advogado-criminal

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

Quality

53%

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 ./skills/advogado-criminal/SKILL.md

Quality

Content

51%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-structured, token-efficient overview that correctly delegates detail to a single verified reference file, exemplifying good progressive disclosure. Its weakness is that the body itself carries almost no actionable or sequenced procedural content—everything substantive lives in the referenced guide.

Suggestions

Add a brief inline quick-start or core procedure (2-4 concrete steps) so the skill is actionable without forcing a full guide read for common cases.

Include at least one explicit validation/checklist step in the body (e.g., 'confirm jurisdiction and whether the user is vitima or acusado before advising') rather than only referencing the guide's mandatory validation.

Condense the six repetitive 'When the user mentions...' bullets into a single trigger line to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no padded concept explanations, but the six near-identical 'When the user mentions X or related topics' bullets repeat a template that could be condensed into one line, leaving minor instances that could be trimmed.	4 / 5
Actionability	The body's only concrete instruction is to read the detailed guide; all substantive procedural guidance is deferred to the reference, so it provides 'minimal concrete guidance; high-level hints but missing the specific steps to execute'.	2 / 5
Workflow Clarity	No sequenced process or validation checkpoints appear in the body itself—only a pointer to the guide whose safety/validation requirements are 'mandatory', so the body offers a rough direction with steps poorly defined and no inline validation.	2 / 5
Progressive Disclosure	The body is a clear overview that signals a single one-level-deep reference (references/detailed-guide.md, verified to exist) with a markdown link, and content is appropriately split between SKILL.md and the guide, matching 'clear overview with well-signaled one-level-deep references'.	5 / 5
	Total	13 / 20 Passed

Description

56%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 clearly conveys a well-defined Brazilian criminal-law niche with strong natural trigger terms, but it lists expertise topics rather than concrete actions and omits an explicit 'Use when...' clause. It is distinct and on-domain yet would benefit from stating what the skill does and when to invoke it.

Suggestions

Add concrete actions the skill performs (e.g., 'avalia casos, redata medidas protetivas, orienta sobre inquérito e ação penal') instead of only listing subject areas.

Append an explicit trigger clause such as 'Use when the user mentions Maria da Penha, violencia domestica, feminicidio, or direito penal brasileiro.' to satisfy the 'when' half of completeness.

Include a few common synonyms (e.g., 'lei maria da penha', 'violencia contra a mulher', 'delegacia da mulher') to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Advogado criminalista especializado em') and lists expertise areas (Maria da Penha, violencia domestica, feminicidio, etc.), but these are subject nouns rather than concrete actions, so it only 'names the domain but actions are minimal or generic'.	2 / 5
Completeness	It clearly answers 'what' (a criminal lawyer specialized in these areas) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	It includes natural PT-BR terms a user would actually say ('Maria da Penha', 'violencia domestica', 'feminicidio', 'direito penal'), giving good keyword coverage, though a few common synonyms ('lei maria da penha', 'violencia contra a mulher', 'delegacia da mulher') are missing.	4 / 5
Distinctiveness Conflict Risk	The Maria da Penha / feminicidio niche is highly distinctive, but the broad terms 'direito penal' and 'crime' create minor overlap risk with a general criminal-law skill, fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/advogado-criminal/SKILL.md
Commit: b1aebac

Reviewed: ~19 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.