bmad-architecture

Work out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document. Creates, updates, or validates one; works from a spec, a raw idea, or an existing codebase. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design"

Quality

81%

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

78%Weight 40%Scale 1-5

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

A dense, well-architected instruction skill with concrete commands, a clear sequenced workflow, and clean progressive disclosure into real bundle files. The main lever is bringing a few inline validation checkpoints forward from the referenced gate file.

Suggestions

Inline the key validate→fix→proceed checkpoint from reviewer-gate.md into the Finalize sequence so the feedback loop is explicit without loading the reference.

Soften a few jargon-dense sentences (e.g. the Overview invariant list) so the load-bearing rules read as cleanly as the rest.

Show one resolved example of a memlog.py / resolve_customization.py invocation (with placeholders filled) to lift actionability from mostly-executable to copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean, editorial prose that assumes Claude's competence and avoids explaining known concepts ('Record decisions, not rationale'); a few densely jargon-packed sentences could be tightened, keeping it just short of a 5.	4 / 5
Actionability	Concrete executable commands (`uv run .../memlog.py init --workspace ... --field scope="…"`) and a precise AD structure (Binds/Prevents/Rule) give mostly executable guidance; reliance on unresolved template variables leaves minor gaps.	4 / 5
Workflow Clarity	The Finalize section is a clear 8-step sequence with validation (Reviewer Gate, lint_spine.py) and a triage feedback loop; the crispest validate→fix→proceed checkpoints live in referenced files rather than inline, so it is not a 5.	4 / 5
Progressive Disclosure	SKILL.md is an overview that clearly signals one-level-deep references (references/headless.md, references/reviewer-gate.md, scripts/lint_spine.py, assets/spine-template.md), all of which are real bundle files; content is appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

83%Weight 40%Scale 1-5

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, well-structured description that clearly states capability and gives explicit natural-language triggers in third person. Minor gains are possible from a few additional trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Creates, updates, or validates one' and 'works from a spec, a raw idea, or an existing codebase' — with only minor coverage gaps; not quite the comprehensive multi-action list of a 5.	4 / 5
Completeness	Explicitly answers both what ('Work out and record the architecture decisions... in a short architecture document') and when with concrete trigger phrases via the 'Use when the user says...' clause.	5 / 5
Trigger Term Quality	Natural trigger phrases ('create the architecture', 'create technical architecture', 'architecture spine', 'create a solution design') give good synonym coverage; a few natural variants (e.g. 'design the architecture', 'system design') are missing, stopping short of a 5.	4 / 5
Distinctiveness Conflict Risk	The 'architecture spine' / 'solution design' niche is mostly distinct with clear triggers, but there is minor overlap risk with closely related spec/design skills.	4 / 5
	Total	17 / 20 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: skills/bmad-architecture/SKILL.md
Commit: 0a00053

Reviewed: 3 days 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.