L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Documents · SKILL.md

archi-vide

archi-vide

Generate an empty, strongly-typed code architecture (no implementation), with minimal comments that document behavior and relationships between modules.

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: archi-vide description: Generate an empty, strongly-typed code architecture (no implementation), with minimal comments that document behavior and relationships between modules.

Empty Architecture (Archi Vide)

Generate code scaffolding that is:

  • Empty: no business logic, no side effects.
  • Predictable: explicit dependencies and module boundaries.
  • Readable: relationships are clear from type signatures + minimal doc comments.
  • Strictly typed: type composition + generics by default.

Trigger this skill whenever the user asks for:

  • A project/module skeleton, scaffolding, or “architecture”
  • Stubbed code, interfaces, ports/adapters, clean architecture, DDD boundaries
  • “Empty implementation” files to be filled later

Output contract

Always deliver:

  1. File tree (final structure).
  2. Code for each file (or only the files the user requests).
  3. One short rationale explaining boundaries + dependency direction.
  4. An architecture note: an archi-*.md document (global → details) including: why, external impacts, expected results.

Non-goals

  • No real behavior, no algorithm, no persistence, no network calls.
  • No heavy abstraction, no frameworks unless the user explicitly asks for one.
  • No speculative features.

Required loading (selective)

Always apply:

  • Naming (mandatory): Use Skill naming-convention for every single identifier (files, folders, modules, namespaces, classes, types, interfaces, functions, methods, parameters, return types, variables, properties, DB tables/columns, routes).
    • Fallback if naming-convention is unavailable: camelCase functions/variables, PascalCase types/classes/components, kebab-case JS/TS/CSS files, snake_case Python/Ruby/Dart/Go files, SCREAMING_SNAKE_CASE constants — and keep names prefix + entity (+ suffix) shaped.
  • Types: load references/type-rules.md.
  • Stubs: load references/stubs.md.
  • Architecture note: load references/architecture-doc.md.

Default folder layout (omit folders you don’t need):

  • domain/, application/, ports/, infra/, api/

Load exactly one language profile:

Load patterns only when needed:

Generation procedure

  1. Ask for the target language/runtime if unknown (TypeScript/Node, Python, Go, etc.).
  2. Ask for the primary module boundary (feature name) and the IO needs (DB? HTTP? queue?). 2b. If codebase-memory-mcp is available and this scaffold lands inside an existing repo, check index_status first — index it (index_repository) if it isn't yet, then call get_architecture(aspects). The new module's folder layout and dependency direction must match the codebase's actual boundaries, not just the default layout below. No MCP, greenfield repo, or not worth indexing for a single scaffold → use the default layout as-is.

MCP names are bare, not callable as written. Prefix cbm_ under pi, mcp__codebase-memory-mcp__ under Claude Code. Under pi, trace_path, query_graph, detect_changes, get_architecture and get_graph_schema need one cbm_search_tools call first. 3. Load only the files required by the context (language + patterns). 4. Produce a file tree including archi-<feature>.md. 5. Generate strictly-typed stubs that compile and remain obviously empty.

Skills enregistrées