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.
90
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides an extensive list of natural trigger phrases, clearly defines both the input (product concept) and output (architecture-vision.md), and specifies the concrete contents of the deliverable. The description is well-scoped to greenfield architecture decisions, making it distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: takes a product concept as input, produces an architecture-vision.md document, captures technology stack, system design, protocols, packaging strategy, and known risks. | 3 / 3 |
Completeness | Clearly answers both 'what' (produces an architecture-vision.md document capturing technology stack, system design, protocols, packaging strategy, and known risks) and 'when' (extensive list of trigger phrases plus the general condition of wanting to explore technology options for a greenfield project). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including variations like 'arch vision', 'architecture vision', 'tech stack', 'what technology should I use', 'how should I build this', 'design the system', 'choose technologies', and 'pick a tech stack'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to greenfield project architecture vision with a specific output artifact (architecture-vision.md). The combination of architecture definition, tech stack selection, and greenfield context creates a distinct niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted conversational workflow skill with excellent actionability and workflow clarity. The step-by-step process is thoroughly defined with decision tables, validation checkpoints, error handling, and clear agent delegation patterns. The main weaknesses are moderate verbosity (the agent invocation table is duplicated, and some sections could be tightened) and the inability to verify bundle file references, though the progressive disclosure structure is reasonable for a complex multi-step skill.
Suggestions
Remove the duplicated agent invocation table — it appears both in Step 3 and as a standalone 'Agent Invocation Guide' section. Keep only one.
Tighten the Step 2 section by reducing the explanatory framing text (e.g., 'Frame it as...' and 'Present the findings to the user as a conversation starter') which instructs Claude on conversational style it already handles well.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200+ lines) with some redundancy — the agent invocation table appears twice (once in Step 3 and once as a standalone section), and some explanatory text could be tightened. However, most content is genuinely instructive and not explaining things Claude already knows. The structured blocks for user expertise context add bulk but serve a purpose. | 2 / 3 |
Actionability | The skill provides highly concrete, step-by-step guidance with specific file paths, exact agent invocation patterns, structured context blocks to include, decision tables for situational responses, and clear output artifacts. Every step tells Claude exactly what to do, read, invoke, or write. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0-5) with explicit validation checkpoints: user confirmation after requirements extraction, readiness check with pillar alignment assessment before document writing, and coverage tracking for architectural layers. Error handling covers cancellation, failures, and edge cases with specific recovery actions. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (ensure-config.md, technology-evaluation-guide.md, architecture-vision-template.md) with clear paths, but no bundle files were provided to verify these exist. The main SKILL.md itself is quite long and some content (like the detailed agent invocation guide duplicated as a table) could potentially be split out. The inline content is well-structured with headers but borders on monolithic. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
1fe948f
Table of Contents
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.