CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lex

Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.

Quality

68%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/lex/SKILL.md

The canonical home for this skill is lex in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content body is a lean, well-structured instruction sheet with genuinely executable CLI commands, a sequenced workflow ending in source verification, and concise pitfalls guidance. Its main gaps are the absence of any feedback loop for failed searches/verification, no explanation of where the 'lex' CLI comes from, and no pointer to the template catalog for discovery. It sits comfortably in the 'good' band but short of excellent on error handling.

Suggestions

Add an error-recovery branch to the workflow, e.g., 'If lex search returns no match, state the gap and fall back to the closest jurisdiction's template rather than improvising legal content.'

State how the 'lex' CLI is invoked (bundled script path, install command) so the commands are executable from the skill alone, or note that it is an external prerequisite.

Add a one-line pointer to the template catalog (e.g., 'Run lex search with no query to list all 29 jurisdiction templates') so discovery doesn't depend on guessing queries.

DimensionReasoningScore

Conciseness

The body is efficient — compact step lists, two short CLI examples, and terse best-practice bullets — with only minor padding: the 'Truth Engine' / 'eliminate legal hallucinations' marketing language in the Overview and the repeated '29+ jurisdictions' phrasing could be trimmed. Not 5 because the Overview spends tokens on positioning rather than instruction.

4 / 5

Actionability

Gives concrete, runnable CLI commands ('lex search <query>', 'lex get <path>', 'lex draft "Czech house sale contract"', 'lex verify') plus a real template path ('templates/02_employment_workforce.md'). Not 5 because the 'lex' CLI itself is never established as provided or installed (no scripts/ bundle exists), so the commands are not guaranteed executable from the skill alone.

4 / 5

Workflow Clarity

A clear four-step sequence (identify jurisdiction → search & fetch → draft → verify authority) with a verification checkpoint at the end ('lex verify' producing a 'Verified Sources' section). Not 5 because there is no error-recovery or feedback loop (e.g., what to do when no template matches or verification finds no source), and the boundary case (outside US/EU/CA) is handled only in Best Practices.

4 / 5

Progressive Disclosure

The body is well-organized into clear sections (Overview, When to Use, How It Works, Examples, Best Practices, Common Pitfalls, Related Skills) with no inlined bulk content and no buried references; template detail is appropriately delegated to the CLI rather than inlined. Not 5 because the ~60-line body slightly exceeds the simple-skill threshold and the template catalog it indexes is never disclosed or linked, leaving navigation to blind 'lex search'.

4 / 5

Total

16

/

20

Passed

Description

48%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 clear niche (cross-jurisdictional legal context and contract scaffolding) but never states what the skill concretely does or when to invoke it. It reads as a product tagline rather than a capability description, with the buzzword "'Truth Engine'" substituting for specifics. Adding concrete verbs and a 'Use when...' clause would move it substantially closer to the good examples.

Suggestions

Replace the tagline framing with concrete third-person actions, e.g., 'Compares legal requirements across US, EU, and Canadian jurisdictions and drafts jurisdiction-compliant contract scaffolds from verified government sources.'

Add an explicit trigger clause: 'Use when comparing employment or business-formation law across jurisdictions, or when drafting contracts needing US/EU/CA-compliant clauses.'

Drop the "'Truth Engine'" buzzword and replace vague 'legal context' with the concrete capabilities already shown in the body (search templates, draft contracts, verify government sources).

DimensionReasoningScore

Specificity

Names the domain ('cross-jurisdictional legal context (US, EU, CA)') and 'contract scaffolding', but contains no concrete action verbs at all — only noun phrases plus the buzzword "'Truth Engine'". It stays at 2 rather than 3 because it lists none of the 1–2 concrete actions (e.g., compare, draft, verify) the skill actually performs.

2 / 5

Completeness

A 'what' is stated ('Centralized Truth Engine for cross-jurisdictional legal context and contract scaffolding') but it is jargon-laden and vague, and there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because 'when' is entirely absent, not merely under-specified.

3 / 5

Trigger Term Quality

Relevant keywords like 'legal', 'cross-jurisdictional', and 'contract scaffolding' are present, but common natural variations users would say ('law', 'jurisdiction', 'employment law', 'business formation', 'regulation') are missing. Not 4 because coverage stops at the domain label without synonyms or user-style phrasing.

3 / 5

Distinctiveness Conflict Risk

The cross-jurisdictional legal scope (US, EU, CA) carves out a fairly distinct niche with minor overlap risk against general legal or contract-template skills. Not 5 because 'contract scaffolding' could trigger generic contract-drafting skills, and no distinctive trigger phrase separates it.

4 / 5

Total

12

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/lex/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.