Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.
38
24%
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-especialista/SKILL.mdQuality
Discovery
22%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description reads more like a professional title or bio than a functional skill description. It lists legal domains but fails to specify concrete actions the skill performs and entirely lacks a 'Use when...' clause. The first-person framing as 'Advogado especialista' (specialist lawyer) is problematic, and the breadth of claiming all areas of law reduces its usefulness for skill selection.
Suggestions
Add concrete actions the skill performs, e.g., 'Redige petições, analisa contratos, orienta sobre direitos, calcula prazos processuais, elabora pareceres jurídicos'.
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Brazilian legal questions, needs help drafting legal documents, or mentions termos como petição, processo, contrato, ou legislação brasileira'.
Rewrite in third person describing capabilities rather than identity, e.g., 'Provides Brazilian legal guidance across multiple domains...' instead of 'Advogado especialista'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only states the skill is a 'specialist lawyer in all areas of Brazilian law' and lists legal domains, but does not describe any concrete actions (e.g., draft petitions, analyze contracts, calculate deadlines). Listing areas of law is not the same as listing capabilities. | 1 / 3 |
Completeness | The description partially addresses 'what' (specialist in Brazilian law areas) but in a very vague way without concrete actions, and completely lacks any 'when' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | It includes several relevant legal domain keywords (família, criminal, trabalhista, tributário, consumidor, imobiliário, empresarial, civil, constitucional) that users might mention, but lacks action-oriented trigger terms like 'petição', 'contrato', 'consulta jurídica', 'processo', or common user phrasings. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on Brazilian law ('Direito brasileiro') provides some distinctiveness, but claiming expertise in 'all areas' is extremely broad and could overlap with any legal-related skill. The lack of specific actions makes it harder to distinguish from other potential legal skills. | 2 / 3 |
Total | 6 / 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 essentially a Brazilian legal encyclopedia crammed into a single SKILL.md file, containing extensive reference tables on family law, criminal law, labor law, consumer law, and many other areas. While the 12-step case analysis workflow and client profile adaptation are useful structural elements, the overwhelming majority of content is reference material that Claude already knows or could derive, making it extremely token-inefficient. The content would benefit enormously from being split into separate reference files with the SKILL.md serving as a concise routing and workflow guide.
Suggestions
Extract all module reference tables (Modules 1-14) into separate files (e.g., `modulo-familia.md`, `modulo-criminal.md`) and keep only the routing table and workflow in SKILL.md
Remove reference information Claude already knows (penalty ranges, article numbers, court precedents) or move it to appendix files that are loaded only when needed
Add validation checkpoints to the 12-step workflow, such as 'Verify all cited articles exist before presenting analysis' and 'Confirm client profile before proceeding'
Reduce the SKILL.md to under 100 lines focusing on: when to use, client profile identification, the case analysis workflow, orchestration rules, and links to detailed reference modules
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at 700+ lines, containing encyclopedic legal reference material that Claude already knows (Brazilian law articles, penalty ranges, court precedents, types of damages, etc.). The vast majority of content is reference information that doesn't teach Claude anything new about how to perform a task — it's essentially a legal textbook dumped into a skill file. | 1 / 3 |
Actionability | The 12-step workflow for case analysis and the client profile adaptation table provide some concrete guidance on how to approach legal consultations. However, most content is reference tables rather than executable instructions, and the 'modules' referenced (Module 1-14) are just inline content sections rather than actionable procedures with clear steps. | 2 / 3 |
Workflow Clarity | The 12-step case analysis workflow is reasonably well-sequenced and includes a structured output template (Etapa 12). However, it lacks validation checkpoints, feedback loops, or error recovery steps. The initial routing table (identify area → module) is helpful but the modules themselves are just reference material without procedural guidance. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with all 14 modules inline rather than split into separate reference files. The skill mentions orchestrating with `advogado-criminal` but keeps hundreds of lines of reference tables that should be in separate files. There's no meaningful progressive disclosure — everything is dumped into a single massive document. | 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 (1115 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 | |
1a9f5ac
Table of Contents
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.