CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pattern-conformity

Extrai e aplica convencoes existentes do repositorio. 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".

Quality

88%

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 well-engineered process skill: concrete sampling commands, a disciplined extraction checklist, a complete output template, and a conformity gate with a post-write validation feedback loop. The only meaningful improvement is structural — moving the patterns.md template and extraction checklists into reference files would tighten the main body's token cost.

DimensionReasoningScore

Conciseness

The body is checklist-driven with essentially no explanation of concepts Claude already knows — P1-P8 are extraction prompts, not tutorials. It is not a 5 because of minor trimmable weight: the ~80-line inline patterns.md template, the opening principle blockquote, and slight redundancy between the Fase 4 gate and the post-write checkpoint. It is above 3 because padding is minor and every section carries operational content.

4 / 5

Actionability

Fully executable guidance throughout: copy-paste-ready find/grep commands per sample category, concrete reading instructions with line-count ranges ("Ler 2-3 arquivos de tamanho medio (200-400 linhas)"), a complete fill-in template for memory/patterns.md, and a concrete deviation-comment code example. This matches the top anchor for copy-paste-ready commands covering common cases.

5 / 5

Workflow Clarity

Clear Fase 0-4 sequence with branching (cache hit skips to Fase 3, --update bypasses cache), explicit validation steps (last_extracted freshness check, high/medium/low confidence criteria), and a genuine feedback loop: the post-write checkpoint re-reads generated code against the P1-P8 checklist and sends unjustified deviations back for correction. This matches the anchor with explicit validation, error-recovery loops, and checklists.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), so there are no nested or dead references, and the body is cleanly sectioned (Quando Usar / Quando NAO Usar / Protocolo / Handoffs / Anti-padroes). It is not a 5 because the large inline patterns.md template and the P1-P8 extraction checklists (~150 lines of reference material) could plausibly live in one-level-deep reference files to slim the main skill; it is above 3 because what remains inline is well-signaled and navigable.

4 / 5

Total

18

/

20

Passed

Description

86%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: concise third-person 'what' statement paired with an extensive, explicit list of natural trigger phrases covering many synonyms. The only real gap is that the capability statement stays at a high level (extract + apply) rather than naming the concrete pattern categories the skill actually handles.

DimensionReasoningScore

Specificity

"Extrai e aplica convencoes existentes do repositorio" names the domain and exactly two actions (extract, apply), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because the description never enumerates the several specific actions the skill performs (naming, error-handling, testing, structure pattern extraction).

3 / 5

Completeness

It explicitly answers both 'what' ("Extrai e aplica convencoes existentes do repositorio") and 'when' ("Trigger em:" followed by concrete trigger phrases), matching the top anchor. A score of 4 would require the 'when' to be less explicit, which is not the case here.

5 / 5

Trigger Term Quality

The "Trigger em:" clause lists ~20 natural user phrases with rich synonym coverage ("padrao do projeto", "convencao do projeto", "code style do projeto", "patterns do codebase", "padrao de tratamento de erro", "mesma estrutura do projeto"), matching the comprehensive-synonyms anchor. It is not a 4 because virtually no natural variation of the request is missing.

5 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche (extracting and enforcing observed codebase conventions) with mostly distinct triggers, but broad phrases like "padrao de codigo" and "code style do projeto" carry minor overlap risk with formatting/lint-style skills. It does not reach 5 because the conflict risk is more than minimal; it is above 3 because the core triggers are unmistakably about this skill.

4 / 5

Total

17

/

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.