moriyoshi

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`.

Audit the licenses of every third-party dependency Cornus actually ships (the Go modules compiled into the binaries plus the npm packages bundled into the embedded web SPA), classify each as permissive / weak-copyleft / strong-copyleft, flag anything that needs review, and regenerate THIRD_PARTY_NOTICES.md and the NOTICE stanza. Use when adding or bumping dependencies, before a release, or whenever you want to re-verify license compliance.

Read `.agents/docs/JOURNAL.md` and `.agents/docs/LTM/` documents, find durable knowledge that belongs in the canonical docs, and update those documents with concise synthesized findings. Targets are `.agents/docs/OVERVIEW.md`, the root `ARCHITECTURE.md`, and the user-facing VitePress site under `docs/`. Use when journal or LTM notes have accumulated implementation, system, or user-facing knowledge that should be promoted into the project's canonical overview, architecture, or user reference 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.

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.

Translate, localize, review, or synchronize Markdown documentation while preserving source meaning, document structure, code, configuration, links, and project terminology. Use for creating or updating locale trees such as docs/ja or docs/zh, auditing an existing translation against its source, fixing mixed-language or unnatural translated prose, or propagating source-document changes into translations.

Capture a screenshot of a web page — primarily the `cornus web` SPA running locally (localhost:5000), or any URL — and embed it into a document (VitePress docs/, .agents/docs notes, or generic markdown) with the image saved to the correct asset location and a proper markdown/HTML embed. Use when asked to screenshot the web UI or a page for docs, add a UI image to a guide, or illustrate a document with a captured web view.

Consolidate related long-term memory documents under .agents/docs/LTM/ into broader synthesis documents and refresh the LTM index, keeping the source documents intact. Use when LTM has grown into overlapping topic files that should be merged into higher-level syntheses.

Read `.agents/docs/JOURNAL.md` and `.agents/docs/LTM/` documents, find durable knowledge that belongs in the canonical docs, and update those documents with concise synthesized findings. Targets are `.agents/docs/OVERVIEW.md`, the root `ARCHITECTURE.md`, and the consolidated plan `.agents/docs/PLAN.md`. Use when journal or LTM notes have accumulated implementation or design knowledge that should be promoted into the project's canonical overview, architecture, or plan.

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.

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.

Consolidate related long-term memory documents under .agents/docs/LTM/ into broader synthesis documents and refresh the LTM index, keeping the source documents intact. Use when LTM has grown into overlapping topic files that should be merged into higher-level syntheses.

Read `.agents/docs/JOURNAL.md` and `.agents/docs/LTM/` documents, find durable knowledge that belongs in the canonical docs, and update those documents with concise synthesized findings. Targets are `.agents/docs/OVERVIEW.md` and `.agents/docs/ARCHITECTURE.md`. Use when journal or LTM notes have accumulated implementation or system knowledge that should be promoted into the project's canonical overview or design document.

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.

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

Consolidate related long-term memory documents under .agents/docs/LTM/ into broader synthesis documents and refresh the LTM index. Use when LTM has grown into overlapping topic files that benefit from second-stage consolidation, 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 synthesised 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 reorganise 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.

Consolidate related long-term memory documents under .agents/docs/LTM/ into broader synthesis documents and refresh the LTM index. Use when LTM has grown into overlapping topic files that benefit from second-stage consolidation, 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 synthesised findings. Use when long-term memory notes have accumulated implementation or system knowledge that should be promoted into canonical project docs.

Read JOURNAL.md and reorganise 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 older record sections.

Read `.agents/docs/JOURNAL.md` and `.agents/docs/LTM/` documents, find durable knowledge that belongs in the canonical docs, and update those documents with concise synthesized findings. The canonical target is the root `README.md` (the as-built, human-reader-ready description of the binding); working-practice rules live in `AGENTS.md`. Use when journal or LTM notes have accumulated implementation or design knowledge that should be promoted into the project's canonical documentation.

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.

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.

Consolidate related long-term memory documents under .agents/docs/LTM/ into broader synthesis documents and a refreshed index. Use when LTM has grown into many overlapping topic files and you want higher-level, deduplicated reference material 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-organized reference files.