CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-architecture

Agent skill for architecture - invoke with $agent-architecture

57

1.49x
Quality

37%

Does it follow best practices?

Impact

88%

1.49x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-architecture/SKILL.md

The canonical home for this skill is agent-architecture in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

46%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.

The content is a large worked example of an architecture (auth service) rather than lean guidance for performing the Architecture phase, packing concrete templates but at high token cost and with no file-based disclosure. Workflow sequencing is present but lacks validation checkpoints.

Suggestions

Slim the body to the essential phase workflow and decision criteria; move the full SQL DDL, OpenAPI spec, and Kubernetes manifests into reference files under ./references/ and link to them.

Add explicit validation checkpoints to the architecture workflow (e.g. "verify interfaces cover all spec requirements before selecting technologies") with a fix-and-retry loop.

Replace the single auth-service example with parameterized guidance so the architecture generalizes rather than baking in one technology stack (NestJS/PostgreSQL/Redis).

DimensionReasoningScore

Conciseness

The ~470-line body inlines full SQL DDL, an OpenAPI spec, Kubernetes manifests, and a mermaid diagram that largely restate artifacts Claude can already produce, making it noticeably verbose with several padded reference sections.

2 / 5

Actionability

It provides concrete, copy-pasteable templates (mermaid graph, component YAML, SQL schemas, OpenAPI, K8s Deployment/Service) that cover common architecture cases, with only minor gaps in how to apply them.

4 / 5

Workflow Clarity

The SPARC Architecture Phase lists five sequenced steps, but there are no validation checkpoints or feedback loops and the transition from phase steps to the example artifacts is left implicit.

3 / 5

Progressive Disclosure

No bundle files exist and the body is a monolithic ~470-line document with reference-grade material (full OpenAPI/K8s/SQL specs) inlined that clearly belongs in separate files, despite having section headers.

2 / 5

Total

11

/

20

Passed

Description

28%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.

The description is thin and meta-referential, stating only that an agent skill exists for architecture and how to invoke it, without naming concrete capabilities or trigger conditions. It fails to answer what the skill does or when to use it.

Suggestions

Replace the description with concrete actions the skill performs, e.g. "Designs system architectures, defines component boundaries and interfaces, and selects technology stacks".

Add an explicit trigger clause such as "Use when the user needs a system design, component architecture, or scalability plan".

Drop the "$agent-architecture" invocation syntax from the description; surface natural terms like "system design", "component architecture", and "scalability planning" that users would actually say.

DimensionReasoningScore

Specificity

The phrase "Agent skill for architecture" names the domain but describes zero concrete actions, fitting the "names the domain but actions are minimal or generic" anchor.

2 / 5

Completeness

It gives a vague "what" ("Agent skill for architecture") and no "when"/"Use when..." clause at all, matching the "vague what and no when" anchor.

2 / 5

Trigger Term Quality

It offers only the generic keyword "architecture" plus the technical invocation token "$agent-architecture", missing the natural phrases (e.g. "system design", "component design") a user would actually say.

2 / 5

Distinctiveness Conflict Risk

"architecture" is a recognizable niche but broad enough to overlap with other architecture-related skills; the invocation token helps somewhat but does not fully isolate it.

3 / 5

Total

9

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
Reviewed

Table of Contents

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.