bmad-architecture

Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality instruction skill: lean and fluff-free prose, concrete executable commands and a precise decision-logging structure, clearly sequenced workflows with explicit validation and feedback loops, and a well-structured progressive-disclosure layout pointing to real, one-level-deep bundle files.

Dimension	Reasoning	Score
Conciseness	The body is dense, information-rich prose with no fluff and no explanation of concepts Claude already knows; every sentence carries load-bearing guidance for a multi-intent skill, matching the score-3 anchor where every token earns its place.	3 / 3
Actionability	It provides concrete, copy-paste-ready commands ('uv run {project-root}/_bmad/scripts/memlog.py init --workspace … --field scope="…"'), named file paths, and a precise decision structure (AD-n with Binds/Prevents/Rule), matching the score-3 anchor for fully executable guidance.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (Finalize: 8 numbered steps; Activation: 6) with explicit validation checkpoints — the Reviewer Gate's 'deterministic lint_spine.py pass', reconcile, and triage steps form validate→fix→retry feedback loops, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The body is a terse overview that offloads detail to well-signaled, one-level-deep references (references/headless.md, references/reviewer-gate.md, assets/spine-template.md, scripts/lint_spine.py), all verified to exist with no 2+-level knowledge nesting, matching the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concise description that states the concrete capability, mechanism, and output, paired with an explicit 'Use when' clause covering four natural trigger phrases. It cleanly answers what, when, and how it differs from neighboring skills.

Dimension	Reasoning	Score
Specificity	The description names concrete actions — 'Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs' — specifying both the mechanism (invariant spine) and the output (projected into needed format), matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	It explicitly answers both what ('Produce the architecture: a lean spine of invariants…') and when ('Use when the user says…'), with an explicit 'Use when' clause and enumerated triggers, matching the score-3 anchor.	3 / 3
Trigger Term Quality	It lists four natural phrasings a user would actually say — 'create the architecture', 'create technical architecture', 'architecture spine', 'create a solution design' — giving good coverage rather than the partial set that would cap it at 2.	3 / 3
Distinctiveness Conflict Risk	The architecture-design niche is clearly bounded by distinct triggers ('architecture spine', 'create technical architecture', 'create a solution design') and is unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: bmad-code-org/BMAD-METHOD
Path: src/bmm-skills/3-solutioning/bmad-architecture/SKILL.md
Commit: bb45db4

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.