architecture

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is architecture in sickn33/antigravity-awesome-skills

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 body is token-efficient and well-structured for navigation in intent, but it is materially undermined by referencing five bundle files that do not exist and by offering only abstract checkpoints instead of concrete, executable architecture guidance.

Suggestions

Provide the referenced bundle files (context-discovery.md, trade-off-analysis.md, pattern-selection.md, examples.md, patterns-reference.md) or inline the essential ADR template and trade-off framework so the skill is self-contained.

Replace the abstract validation checklist with a concrete, sequenced decision workflow with explicit validation checkpoints (e.g., confirm constraints before trade-off analysis, review ADR against requirements).

Add at least one concrete artifact — an ADR template or a worked trade-off example — so the skill instructs rather than describes.

Dimension	Reasoning	Score
Conciseness	The body is lean — a content map, related-skills table, core principle, and checklist — and does not explain concepts Claude already knows; nearly every token earns its place (the epigraph is the only borderline padding).	3 / 3
Actionability	The body describes rather than instructs: the validation checklist is abstract ("Requirements clearly understood", "Each decision has trade-off analysis") and the concrete guidance (ADR templates, decision trees, trade-off framework) is deferred to referenced files that do not exist.	1 / 3
Workflow Clarity	A validation checklist provides completion checkpoints, but there is no explicitly sequenced decision workflow (discover -> trade-off -> select -> ADR); the sequence is only implied by the content-map table ordering, and no error-feedback loops are present.	2 / 3
Progressive Disclosure	The content map is well-signaled (file, description, when-to-read) and one level deep, but the referenced files (context-discovery.md, trade-off-analysis.md, pattern-selection.md, examples.md, patterns-reference.md) are not present, so the navigation is broken rather than easy to follow.	2 / 3
	Total	8 / 12 Passed

Description

85%

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 concise, third-person description that clearly states both capability and trigger, with a well-defined niche. Its main weakness is narrow trigger-term coverage that omits common phrasings a user would naturally say.

Suggestions

Broaden the "Use when" clause to include natural variations users actually say, e.g. "evaluating trade-offs", "writing ADRs", or "designing a system".

Consider whether "system design" overlaps too broadly with general design skills and tighten the trigger toward decision/trade-off/ADR intent.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Requirements analysis, trade-off evaluation, ADR documentation" — matching the anchor for several specific concrete actions rather than a single named domain.	3 / 3
Completeness	Clearly answers what ("Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation") and when (explicit "Use when..." clause), matching the anchor for both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	The "Use when making architecture decisions or analyzing system design" trigger offers only two natural phrases, omitting common variations a user might say (e.g., "evaluating trade-offs", "writing an ADR", "designing a system").	2 / 3
Distinctiveness Conflict Risk	The architecture-decision/ADR niche is distinct and the description even scopes out implementation, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/architecture/SKILL.md
Commit: 04514f0

Reviewed: about 12 hours 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.