winterbaume

Generate AWS API coverage reports comparing winterbaume implementations against official AWS API models, plus Terraform converter coverage at the resource-type and per-attribute levels.

Use when the vendored AWS Smithy models under vendor/api-models-aws change, or when API coverage, README service tables, TODO unimplemented-service lists, generated model/wire files, or service dossiers need to be reconciled with the current Smithy checkout.

Update README.md with the latest API coverage data from the api-coverage skill.

Implement or enhance an AWS service in winterbaume — creates a new crate from a stub or adds missing operations to an existing crate. Targets moto API coverage parity.

Port moto's Python test cases for a given AWS service to winterbaume Rust integration tests. Reads moto tests from the moto GitHub repository, translates to aws-sdk-rust + MockAws style, and appends to existing integration_test.rs.

Check whether a service crate passes the publication quality gate, then fix all failures. Reads the crate's source files, runs build/clippy/test, reports pass/fail for each gate check, creates a TODO list of failures, and works through them until the crate passes.

Generate a new AWS service dossier under .agents/docs/services or enhance an existing service dossier with Smithy-derived operation/resource facts, official AWS documentation research, concrete usage scenarios, and durable Winterbaume LTM lessons.

Research an AWS service via AWS Documentation MCP Server, plan a comprehensive test suite, write the plan to JOURNAL.md, and implement two complementary test files — per-operation integration tests in `tests/integration_test.rs` and end-to-end scenario tests in `tests/scenario_test.rs`.

Generate or update the root umbrella CHANGELOG.md and per-crate CHANGELOG.md files from cargo-dist style git release tags, GitHub release context, and commit history. Use when Codex is asked to create changelogs, compare changes between independent crate releases, prepare release notes, fill an Unreleased section, regenerate crate changelogs, or refresh the root changelog for winterbaume.

Implement or enhance a Terraform converter for an AWS service via the spec-driven codegen pipeline. Creates a new spec + converter or adds missing resource types / fields to an existing one.

Generate terraform E2E test suites for an AWS service, testing all terraform resource types winterbaume's handlers support via real `terraform apply` against an in-process server.

File a winterbaume bug report on GitHub Issues using the project's official bug-report issue form layout, so that the auto-label-service workflow can apply the correct `service:<slug>` label. Use this whenever Claude (or the user) discovers a defect in a `winterbaume-<service>` crate during exploration, testing, or development — for example a wrong status code, a missing field, a serialisation bug, an incorrect default, or any divergence from real AWS behaviour — and the bug should be tracked in the issue tracker. Use proactively whenever the user says things like "file a bug", "open an issue", "report this", "track this regression", or otherwise indicates the finding should not be lost. Do NOT use for feature requests, design discussions, or work that is being fixed in the same session without an issue.

Consolidate related long-term memory documents under .agents/docs/LTM/ into broader synthesis documents, refresh the LTM index, and promote service-specific durable knowledge into .agents/docs/services/*.md. Use when LTM has grown into overlapping topic files or when service-specific LTM findings should be folded into the AWS service research documents without deleting the source documents.

Read `.agents/docs/LTM/` documents, find durable knowledge that belongs in `.agents/docs/OVERVIEW.md` or `.agents/docs/ARCHITECTURE.md`, and update those core documents with concise synthesized findings. Use when long-term memory notes have accumulated implementation or system knowledge that should be promoted into the project's canonical overview or architecture docs.

Read JOURNAL.md and reorganize its contents into semantically separate long-term memory documents under .agents/docs/LTM/. Use when you want to consolidate accumulated journal entries into reusable, topic-organised reference files.

Audit whether the durable information in `.agents/docs/JOURNAL.md` is already represented in `.agents/docs/LTM/` and `.agents/docs/TODO.md`; if not, follow the `good-sleep` workflow to fill the gaps, then collapse all JOURNAL consolidation records into one canonical entry and remove the older record sections.

Refactor a service crate's state module to use domain-specific error enums instead of constructing end-user-facing error structs (error_type/message/status). Moves error shaping responsibility into the handler layer.

Read TODO.md and scan source code for TODO/FIXME comments, build a consolidated list, then dispatch parallel agents to address as many items as possible.

Verify whether the current Winterbaume repository state conforms to RELEASE.md and the public publish readiness gates embedded in this skill. Use when asked to check release readiness, publish readiness, first public release readiness, crates.io publishability metadata, cargo-dist release readiness, or public launch blockers.