Name: arn-spark-arch-vision
Rating: 74.4 (1 reviews)
Author: AppsVortex

arn-spark-arch-vision

This skill should be used when the user says "arch vision", "architecture vision", "arn arch vision", "define the architecture", "tech stack", "what technology should I use", "design the system", "system architecture", "how should I build this", "technology choices", "choose technologies", "pick a tech stack", or wants to explore technology options and define the high-level architecture for a greenfield project. Takes a product concept as input and produces an architecture-vision.md document capturing the technology stack, system design, protocols, packaging strategy, and known risks.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-3

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

A well-structured conversational workflow with strong actionability, clear sequencing, validation checkpoints, and sound progressive disclosure. The main weakness is redundancy: the Agent Invocation Guide repeats Step 3's situation/action table and several deferral messages are stated twice.

Suggestions

Remove the standalone 'Agent Invocation Guide' table — it duplicates the situation/action table already embedded in Step 3; cross-reference Step 3 instead.

Consolidate the repeated deferral guidance (code-pattern and product/scope questions appear both in Step 3's table and again in the Agent Invocation Guide) into a single statement.

Trim a few of the longer quoted user-facing messages to their essential phrasing to reduce token weight while keeping the conversational framing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance, but the 'Agent Invocation Guide' table near-duplicates the situation/action table already in Step 3, and the deferral guidance for code-pattern and product questions is repeated in both places. Trimming these would tighten the body without losing clarity.	2 / 3
Actionability	Concrete and specific throughout: exact file paths to read and write, the named agent to invoke, the context blocks to pass, a situation→action table, and a named output template — copy-paste ready procedure even without code.	3 / 3
Workflow Clarity	Clear Step 0→5 sequence with explicit validation checkpoints ('Wait for user confirmation or corrections before proceeding', a readiness check before writing) and a dedicated Error Handling section covering cancellation, agent failure, missing WebSearch, write failure, and an existing-document replace/update loop.	3 / 3
Progressive Disclosure	The body is an overview that defers detail to one-level-deep, clearly signaled references — architecture-vision-template.md (loaded at write time) and technology-evaluation-guide.md (loaded lazily) — both present in ./references; the two ensure-config references belong to another skill.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 description with explicit trigger guidance, concrete named outputs, and a clearly bounded niche. It uses third-person voice and avoids vague fluff. The only minor weakness is verbosity from listing many near-synonymous trigger terms, but the description rubric does not penalize this.

Dimension	Reasoning	Score
Specificity	Lists concrete deliverables — 'produces an architecture-vision.md document capturing the technology stack, system design, protocols, packaging strategy, and known risks' — naming multiple specific outputs rather than vague actions.	3 / 3
Completeness	Explicitly answers both what (produces an architecture-vision.md document with named sections) and when ('This skill should be used when the user says ... or wants to explore technology options and define the high-level architecture for a greenfield project').	3 / 3
Trigger Term Quality	Covers many natural phrases a user would actually say ('tech stack', 'design the system', 'how should I build this', 'pick a tech stack', 'define the architecture') plus niche variants like 'arn arch vision'.	3 / 3
Distinctiveness Conflict Risk	The greenfield-architecture-vision niche and the unique 'arn arch vision' trigger make it clearly distinguishable from sibling skills and unlikely to fire for the wrong one.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-spark/skills/arn-spark-arch-vision/SKILL.md
Commit: 7f87870

Reviewed: 14 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.