Menu
Technical design, architecture. Use when the user asks about architect.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | architect |
| description | Technical design, architecture. Use when the user asks about architect. |
| metadata | {"managed-by":"bmalph"} |
This wrapper requires local BMALPH assets under _bmad/, which this repository intentionally keeps out of git.
If _bmad/ is missing in a fresh clone or workspace, run make bmalph-setup first.
If BMALPH is already installed and you need to restore local files or reapply this repository's planning artifacts under specs/, rerun make bmalph-setup.
Read and follow the agent defined in _bmad/bmm/agents/architect.agent.yaml.
Systematically retrieve and address PR code review comments using make pr-comments. Use when handling code review feedback or addressing PR comments.
Codex entrypoint for post-implementation BMAD FR/NFR review gates. Use after a PR, feature, or bugfix has BMAD specs and must be checked against every functional requirement, non-functional requirement, expanded quality dimension, Wikipedia system quality attribute, generated positive/negative/ edge test case, automated test and CI coverage expectation, flaky-test risk, whole-codebase impact surface, manual-test expectation, GitHub review comments and requested-changes state, and CI check before completion.
Run a BMAD spec-driven post-implementation review gate. Use after implementing a GitHub PR, feature, bugfix, or task with BMAD specs to verify every FR/NFR, pinned NonFunctionals.com NFR category, expanded quality dimension, Wikipedia system quality attribute, positive/negative/edge test case, automated test and CI coverage expectation, flaky-test risk, whole-codebase impact surface, manual test expectation, QA best practice, GitHub review comments and requested-changes state, and CI check before completion.
Design LLM-powered modules with Clean Architecture boundaries, SOLID, DRY, KISS, and provider-agnostic ports/adapters. Use when adding prompt workflows, model/provider clients, tool orchestration, AI review automation, agent skills, or other LLM-backed capabilities.
advanced elicitation. Use when the user asks about advanced elicitation.
adversarial review. Use when the user asks about adversarial review.
