advogado-criminal

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

Quality

68%

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

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable and domain-accurate with concrete citations and a clear 10-step workflow, but it is a monolithic, overly long document that lacks validation checkpoints and externalizes nothing into reference files. Splitting reference tables out and adding verification steps would materially improve it.

Suggestions

Move the large reference tables (legislation map 2006-2025, crime/pena tables, dosimetria, prescription, execution benefits) into separate files under references/ and link to them from SKILL.md, keeping the body a concise overview.

Add explicit validation checkpoints to the 10-step workflow (e.g., verify cited statute numbers and confirm required user inputs before producing the verdict).

Trim inline exhaustive enumerations where a pointer to a reference file would preserve clarity at a fraction of the token cost.

Dimension	Reasoning	Score
Conciseness	The body is well-structured and not padded with concepts Claude already knows, but at ~935 lines it is excessively verbose, packing exhaustive legal reference tables inline; much of it could be trimmed or moved out, so it does not meet the lean 'every token earns its place' level 3 anchor.	2 / 3
Actionability	It gives concrete, specific guidance — exact statute and article numbers (Art. 121-A, Lei 14.994/2024), defined penalties, an explicit 10-step workflow, and a fill-in verdict template — providing actionable, copy-ready instructions appropriate to an instruction-only legal skill.	3 / 3
Workflow Clarity	The 10-step analysis workflow is clearly sequenced, but it lacks explicit validation checkpoints or feedback loops (validate -> fix -> retry); given the high-stakes legal context, checkpoints remain implicit, matching the level 2 anchor of steps present but validation gaps.	2 / 3
Progressive Disclosure	No bundle files exist and the entire reference corpus (legislation maps, crime/pena tables, dosimetria, execution benefits) lives inline in one monolithic ~935-line SKILL.md with no signaled references or navigation to deeper files, so content that should be split stays inline at level 2.	2 / 3
	Total	9 / 12 Passed

Description

72%Weight 40%Scale 1-3

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 is domain-specific and trigger-rich, making it distinct and easy to match, but it omits an explicit 'Use when' clause and frames capabilities as subject expertise rather than concrete actions. Adding a trigger clause would lift completeness and specificity.

Suggestions

Add an explicit 'Use when...' / 'Use quando o usuario menciona...' clause so the 'when' trigger is stated, not implied.

Reframe capabilities as concrete actions (e.g., 'Analisa casos criminais, calcula dosimetria, orienta sobre medidas protetivas') rather than only listing subject areas.

Include common user variations such as 'Lei Maria da Penha' and 'denuncia' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ('Advogado criminalista') and enumerates specific legal subjects ('Maria da Penha, violencia domestica, feminicidio...medidas protetivas, inquerito policial e acao penal'), but it lists topics via 'especializado em' rather than naming discrete actions a skill performs, so it falls short of the multi-action level 3 anchor.	2 / 3
Completeness	It answers 'what' clearly (specialist in those criminal-law domains) but lacks any 'Use when...' / 'quando usar' clause, so 'when' is only implied; per the rubric guideline a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	It surfaces natural phrases a Portuguese-speaking user would actually say ('maria da penha', 'violencia domestica', 'feminicidio', 'direito penal', 'medidas protetivas'), giving good coverage of likely trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply defined (Brazilian criminal law, Maria da Penha, feminicidio) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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
skill_md_line_count	SKILL.md is long (956 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/advogado-criminal/SKILL.md
Commit: 07da495

Reviewed: 5 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.