CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

advogado-especialista

Apoio a pesquisa juridica brasileira, organizacao de fatos e minutas, com verificacao em fontes oficiais e revisao profissional para casos concretos.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-advogado-especialista/SKILL.md

The canonical home for this skill is advogado-especialista in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

50%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 serviceable overview with genuine safety guardrails and a clearly signaled deep-dive reference, but it reads largely as template boilerplate: repetitive trigger bullets, an implicit rather than ordered workflow, and an orphaned references/fontes.md that no file links to. Tightening the boilerplate and surfacing fontes.md would lift most dimensions.

Suggestions

Link references/fontes.md from the body (e.g., in a 'Fontes oficiais' section pointing to it for the source index) so the bundle file is discoverable.

Collapse the six 'When the user mentions...' bullets into one line listing the trigger terms, freeing tokens for a concrete example (e.g., citation format with URL/date).

Turn the implicit procedure into an ordered intake-then-verify-then-draft sequence with explicit checkpoints (identify case data -> check consolidated text/precedents -> draft with citation -> re-verify), mirroring the guide's steps.

DimensionReasoningScore

Conciseness

The 'Escopo e verificacao' paragraph is dense and earns its tokens, but the six near-identical 'When the user mentions X or related topics' bullets and the boilerplate Do-Not-Use/Limitations sections are padding that could be tightened to a line or two — matching 'mostly efficient but includes some unnecessary explanation'. Not a 2 because the body is short and its core content is not padded.

3 / 5

Actionability

The body gives concrete intake directives ('identificar estado/municipio, foro, data dos fatos, rito, documentos e urgencia', 'citar URL, numero, data e limites da tese') but the actual procedure for researching, drafting, and verifying is deferred to the guide, and the body offers no examples — matching 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

A sequence is only implicit in a paragraph, with guardrails present ('Nao calcular prazo final sem termo inicial', 'Nao protocolar... sem autorizacao especifica') but no ordered steps or explicit validation checkpoints in the body itself — matching 'steps listed but validation gaps; checkpoints missing or implicit'. The destructive/batch cap does not apply since the skill performs no batch or destructive operations.

3 / 5

Progressive Disclosure

detailed-guide.md is clearly signaled (one level deep, with guidance to load relevant sections or read fully), but the bundle's second file, fontes.md, is never referenced from SKILL.md or the detailed guide, leaving 146 lines of source index unreachable. Scored against the actual bundle structure, this matches 'some structure but could be better organized' rather than the 'minor organization gaps' of a 4.

3 / 5

Total

12

/

20

Passed

Description

58%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 communicates a concrete, fairly distinct set of capabilities for Brazilian legal work, but entirely lacks a 'when to use' clause and the most natural Portuguese trigger words (advogado, direito, lei, peticao). This limits discoverability and routing reliability even though the capability statement itself is solid.

Suggestions

Append an explicit trigger clause, e.g. 'Use quando o usuario mencionar advogado, direito, lei, peticao, processo judicial ou pedir pesquisa juridica brasileira.'

Add the missing natural synonyms and file/task variations users actually say (advogado, direito, lei, peticao, contrato, prazo) to improve trigger_term_quality.

Replace the vague 'revisao profissional' with concrete outcomes such as 'revisao de minutas e citacao de precedentes (STJ/STF)' to push specificity toward 5.

DimensionReasoningScore

Specificity

The description names the domain (Brazilian legal research) and several concrete actions — 'organizacao de fatos e minutas', 'verificacao em fontes oficiais', 'revisao profissional' — matching the 'several specific actions with minor gaps' anchor. It is not a 5 because coverage has gaps (e.g., prazo/deadline calculation, petition drafting) and 'revisao profissional' is soft.

4 / 5

Completeness

The 'what' is clear (research support, fact organization, drafting, verification, review), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Terms like 'pesquisa juridica', 'minutas', 'fontes oficiais', and 'casos concretos' are relevant, but common natural phrases a Brazilian user would say — 'advogado', 'direito', 'lei', 'peticao', 'processo' — are absent, matching 'some relevant keywords but missing common variations or synonyms'. It exceeds score 2 because several genuinely natural keywords are present.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly distinct — Brazilian legal research with official-source verification — with only minor overlap risk against generic research or writing skills, matching the 'mostly distinct' anchor. It falls short of 5 because without explicit triggers it could still fire for adjacent legal/writing requests.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

boisenoise/skills-collections

Path

skills/antigravity-advogado-especialista/SKILL.md

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.