalaSkillAI & models
Fan out work to multiple parallel agents and collect results in a Scala Golem project. Use when the user asks about parallel execution, fan-out/fan-in, spawning child agents for parallel work, forking, or aggregating results from multiple agents.
Ready to connect
- View details
golem-parallel-workers-tsSkillAI & models
Fan out work to multiple parallel agents and collect results in a TypeScript Golem project. Use when the user asks about parallel execution, fan-out/fan-in, spawning child agents for parallel work, forking, or aggregating results from multiple agents.
Ready to connect
- View details
golem-permission-card-effectSkillAI & models
Transfers opaque permission cards across Effect agent, tool, and middleware boundaries. Use when delegated authority is part of a schema.
Ready to connect
- View details
golem-profiles-and-environmentsSkillCloud & infra
Understanding Golem CLI profiles, application environments, and component presets. Use when configuring deployment targets, switching between local and cloud servers, managing CLI profiles, defining environment-specific presets, or understanding how environments, presets, and profiles interact.
Ready to connect
- View details
golem-quota-effectSkillAI & models
Adding resource quotas to an Effect-based Golem agent. Use when the user asks about rate limiting, resource quotas, Quota tokens, Quota.acquireQuotaToken, Quota.withReservation, throttling API calls, limiting concurrency, capacity limits, or splitting tokens between agents.
Ready to connect
- View details
golem-quota-moonbitSkillAI & models
Adding resource quotas to a MoonBit Golem agent. Use when the user asks about rate limiting, resource quotas, quota tokens, QuotaToken, with_reservation, throttling API calls, limiting concurrency, capacity limits, or splitting tokens between agents.
Ready to connect
- View details
golem-quota-rustSkillAI & models
Adding resource quotas to a Rust Golem agent. Use when the user asks about rate limiting, resource quotas, quota tokens, QuotaToken, reservations, throttling API calls, limiting concurrency, capacity limits, or splitting tokens between agents.
Ready to connect
- View details
golem-quota-scalaSkillAI & models
Adding resource quotas to a Scala Golem agent. Use when the user asks about rate limiting, resource quotas, quota tokens, QuotaToken, withReservation, throttling API calls, limiting concurrency, capacity limits, or splitting tokens between agents.
Ready to connect
- View details
golem-quota-tsSkillAI & models
Adding resource quotas to a TypeScript Golem agent. Use when the user asks about rate limiting, resource quotas, quota tokens, acquireQuotaToken, withReservation, throttling API calls, limiting concurrency, capacity limits, or splitting tokens between agents.
Ready to connect
- View details
golem-read-only-method-effectSkillAI & models
Adds cacheable read-only methods to Effect Golem agents. Use for queries that do not mutate agent state.
Ready to connect
- View details
golem-recurring-task-effectSkillProductivity
Implementing durable recurring, cron-like, polling, cleanup, and heartbeat tasks by self-scheduling Effect Golem agent methods. Use for periodic jobs, exponential backoff, cancelable schedules, or self-scheduling agents with @golemcloud/effect-golem.
Ready to connect
- View details
golem-recurring-task-moonbitSkillProductivity
Implementing a recurring (cron-like) task in a MoonBit Golem agent by self-scheduling future invocations. Use when the user asks about periodic tasks, recurring jobs, cron-like scheduling, polling loops, heartbeats, or self-scheduling agents.
Ready to connect
- View details
golem-recurring-task-rustSkillProductivity
Implements recurring Rust agent work by self-scheduling future invocations. Use for periodic jobs, polling loops, heartbeats, cleanup, or retry backoff.
Ready to connect
- View details
golem-recurring-task-scalaSkillProductivity
Implementing a recurring (cron-like) task in a Scala Golem agent by self-scheduling future invocations. Use when the user asks about periodic tasks, recurring jobs, cron-like scheduling, polling loops, heartbeats, or self-scheduling agents.
Ready to connect
- View details
golem-recurring-task-tsSkillProductivity
Implementing a recurring (cron-like) task in a TypeScript Golem agent by self-scheduling future invocations. Use when the user asks about periodic tasks, recurring jobs, cron-like scheduling, polling loops, heartbeats, or self-scheduling agents.
Ready to connect
- View details
golem-redeploy-agentsSkillCloud & infra
Redeploying existing agents by deleting and recreating them. Use when asked to redeploy agents, reset agent state while keeping the same identity, or force agents to start fresh with the latest component version.
Ready to connect
- View details
golem-retry-policies-effectSkillProductivity
Configures Golem host-operation retry policies for Effect-based agents and distinguishes them from Effect typed failures and Schedule retries. Use for retry policies, exponential backoff, transient recovery, retry predicates, Retry.withPolicy, Retry.setPolicy, Effect.retry, or retry-policy manifests
Ready to connect
- View details
golem-retry-policies-moonbitSkillAI & models
Configuring semantic retry policies for a MoonBit Golem agent. Use when the user asks about retry policies, retry strategies, exponential backoff, error handling retries, transient error recovery, retry predicates, with_named_policy, NamedPolicy, Policy composition, jitter, countBox, timeBox, andThe
Ready to connect
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
63,068 of the 63,139 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.