Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/a1
VS-Enhanced Research Question Refiner - Prevents Mode Collapse and derives differentiated research questions Enhanced VS 3-Phase process: Modal question avoidance, alternatives presentation, differentiated RQ recommendation
Passed 18 of 22 test cases with the skill, and 3 of 22 without it.
and 26 more in the full report
16 fixed2 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have a rough research idea regarding how remote work isolation impacts employee creativity in tech companies. Please refine this idea into a structured research question analysis. I need you to first highlight the most common or obvious baseline questions researchers usually ask about this, then provide alternative question directions ranging from safe/specific to highly innovative with typicality ratings, and finally execute a full recommendation for one direction using a PICO framework with variable definitions, theoretical contribution points, and feasibility ratings.
| Checked | Without skill | With skill |
|---|---|---|
| The output assigns a T-Score greater than 0.80 to high-typicality simple causation baseline questions | Missed | Passed |
| The alternative research questions are categorized into three distinct directions corresponding to safe, differentiated, and innovative T-Score tiers | Passed | Passed |
| The recommendation execution section contains a structured PICO table explicitly listing Population, Intervention, Comparison, Outcome, and Study design | Missed | Passed |
The instructions your model reads when the skill loads.
Entry point agent — no prerequisites required.
diverga_mark_checkpoint("CP_RESEARCH_DIRECTION", decision, rationale)diverga_mark_checkpoint("CP_VS_001", decision, rationale)diverga_mark_checkpoint("CP_VS_003", decision, rationale)Read .research/decision-log.yaml directly to verify prerequisites. Conversation history is last resort.
Agent ID: 01 Category: A - Theory & Design VS Level: Enhanced (3-Phase) Tier: Core Icon: 🎯
Transforms vague research ideas into clear, testable research questions. Systematically structures research questions using PICO/SPIDER frameworks.
Applies VS-Research methodology to avoid overly broad or predictable research questions, deriving differentiated questions with clear academic contribution.
Purpose: Explicitly identify the most predictable "obvious" research questions
⚠️ **Modal Warning**: The following are the most predictable research questions for [topic]:
| Modal Research Question | T-Score | Problem |
test cases passed, vs 3 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.