architecture-deepener

Encontra oportunidades de "deepening" no codebase — refactors que transformam modulos shallow (interface complexa, implementacao simples) em deep (interface simples, implementacao rica). Foco em testabilidade e AI-navigability. Use quando usuario quiser melhorar arquitetura, encontrar oportunidades de refactor, consolidar modulos acoplados, ou preparar codebase para trabalho de agente. Trigger em: "deepening", "deep module", "shallow module", "refactor architecture", "improve architecture", "consolidate modules", "agent-friendly codebase", "AI-navigable", "module depth".

Quality

84%

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

Quality

Content

77%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 well-structured and highly actionable, with a clear phased workflow and explicit validation feedback loop. It loses points for verbosity in the 'Lenses' conceptual section and for inlining glossary/lens material that would benefit from being split into a real reference file.

Suggestions

Move the 'Lentes Adicionais' conceptual section (cohesion/coupling, REST/RPC/async, HATEOAS, layers/tiers) into a separate reference file, since it re-explains architecture concepts Claude already knows — keep only the mapping to this skill's vocabulary inline.

Extract the Glossario into its own reference file (mirroring the upstream LANGUAGE.md) so SKILL.md stays a lean overview; reference it one level deep with a clear link.

Tighten Fase 1's 'explore organicamente' guidance with a short explicit checklist of what to record per friction point, reducing reliance on 'feel friction'.

Dimension	Reasoning	Score
Conciseness	The operational core (Processo, Heurísticas, Output, Anti-Padrões) is efficient, but the ~60-line 'Lentes Adicionais' section re-explains cohesion/coupling, SRP, REST-vs-RPC-vs-async, HATEOAS, and layers-vs-tiers — concepts Claude already knows — which is noticeable padding that could be tightened.	3 / 5
Actionability	Highly actionable for an instruction-only skill: a copy-paste output markdown template, a concrete fitness-functions YAML schema with a worked example, exact output paths ('_architecture_review/YYYY-MM-DD-candidates.md', '.harness/fitness-functions.yml'), and a symptom→action heuristics table covering the common cases.	5 / 5
Workflow Clarity	Three phases are clearly sequenced (Explore → Apresentar candidatos → Grilling Loop) with an explicit validation checkpoint and feedback loop ('rodar a suite de testes... se algum teste que deveria sobreviver quebrou... Corrigir a interface... e rodar de novo') plus an 'Evidencia de Conclusao' checklist and a sequenced Handoff.	5 / 5
Progressive Disclosure	Section headers are clear, but no bundle files exist (references/, scripts/, assets/ absent) and the 310-line body inlines content that the upstream skill keeps in a separate LANGUAGE.md (glossary, lenses); the 'Material Adicional' pointers target external/non-existent docs ('a criar') rather than real one-level-deep reference files.	3 / 5
	Total	16 / 20 Passed

Description

91%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.

A strong description: third-person voice, explicit what+when, and a dedicated trigger-term block with good synonym coverage. Its only weak spot is mild overlap with general refactor skills on the broadest triggers.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Encontra oportunidades de deepening', 'transforma modulos shallow em deep', 'consolidar modulos acoplados', 'preparar codebase para trabalho de agente' — but they lean on the skill's own domain vocabulary rather than fully operational verbs, leaving minor coverage gaps versus the comprehensive anchor.	4 / 5
Completeness	Explicitly answers both 'what' (find deepening opportunities, transform shallow→deep, consolidate coupled modules, prep for agent work) and 'when' ('Use quando usuario quiser melhorar arquitetura, encontrar oportunidades de refactor, consolidar modulos acoplados...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The explicit 'Trigger em:' block gives nine natural phrases with synonyms and variations — 'deepening', 'deep module', 'shallow module', 'refactor architecture', 'improve architecture', 'consolidate modules', 'agent-friendly codebase', 'AI-navigable', 'module depth' — comprehensive coverage of what a user would say.	5 / 5
Distinctiveness Conflict Risk	The deepening/depth vocabulary ('deep module', 'shallow module', 'module depth') carves a clear niche, but 'refactor architecture' and 'improve architecture' overlap with a generic refactor skill, giving minor conflict risk rather than the minimal risk of the top anchor.	4 / 5
	Total	18 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/38-architecture-deepener/SKILL.md
Commit: 74aa7c1

Reviewed: 3 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.