chatto

Keep track of architectural decisions in a structured format using Architecture Decision Records (ADRs).

Run a full review of all Architecture Decision Records for implementation drift, contradictions, stale decisions, missing supersession notes, weak rationale, and missing cross-references. Use when the user asks for an ADR review, ADR audit, stale ADR check, architecture decision consistency check, or wants to verify ADRs against the current codebase, feature/design records, architecture docs, glossary, or public API state.

Review Chatto public API and protocol changes for compatibility, migration needs, and generated output.

Design rules concerning Chatto's ConnectRPC API, both resources and realtime

Maintain Chatto runtime documentation in docs/architecture/ when runtime structures change, or audit it when requested.

Audit Chatto API design for consistency, completeness, integration use, and future growth. Use for a whole-API review or a focused review of a service or workflow.

Use when designing, implementing, reviewing, debugging, or documenting Chatto event-sourced domain behavior, including EVT subjects, aggregate boundaries, Services, projections, optimistic concurrency control, read-your-writes, live/reconnect delivery, replay compatibility, migration safety, and rollback/deployment implications.

Check a Chatto pull request before review or merge. Use when opening a PR or when asked to check one.

Create or update Chatto release pages from release-please state, tags, changelog entries, and PRs.

Keep track of Chatto's features as Feature Decision Records (FDRs) — one structured document per feature capturing behavior, design decisions, and rationale. Replaces the older agent-docs/features/ system.

Look up, add, or audit Chatto terms in docs/GLOSSARY.md.

Apply the repository-wide Loom Architecture—Log-Oriented Outcomes and Materializations—when designing, implementing, reviewing, debugging, or documenting NATS and JetStream event-sourced applications. Use for work involving NATS account boundaries, a primary event stream, optimistic concurrency control, projections and read-your-writes, snapshots or checkpoints, snapshot repositories, durable workers, or reliable external effects.

Review a completed, paused, or blocked coding-agent session to identify friction, mistakes, near misses, missing context, and opportunities to improve future work. Use when the user asks to wrap up, run a retrospective, explain what issues the agent faced, capture lessons learned, or recommend improvements to repository instructions, documentation, skills, tooling, tests, or workflows. Produce an evidence-based, propose-only report; do not apply follow-up changes unless the user asks.

Use the Svelte CLI to check any Svelte component or module that you create, edit, or analyze.

Guidance on writing fast, robust, modern Svelte code. Load this skill whenever in a Svelte project and asked to write/edit or analyze a Svelte component or module. Covers reactivity, event handling, styling, integration with libraries and more.

Look up official Svelte, SvelteKit, and Svelte CLI documentation.

Update Chatto Go and frontend dependencies within their compatible version ranges, then run tests.

Instructions and hints for writing tests.