Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/employment-law-research
Research a US employment law topic across federal, state, and city jurisdictions and produce structured research notes with proper source attribution.
Passed 17 of 21 test cases with the skill, and 11 of 21 without it.
and 5 more in the full report
7 fixed11 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When collecting law firm articles and legal commentary for our research brief's Resources section, what are the target recency timeframes for enacted laws versus pending bills?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies a recency target within the last 6 months for enacted laws reporting. | Missed | Passed |
| Specifies a recency target within the last 3 months for pending bills reporting. | Passed | Passed |
The instructions your model reads when the skill loads.
This skill produces a structured research brief on a specific area of US employment law. The note is the input for downstream work like building a dashboard, writing a memo, or briefing a stakeholder. The most important thing the skill does is enforce a clean separation between primary-source claims (the statute says X) and secondary-source claims (Cooley wrote about it last week).
Assume the audience is practicing lawyers.
Use this skill standalone when the user just wants research, OR as the first step before the employment-law-dashboard skill. If a dashboard is the eventual deliverable, complete this skill's workflow first and save the research note before invoking the dashboard skill.
The skill should fire whenever a user asks for research, comparison, or landscape on a US employment law topic. Examples:
Before doing any web searches, lock down three things with the user:
For dashboard prerequisites, you can usually inherit scope from the dashboard request directly without a separate clarification round.
Before searching, read references/source-policies.md. This is the load-bearing constraint of the skill. It explains which kinds of statements need primary sources only, and which can use reputable secondary sources. Apply it as you research, not just at writeup time — if you find yourself reaching for a secondary source for a statutory claim, push back to the primary source.
Use available web search and fetch tools. Cover the layers in this order:
a. Federal layer
test cases passed, vs 11 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.