CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-review

Padrões e checklist para code review

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/workflow/code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 a well-organized, actionable checklist skill with a copy-paste report template and a clear severity model. Its main gap is the absence of an explicit review workflow with validation checkpoints, plus minor over-explanation in the best-practices section.

Suggestions

Add an explicit numbered workflow connecting the pieces, e.g.: 1. Obter o diff/PR; 2. Aplicar o checklist por categoria; 3. Confirmar cada issue contra o código (revalidar antes de reportar); 4. Categorizar por severidade; 5. Gerar o relatório no formato definido.

Include a short worked example of one filled-in issue entry in the report format so the template's placeholders (Problema/Solução) are unambiguous.

Trim or condense the DO/DON'T section, which mostly restates review etiquette Claude already knows.

DimensionReasoningScore

Conciseness

The body is a lean checklist with skill-specific thresholds ('Funções pequenas e focadas (< 50 linhas ideal)', 'Cobertura adequada (> 80% ideal)') plus a compact report template. Minor trimming is possible — the DO/DON'T section ('Foque no código, não na pessoa', 'Nitpicking excessivo') and generic items Claude already knows ('Sem SQL injection') — matching 'Efficient; minor instances of over-explanation that could be trimmed' rather than score 5's 'every token earns its place'.

4 / 5

Actionability

The checklist items are concrete and checkable, the severity levels map to actions ('Ação: Bloqueia merge'), and the report format is a copy-paste-ready markdown template with placeholders ([arquivo:linha]). It falls short of score 5 because there is no worked example of a filled-in issue entry and no commands for gathering the summary stats (files modified, +Y/-Z lines).

4 / 5

Workflow Clarity

The components of a review are present (when-to-use, checklist, severity model, report template with verdict), but the process that connects them is only implicit — no explicit ordering from examining the diff through checklist application to categorized reporting, and no validation checkpoints (e.g., confirm each issue against the actual code before reporting). This matches 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'; score 4 would require most checkpoints to be explicit.

3 / 5

Progressive Disclosure

With no bundle files, all content lives appropriately in a single well-sectioned SKILL.md (~125 lines) with clear headers (Quando Usar, Checklist, Formato de Report, Severidade, Boas Práticas) and no nested or buried references, fitting 'Good structure; most content is appropriately placed'. Score 5 is reserved for a clear overview with well-signaled one-level-deep references or the sub-50-line simple-skill exception, neither of which applies.

4 / 5

Total

15

/

20

Passed

Description

45%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.

The description names a clear domain and deliverable type but reads as a content label rather than a capability statement: no concrete actions, no 'when to use' guidance, and only one natural trigger phrase. It would benefit from enumerating what the skill does and when to invoke it.

Suggestions

State concrete capabilities in the description, e.g. 'Revisa código e pull requests contra um checklist de funcionalidade, qualidade, segurança, performance, erros e testes, e gera um relatório categorizado por severidade com veredicto de merge.'

Add an explicit trigger clause: 'Use when a pull request needs review, new code was implemented, or the user asks for code review, refactoring review, or análise de código.'

Include natural trigger variations such as 'pull request', 'PR', 'code review', 'refatoração' so the skill is discoverable and distinct from adjacent skills like security review.

DimensionReasoningScore

Specificity

The description 'Padrões e checklist para code review' names the domain and the artifact type (patterns and checklist) but lists no concrete actions (no 'review pull requests', 'identify security issues', or similar), matching the anchor 'Names the domain but actions are minimal or generic'. It is above score 1 because it is not entirely vague, but below score 3 because no specific capabilities are stated.

2 / 5

Completeness

A discernible 'what' is present (provides patterns and a checklist for code review), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines. It is not score 2 because the 'what' names the domain and deliverables rather than being extremely vague.

3 / 5

Trigger Term Quality

'code review' is a highly natural phrase users would say, but common variations and synonyms are missing ('pull request', 'PR', 'refatoração', 'feedback de código'), matching 'Some relevant keywords but missing common variations or synonyms'. The separate triggers field ([review, qualidade, código, análise]) adds only broad terms, not the missing natural variations.

3 / 5

Distinctiveness Conflict Risk

'code review' carves out a specific niche, but the description provides no distinguishing triggers and could overlap with closely related skills (security review, refactoring, quality analysis), fitting 'Somewhat specific but could still overlap with similar skills'. Score 4 would require mostly-distinct triggers that this description lacks.

3 / 5

Total

11

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/cursor-multiagent-system

Path

skills/workflow/code-review/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.