Model/CLAUDE.md

Available Skills

Five Claude Code skills are installed in this repo's dev container. Each maps to a phase of the feature lifecycle.

Skill	Invoke	When to use
grill-me	/grill-me	Before implementing — stress-tests a design through sequential questioning
to-prd	/to-prd	After a planning conversation — formalises context into a GitHub issue PRD
ubiquitous-language	/ubiquitous-language	When domain terms are drifting or ambiguous — builds/updates UBIQUITOUS_LANGUAGE.md
tdd	/tdd	During implementation — enforces vertical-slice TDD (one test → one impl → repeat)
improve-codebase-architecture	/improve-codebase-architecture	During refactoring — surfaces shallow modules and proposes deepening opportunities

Typical session chains

Feature planning: /grill-me → /to-prd → /ubiquitous-language

Implementation: /tdd (+ /grill-me if a design fork appears mid-session)

Refactoring: /improve-codebase-architecture → /grill-me → /tdd → /ubiquitous-language

First time setting up?

New containers install all skills automatically via the Dockerfile. If you're in an existing container, run:

bash .devcontainer/backend/install-claude-skills.sh

Type Safety

All new code must pass pyright with zero errors under typeCheckingMode = strict. Use Optional over | None Annotate all function return types. Use dict[str, Any] for untyped external API payloads — never bare dict. Add pandas-stubs when introducing pandas to a module.