advogado-criminal

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

Quality

55%

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

53%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 clean, well-organized router: concise sections, clear use/anti-use gating, and a properly signaled one-level-deep reference to a real detailed guide. Its weakness is that it is purely a pointer — no procedure summary, examples, or validation steps appear in SKILL.md itself, so the model must load the full 946-line guide even for focused questions.

Suggestions

Add a brief quick-start or core-procedure summary (3-5 steps with the key validation points) inline so simple questions don't require loading the entire guide.

Replace the six repetitive "...or related topics" bullets with a single compact trigger list to save tokens.

List the detailed guide's main sections (with anchor links) so "load the relevant sections" becomes actionable selective loading.

Dimension	Reasoning	Score
Conciseness	The body is lean overall, but the six "When the user mentions X or related topics" bullets are near-duplicates that could collapse into one line. This matches anchor 4 (efficient, minor instances that could be trimmed); not 5 because the repetitive bullet list is avoidable padding.	4 / 5
Actionability	"Read [the detailed guide](references/detailed-guide.md) before executing this skill" is concrete navigation, but the body itself contains no domain-specific steps, commands, examples, or decision guidance — everything actionable is deferred to the referenced file. This matches anchor 2 (high-level hints, missing specific steps); not 3 because no partially-complete executable guidance appears in the body.	2 / 5
Workflow Clarity	A delegation sequence is present ("Read the detailed guide before executing this skill... Treat its safety, prerequisites, and validation requirements as mandatory") but the actual procedure and validation checkpoints are implicit, living entirely in the off-page guide. This matches anchor 3 (sequence present, checkpoints missing/implicit); not 4 because no concrete checkpoint is specified in the body.	3 / 5
Progressive Disclosure	The bundle check confirms a real, one-level-deep references/detailed-guide.md (946 lines, no nested references) that is clearly signaled with a link and loading guidance ("For focused work, load the relevant sections; for end-to-end work, read the guide completely"). This matches anchor 4 (good structure, minor gaps); not 5 because "load the relevant sections" is not actionable without a section index, and all detail sits in one monolithic file.	4 / 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 identifies a well-differentiated niche with strong natural trigger terms, but it is a domain label rather than a capability statement: it says nothing about what the skill does and gives no explicit 'use when' guidance. Adding concrete actions and a trigger clause would move it into good-example territory.

Suggestions

Add an explicit trigger clause, e.g. "Use quando o usuário mencionar maria da penha, violencia domestica, feminicidio ou pedir ajuda com medidas protetivas".

State concrete capabilities in third person, e.g. "Analisa casos, orienta vítimas e réus, redige peças e acompanha inquérito policial e ação penal".

Include common synonyms/variations users would say ("advogado", "denúncia", "defesa criminal", "Lei 11.340") to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	"Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio..." names a specific domain and many sub-areas but lists no concrete actions (no verbs describing what the skill actually does). This matches anchor 2 (domain named, actions minimal/generic); not 3 because not even 1-2 concrete actions are stated.	2 / 5
Completeness	It conveys a clear 'what' (a specialist in these named legal domains) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the 'when' is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	"Maria da Penha", "violencia domestica", "feminicidio", "medidas protetivas", "inquerito policial" are natural phrases users would say when needing this skill. Not 5 because common synonyms and variations (e.g., "advogado", "defesa criminal", "denúncia", "Lei 11.340") are missing.	4 / 5
Distinctiveness Conflict Risk	"Maria da Penha", "feminicidio", "direito penal brasileiro" define a clear niche with distinct triggers and minimal conflict risk. Not 5 because terms like "crime"/"criminal"-adjacent scope could overlap with other legal or general criminal-law skills.	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: 7b534bc

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.