CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-arch-system-design

Agent skill for arch-system-design - invoke with $agent-arch-system-design

45

1.00x
Quality

19%

Does it follow best practices?

Impact

88%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-arch-system-design/SKILL.md

The canonical home for this skill is agent-arch-system-design in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

17%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 body is dominated by an inlined agent-configuration YAML block instead of instruction, and the actual markdown is high-level advice with no executable guidance, no sequenced workflow, and no progressive disclosure to supporting files.

Suggestions

Move the YAML configuration blob into a separate reference file and keep SKILL.md as a concise instruction overview that links to it.

Replace abstract directives with concrete, copy-paste-ready examples (e.g. an ADR template, a C4 model snippet, a technology-evaluation matrix format).

Add an explicit numbered workflow with validation checkpoints (e.g. gather quality attributes -> draft options -> document ADR -> review trade-offs), since the skill drives major decisions requiring confirmation.

DimensionReasoningScore

Conciseness

The body inlines a ~120-line YAML configuration blob (triggers, capabilities, constraints, hooks) that is metadata rather than instruction, plus best-practice lines stating concepts Claude already knows, matching 'Noticeably verbose; several unnecessary explanations or padded sections'.

2 / 5

Actionability

The markdown gives only abstract directives ('Design scalable architectures', 'Document ADRs', 'Consider non-functional requirements') with no concrete code, commands, or executable examples, matching 'Entirely vague or abstract; only describes rather than instructs'.

1 / 5

Workflow Clarity

Responsibilities and deliverables imply a rough order but there is no explicit sequenced workflow and no validation/confirmation checkpoints despite the skill driving major architectural decisions, matching 'Rough sequence present but many gaps; validation absent'.

2 / 5

Progressive Disclosure

A large configuration blob that clearly belongs in a separate file is inlined into the body, and there are no external references at all, matching 'Minimal structure; content that clearly belongs in separate files is inlined'.

2 / 5

Total

7

/

20

Passed

Description

21%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 essentially a label plus invocation syntax rather than a capability statement: it names the domain but lists no concrete actions, omits any 'use when' trigger guidance, and uses an invocation command instead of natural keywords.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Designs scalable system architectures, documents ADRs, and produces C4/UML diagrams'.

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'system design', 'architecture', 'scalability', or 'microservices'.

Replace the '$agent-arch-system-design' invocation hint with user-facing keywords and synonyms so it triggers on natural language.

DimensionReasoningScore

Specificity

The description only names the domain ('arch-system-design') plus an invocation hint ('$agent-arch-system-design') with no concrete capabilities listed, matching the anchor 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

It offers only a vague 'what' (an agent skill for system design) and no 'when to use it' clause at all, matching 'Has a vague what and no when'; the missing Use-when clause also caps completeness per the guidelines.

2 / 5

Trigger Term Quality

No natural user keywords appear; '$agent-arch-system-design' is an invocation command rather than phrases a user would naturally say, matching 'No natural keywords; only technical jargon or entirely generic language'.

1 / 5

Distinctiveness Conflict Risk

The system-architecture niche is somewhat specific and unlikely to collide with unrelated skills, but the description is too generic in form to fully distinguish it from related design/planning skills, matching 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

8

/

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.