agent-architecture

Agent skill for architecture - invoke with $agent-architecture

1.49x

Quality

—

Does it follow best practices?

Impact

88%

1.49x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

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

The skill body is a well-organized but oversized reference: it packages a complete example architecture across many formats without guiding Claude through a producing workflow or splitting detail into separate files. It is competent as a template library but weak as instruction.

Suggestions

Slim the inline scaffolding (example SQL schema, OpenAPI, k8s manifests) to the minimal patterns needed and move extended examples into referenced files.

Turn the Architecture phase list into a concrete sequenced workflow with explicit validation checkpoints (e.g. review interfaces against requirements before selecting tech).

Add a brief 'When invoked, produce these deliverables' instruction section so the templates serve an actionable process rather than standing alone.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient structured reference content (templates and manifests), but the ~450 lines of illustrative SQL, OpenAPI, and k8s scaffolding pad the skill with content Claude could generate on demand, so it is not fully lean.	2 / 3
Actionability	It supplies concrete, copy-paste-ready templates (mermaid graph, component YAML, schema SQL, OpenAPI, k8s manifests), but these are illustrative reference architectures rather than executable guidance that produces the skill's deliverable, leaving it one step short of fully actionable.	2 / 3
Workflow Clarity	The Architecture phase is laid out as a 5-step sequence, but there are no explicit validation checkpoints or feedback loops for the multi-step design process, which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Content is organized into clear sections but everything (high-level, component, data, API, infra, security, scalability) sits inline in one ~450-line monolithic file with no bundle references, so content that should be split is inline.	2 / 3
	Total	8 / 12 Passed

Description

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

The description is essentially a placeholder: it names a broad domain and tells the user how to invoke it, but says nothing concrete about what the skill does or when to use it. It reads as a stub rather than a meaningful skill description.

Suggestions

Replace the generic statement with concrete capabilities, e.g. 'Designs system architectures: defines components and interfaces, selects technology stacks, and plans scalability and deployment.'

Add an explicit 'Use when...' trigger clause naming natural user phrases, e.g. 'Use when designing a system architecture, choosing a technology stack, or planning service scalability.'

Drop the invocation hint ('$agent-architecture') from the description — invocation is handled by the skill name, not the description.

Dimension	Reasoning	Score
Specificity	The description names only the domain ('architecture') and an invocation hint ('invoke with $agent-architecture') rather than any concrete capability or action, matching the vague/abstract anchor.	1 / 3
Completeness	'what' is weak (a generic 'skill for architecture') and 'when to use' is entirely absent with no 'Use when...' clause, so it fails on both halves; the missing trigger caps it well below 2.	1 / 3
Trigger Term Quality	It offers only a slash-command trigger ('$agent-architecture') and the generic word 'architecture' — no natural keywords a user would say, so it sits at the jargon/generic anchor rather than level 2.	1 / 3
Distinctiveness Conflict Risk	With only the generic term 'architecture' and no distinguishing triggers, it would readily conflict with other architecture-related skills.	1 / 3
	Total	4 / 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: ruvnet/claude-flow
Commit: 8ae8752

Reviewed: 2 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.