CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pattern-conformity

Extrai e codifica os padroes de coding do projeto existente (naming, estrutura de arquivos, error handling, testing style, import style, API design, async patterns) e usa esses padroes como restricao sobre novo codigo. Garante que o agente code "igual ao resto do projeto" em vez de inventar convencoes proprias. Produce um "code style map" salvo em memory/patterns.md que todas as skills de geracao de codigo devem consultar. Trigger em: "segue o padrao do projeto", "coda igual ao resto", "nao reinventa padrao", "detecta padroes do codebase", "code style do projeto", "padrao do projeto", "convencao do projeto", "coda consistente", "mesma convencao", "sem reinventar roda", "padrao de codigo", "patterns do codebase", "pattern enforcement", "conformidade de padrao", "convencoes de naming", "padrao de tratamento de erro", "mesma estrutura do projeto", "detecta as convencoes", "extrai padroes de coding", "como o projeto estrutura".

73

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A highly actionable, well-sequenced meta-skill: concrete sampling commands, a complete output template, and explicit validation checkpoints with feedback loops. The main improvement areas are token efficiency (the large inline template) and splitting template content into a reference file for better progressive disclosure.

Suggestions

Move the ~80-line memory/patterns.md template out of the body into a references/ file (e.g. references/patterns-template.md), keeping only the frontmatter fields and section names inline — this improves both conciseness and progressive disclosure.

Trim the Handoffs section to one line per downstream skill; the per-skill pattern-category detail (P2/P8, P7, P5) duplicates what the template already encodes.

Condense the Distincao de Skills Similares table to the one-sentence contrast that follows it ("Skill 18 diz... Esta skill diz..."), which already carries the differentiation on its own.

DimensionReasoningScore

Conciseness

The body is dense and efficient — checklists and commands with no explanation of concepts Claude already knows — but the ~80-line patterns.md template is inlined wholesale and the Handoffs/Anti-padroes sections carry some redundancy. This is "efficient with minor instances that could be trimmed" rather than the every-token-earns-its-place of anchor 5.

4 / 5

Actionability

Provides copy-paste-ready find commands per sample category, an explicit output template complete with frontmatter fields, a deviation-comment code example, and a concrete report format. Guidance is fully executable and covers the common cases, matching the anchor-5 example.

5 / 5

Workflow Clarity

Fase 0–4 are clearly sequenced with a cache-hit check, an explicit post-write validation checkpoint ("Checkpoint pós-escrita: reler o arquivo gerado contra a checklist P1-P8"), and a feedback loop ("desvio sem comentário de justificativa volta pra corrigir"). This matches the anchor with explicit validation steps and error-recovery loops.

5 / 5

Progressive Disclosure

Sections are well-organized and external references (GLOBAL.md, policies/*.md) are clearly signaled in a governance section, but no bundle files exist and the large patterns.md template — content that could live in a references/ file — is inlined. Good structure with minor organization gaps fits anchor 4; it is not the well-split, one-level-deep reference structure of anchor 5.

4 / 5

Total

18

/

20

Passed

Description

96%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: concrete third-person capability statement, a named output artifact, and an unusually thorough explicit trigger list with synonyms. The only weakness is mild overlap risk between a few broad trigger phrases and adjacent codebase-analysis skills.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — "Extrai e codifica os padroes de coding", "usa esses padroes como restricao sobre novo codigo", "Produce um 'code style map' salvo em memory/patterns.md" — with seven enumerated pattern categories (naming, error handling, testing style, API design, etc.). This matches the comprehensive-coverage anchor; score 4 would require coverage gaps that are not present.

5 / 5

Completeness

Explicitly answers both: what ("Extrai e codifica os padroes... Produce um 'code style map'") and when ("Trigger em:" followed by concrete trigger phrases). This is the anchor-5 pattern of capability sentence plus explicit use-when clause, not the merely-explicit-when of anchor 4.

5 / 5

Trigger Term Quality

"Trigger em:" lists ~21 natural phrases a user would actually say, including synonyms and variations ("padrao do projeto", "convencao do projeto", "coda consistente", "pattern enforcement", "mesma estrutura do projeto"). Coverage is comprehensive with synonyms; nothing significant is missing, so it exceeds the 4 anchor.

5 / 5

Distinctiveness Conflict Risk

The niche — encoding an existing project's concrete coding conventions as generation constraints with a distinct output artifact (memory/patterns.md) — is mostly distinct, but broad triggers like "padrao de codigo" and "patterns do codebase" carry minor overlap risk with repo-audit or style-guide skills. It is more distinct than anchor 3 but does not have the minimal conflict risk of anchor 5.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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/47-pattern-conformity/SKILL.md

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.