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 515 of 2,105
- View details
golem-update-running-agentsSkillCloud & infra
Updating running agents to a new component version. Use when asked to update existing agents, explain update modes (auto/manual), or trigger updates via the CLI or deploy command.
Ready to connect
- View details
golem-view-agent-filesSkillFiles & storage
Listing files in an agent's virtual filesystem. Use when browsing or inspecting files stored by a running agent instance.
Ready to connect
- View details
golem-view-agent-logsSkillMonitoring & ops
Viewing agent logs and output. Use when streaming agent stdout/stderr/log channels or understanding how to observe agent output at runtime.
Ready to connect
- View details
golem-wait-for-external-input-effectSkillAI & models
Waiting for external input with durable promises in an Effect-based Golem agent. Use for human-in-the-loop workflows, callbacks, external decisions, or suspending an @golemcloud/effect-golem invocation until another agent supplies data.
Ready to connect
- View details
golem-wait-for-external-input-moonbitSkillAI & models
Waiting for external input using Golem promises in a MoonBit Golem project. Use when the user asks about promises, waiting for external events, human-in-the-loop workflows, pausing an agent until an external signal, or suspending execution until data arrives from outside.
Ready to connect
- View details
golem-wait-for-external-input-rustSkillAI & models
Waiting for external input using Golem promises in a Rust Golem project. Use when the user asks about promises, waiting for external events, human-in-the-loop workflows, pausing an agent until an external signal, or suspending execution until data arrives from outside.
Ready to connect
- View details
golem-wait-for-external-input-scalaSkillAI & models
Waiting for external input using Golem promises in a Scala Golem project. Use when the user asks about promises, waiting for external events, human-in-the-loop workflows, pausing an agent until an external signal, or suspending execution until data arrives from outside.
Ready to connect
- View details
golem-wait-for-external-input-tsSkillAI & models
Waiting for external input using Golem promises in a TypeScript Golem project. Use when the user asks about promises, waiting for external events, human-in-the-loop workflows, pausing an agent until an external signal, or suspending execution until data arrives from outside.
Ready to connect
- View details
investigating-benchmark-performanceSkillMonitoring & ops
Investigating benchmark performance by running Golem benchmarks with OTLP tracing enabled and analyzing trace data from Jaeger. Use when diagnosing slow benchmarks, understanding benchmark call flows, or profiling span durations during benchmark runs.
Ready to connect
- View details
investigating-executor-performanceSkillMonitoring & ops
Investigating worker-executor performance by running executor tests with OTLP tracing enabled and analyzing trace data from Jaeger. Use when diagnosing slow tests, understanding executor call flows, or profiling span durations.
Ready to connect
- View details
managing-docs-versionsSkillDocs & knowledge
Cutting a new docs version, promoting next to a release, and managing versioned documentation content under docs/src/content/. Use when releasing a Golem version, backporting docs fixes, renaming a docs version, or changing the version selector.
Ready to connect
- View details
migrate-ts-decorator-sdkSkillAI & models
Migrating a TypeScript Golem agent from the removed decorator/base API (@agent + BaseAgent) to the current schema-driven defineAgent API. Use when porting an existing decorator-based TS agent, when you see @agent()/extends BaseAgent/@endpoint/@description code that no longer compiles, or when asked
Ready to connect
- View details
modifying-builtin-pluginsSkillDev tools
Builds and modifies built-in plugins and their descriptor-driven registry-service provisioning. Use for plugin source, committed WASM, descriptors, versions, provisioning, or grants.
Ready to connect
- View details
modifying-cli-manifest-schemaSkillDev tools
Changing the current application manifest JSON schema and aligning CLI schema references.
Ready to connect
- View details
modifying-cli-output-schemaSkillDev tools
Adding or modifying Golem CLI StructuredOutput implementations, command-output.schema.json, or DTO-backed output schema generators.
Ready to connect
- View details
modifying-http-endpointsSkillDev tools
Adding or modifying HTTP REST API endpoints in Golem services. Use when creating new endpoints, changing existing API routes, or updating request/response types for the Golem REST API.
Ready to connect
- View details
modifying-service-configsSkillDev tools
Modifying service configuration types or defaults. Use when changing config structs, adding config fields, or updating default values for any Golem service.
Ready to connect
- View details
modifying-test-componentsSkillDev tools
Builds or modifies selected test WASM components in test-components/. Use for fixture source changes, missing artifacts, or SDK changes requiring targeted downstream rebuilds.
Ready to connect
- View details
modifying-wit-interfacesSkillFiles & storage
Adding or modifying WIT (WebAssembly Interface Types) interfaces. Use when changing .wit files, updating WIT dependencies, or working with component interfaces.
Ready to connect
- View details
moonbit-agent-guideSkillFiles & storage
Guide for writing, refactoring, and testing MoonBit projects. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/run/test/doc/ide etc.), or following MoonBit-specific layout, documentation, and testing conventions.
Ready to connect
- View details
moonbit-code-transformSkillDev tools
Writing MoonBit source-to-source code transformations using moonbitlang/parser and its fmt package. Use when parsing MoonBit source into AST, constructing new AST nodes, or emitting generated MoonBit code.
Ready to connect
- View details
moonbit-proofSkillDev tools
Use when writing or refactoring proof-carrying code in MoonBit, especially for Why3-backed specifications, abstraction functions, representation invariants, proof assertions, recursive verified data structures, or reducing trusted proof bridges.
Ready to connect
- View details
moonbit-refactoringSkillDev tools
Refactor MoonBit code to be idiomatic: shrink public APIs, convert functions to methods, use pattern matching with views, add loop invariants, and ensure test coverage without regressions. Use when updating MoonBit packages or refactoring MoonBit APIs, modules, or tests.
Ready to connect
- View details
pre-pr-checklistSkillDev tools
Final checks before submitting a pull request. Use when preparing to create a PR, to ensure formatting, linting, and the correct tests have been run.
Ready to connect
- View details
rebuild-all-test-componentsSkillDev tools
Rebuilds the complete normal test-component artifact set. Use only when explicitly asked for a full rebuild or when many worker/integration test WASMs are missing.
Ready to connect
- View details
sdk-developmentSkillDev tools
Working on the Rust, TypeScript, or MoonBit SDKs in sdks/. Use when modifying SDK code, adding SDK features, or testing SDK changes with the main Golem platform.
Ready to connect
- View details
understanding-durable-executionSkillDev tools
Explains how the Golem worker executor implements durable execution: oplog recording and deterministic replay, durable host calls and guest completion delivery, the replay-to-live transition, the invocation queue and results, durable RPC exactly-once, streaming invocations and durable streams, tool
Ready to connect
- View details
boss-zhipin-scraperSkillWeb & browsing
Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Use when user wants to search/analyze jobs on BOSS直聘 or zhipin.com.
Ready to connect
- View details
fact-checkSkillSecurity
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the bur
Ready to connect
- View details
brooks-auditSkillDev tools
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codeb
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.