Golem Cloud is the agent-native platform for building AI agents and distributed applications that never lose state, never duplicate work, and never require you to build infrastructure.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Running and debugging tests in the Golem workspace. Use when writing tests, running specific tests, filtering tests, debugging test failures, or understanding test infrastructure.
Skill Claude CodeCodex
Adding a new component or agent templates to an existing Golem application. Use when adding a second component, adding agent templates like human-in-the-loop or snapshotting to an existing component, or converting a single-component app to multi-component.
Skill Claude CodeCodex
Defining environment variables for Golem agents in golem.yaml (env, envDefaults, secretDefaults) or via CLI. Use when adding, setting, or overriding env vars on a component, agent, template, preset, or environment, or when wiring template substitution and merge modes.
Skill Claude CodeCodex
Adding initial files to Golem agent filesystems via the files: section in golem.yaml. Use when provisioning local or remote files into an agent's virtual filesystem, setting read-only / read-write permissions, or configuring file mounts at the component, agent, template, or preset level.
Skill Claude CodeCodex
Building a Golem application. Use when asked to build a Golem project, compile components to WASM, or troubleshoot build errors.
Skill Claude CodeCodex
Canceling a pending (queued) invocation on an agent. Use when canceling, removing, or aborting an enqueued invocation that has not started yet.
Skill Claude CodeCodex
Understanding and parsing Golem CLI structured output. Use when using --format json, --format yaml, --format toon, discovering $type schemas with golem output-schema, or writing agents/tools that parse CLI output.
Skill Claude CodeCodex
Setting up a Golem Cloud account from scratch. Use when creating a Golem Cloud account, authenticating with Golem Cloud via the CLI, setting up a cloud profile, or deploying to Golem Cloud for the first time.
Skill Claude CodeCodex
Configuring HTTP API domain deployments and security schemes in golem.yaml. Use when the user asks to deploy agents to a domain, configure API domains, set up authentication/security schemes (OIDC), or manage the httpApi section of the application manifest.
Skill Claude CodeCodex
Configuring MCP (Model Context Protocol) server deployments in golem.yaml. Use when the user asks to expose agents through MCP, enable MCP for an agent, add MCP server support, set up MCP authentication, or configure MCP deployments for local or cloud environments.
Skill Claude CodeCodex
Querying the operation log. Use when dumping or searching the oplog, or debugging agent behavior from its recorded history.
Skill Claude CodeCodex
Deleting an agent instance. Use when removing, deleting, or destroying a running or idle agent instance via the CLI.
Skill Claude CodeCodex
Deploying a Golem application. Use when asked to deploy agents to a Golem server, update running agents, or troubleshoot deployment issues.
Skill Claude CodeCodex
Configuring the deployment logical version in the Golem Application Manifest (golem.yaml): the version: source (git tag, git commit hash, static string, or env var), tuning tagPattern/hashFallback/staticFallback/allowDirty, per-environment version overrides, and the versionCheck uniqueness policy. Use when setting up…
Skill Claude CodeCodex
Editing the Golem Application Manifest (golem.yaml). Use when modifying any section of golem.yaml — components, agents, templates, presets, environments, httpApi, mcp, bridge SDKs, build commands, config, wasiConfig, plugins, files, custom commands, clean paths, retry policies, resource quotas, or secret defaults.
Skill Claude CodeCodex
Checking agent metadata and status. Use when inspecting an agent's state, component revision, environment variables, update history, or current status.
Skill Claude CodeCodex
Setting up a dedicated Golem environment for integration testing. Use when adding integration tests for a Golem application, configuring a throwaway local server for tests, isolating test state from local development, or wiring up CI to run end-to-end tests against a real Golem server.
Skill Claude CodeCodex
Interrupting and resuming a Golem agent. Use when pausing, suspending, interrupting, or resuming an agent instance via the CLI.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: