BC jev-question-translator
Turns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a battery of narrow questions that TypeSafe's Jev, a fast classifier that returns probabilities rather than prose, can answer reliably across many documents. The skill breaks conclusions such as negligence, felony murder, or standing into element-level questions, writes the governing rule into each question, and delivers the questions alone, in Jev's request format or in plain English. Built for legal work that asks the same questions of many texts: coding statutes across jurisdictions, coding opinions or case files for empirical research, checking contracts against a review checklist, screening intake narratives, and grading student work against a rubric. Use when asked to write Jev questions, build a classifier for legal documents, or turn a legal test into yes-or-no questions. Running the questions requires Jev access; writing them does not.
Turns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a…
As a process C 64/100 · Has gaps — weak spots: failures and branches, consistency, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6584 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (jev-question-translator) differs from the folder (jev-question-translator-seth-chandler)
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6584 tokens
- 100Tools and files. No external tools needed
- 100Steps. 73 steps
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 1012: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 73 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.