advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
51
41%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/advogado-criminal/SKILL.mdQuality
Discovery
54%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 effectively identifies a clear legal niche with strong domain-specific trigger terms in Portuguese, making it distinctive and unlikely to conflict with other skills. However, it fails to describe concrete actions the skill performs (it reads as a credential statement rather than a capability description) and completely lacks a 'Use when...' clause, significantly hurting completeness.
Suggestions
Add concrete actions the skill performs, e.g., 'Elabora peticoes, analisa processos, orienta sobre medidas protetivas, redige denuncias' instead of just listing topic areas.
Add an explicit 'Use when...' clause, e.g., 'Use quando o usuario precisar de orientacao sobre violencia domestica, Lei Maria da Penha, medidas protetivas, ou questoes de direito penal brasileiro.'
Rewrite in third person describing capabilities rather than identity (e.g., 'Orienta sobre direito penal brasileiro...' instead of 'Advogado criminalista especializado em...').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (criminal law, domestic violence, Maria da Penha) and lists several specific legal areas, but does not describe concrete actions the skill performs (e.g., 'drafts petitions', 'analyzes cases', 'generates legal documents'). It reads more like a professional profile than a capability list. | 2 / 3 |
Completeness | The description only partially answers 'what' (lists topics but no concrete actions) and completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 2, and the weak 'what' further reduces it. | 1 / 3 |
Trigger Term Quality | Includes strong natural keywords a Portuguese-speaking user would use: 'Maria da Penha', 'violencia domestica', 'feminicidio', 'direito penal brasileiro', 'medidas protetivas', 'inquerito policial', 'acao penal'. These are highly relevant and cover common variations of the domain. | 3 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to Brazilian criminal law and domestic violence legislation (Maria da Penha). It occupies a very clear niche that is unlikely to conflict with other skills, given the specialized legal terminology and jurisdiction. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an exhaustive legal reference document rather than an efficient skill file. While it demonstrates deep domain knowledge and includes a useful 10-step case analysis workflow, it massively violates token efficiency by inlining hundreds of lines of legal reference tables that Claude likely already knows from training data. The content would be far more effective as a concise overview with workflows, pointing to separate reference files for legislation tables, crime comparisons, and procedural details.
Suggestions
Extract all reference tables (legislation maps, crime/penalty tables, prescription tables, drug law comparisons, property crimes, execution benefits) into separate reference files and link to them from the main SKILL.md, keeping only the workflow and key decision logic inline.
Remove content Claude already knows from training data — Brazilian Penal Code articles, basic criminal law concepts, CPC provisions, and standard legal definitions. Focus only on novel decision logic, specific workflows, and non-obvious guidance.
Add explicit validation checkpoints to the 10-step workflow, such as 'Verify cited articles exist and are current before proceeding to dosimetry' and 'If classification is ambiguous, list alternatives and request clarification before continuing.'
Reduce the SKILL.md to under 100 lines focusing on: (1) when/how to identify the request type, (2) the core analysis workflow with validation steps, (3) key constraints and safety rules, and (4) links to detailed reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines. Contains massive reference tables that Claude already knows (e.g., basic criminal law concepts, prescription tables, prison types, CPC articles). The entire content reads like a law textbook rather than a skill that adds what Claude doesn't already know. Much of this (Brazilian Penal Code articles, STJ súmulas, crime classifications) is within Claude's training data. | 1 / 3 |
Actionability | The 10-step workflow for case analysis and the verdict template in Etapa 10 provide some concrete, actionable structure. However, most content is reference tables rather than executable guidance. The flowchart for victim assistance and the decision tables for identifying request types are useful but could be more concise. No actual code examples beyond trivial bash commands. | 2 / 3 |
Workflow Clarity | The 10-step case analysis workflow (Module 10) provides a clear sequence, and the victim assistance flowchart is well-structured. However, there are no explicit validation checkpoints or feedback loops — for instance, no step says 'verify legal basis exists before proceeding' or 'if classification is uncertain, gather more facts before dosimetry.' The workflow lacks error recovery steps for a domain where incorrect analysis could have serious consequences. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inline — 15+ major sections covering legislation tables, crime comparisons, drug law, property crimes, execution benefits, and more, all in a single file. No references to separate files for detailed content. The skill would benefit enormously from splitting reference tables into separate files and keeping only the overview and workflow in the main SKILL.md. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
1a9f5ac
- 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.