BB legal-design-assessment
Audits a legal document against legal design principles. Scores the document on six pillars: language patterns (bureaucratese, archaisms, passive voice, nominalization), readability (Flesch Reading Ease and language-specific equivalents), structure and navigation, hidden conditions (material obligations buried away from their headings), statutory duplication (restating the law instead of citing it), and visual hierarchy where layout is available. Assessment-only; does not rewrite the document. Works on English, French, and German documents, inferring the applicable jurisdiction from the document's language and textual signals: governing-law clause, statute citations, party addresses. Use when a user shares a legal document (contract, NDA, T&C, privacy policy, internal policy) asking how good the drafting is from a legal design perspective, whether it is readable, whether it contains buried clauses or restates the law, or how it scores on Flesch / LIX / Amstad / Kandel-Moles readability metrics.
Audits a legal document against legal design principles.
As a process B 68/100 · Nearly there — weak spots: consistency, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Audits a legal document against legal design principles. Scores th… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (legal-design-assessment) differs from the folder (legal-design-assessment-mirza-chiragov)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 7 branches
- 85Steps. 47 steps, 1 vague phrases
- 100Execution cost. Instruction body is 3393 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1009: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 20 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.