Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/b1
VS-Enhanced Literature Review Strategist - Comprehensive support for multiple review methodologies Full VS 5-Phase process: Prevents Mode Collapse and presents creative search strategies Supports: Systematic Review (PRISMA 2020), Scoping Review (JBI/PRISMA-ScR), Meta-Synthesis, Realist Synthesis, Narrative Review, Rapid Review
Passed 10 of 19 test cases with the skill, and 7 of 19 without it.
and 7 more in the full report
6 fixed6 passed either way9 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am preparing a PRISMA-compliant literature search plan for a systematic review evaluating digital mental health interventions for college students. Please build a full search strategy document. It should start by identifying baseline/common search pitfalls to avoid, present three tiered search strategy options ranging from standard multi-database searches to advanced or innovative approaches with explicit rationale for selection, and then detail the concrete database search strings (including PubMed and OpenAlex), supplementary search plans, and a draft PRISMA flow diagram format. Conclude with a verification checklist and a critical self-evaluation of the strategy's strengths and potential omissions.
| Checked | Without skill | With skill |
|---|---|---|
| Assigns a typicality score between 0.90 and 0.95 to single-database search strategy pitfalls | Missed | Passed |
| Presents Direction B as a comprehensive PRISMA strategy with a typicality score around 0.38 to 0.40 | Missed | Passed |
| Includes a self-critique section containing a confidence assessment table | Missed | Passed |
The instructions your model reads when the skill loads.
diverga_check_prerequisites("b1") → must return approved: true
If not approved → AskUserQuestion for each missing checkpoint (see .claude/references/checkpoint-templates.md)
diverga_mark_checkpoint("CP_SCREENING_CRITERIA", decision, rationale)diverga_mark_checkpoint("CP_SEARCH_STRATEGY", decision, rationale)diverga_mark_checkpoint("CP_VS_001", decision, rationale)Read .research/decision-log.yaml directly to verify prerequisites. Conversation history is last resort.
Agent ID: 05 (formerly B1-Systematic Literature Scout) Category: B - Literature & Evidence VS Level: Full (5-Phase) Tier: Core Icon: 📚
Develops and executes comprehensive literature search strategies for multiple review methodologies. Applies VS-Research methodology to avoid monotonous strategies like "search PubMed only," proposing comprehensive and reproducible search strategies tailored to review type.
This agent supports 6 major literature review methodologies:
| Review Type | Standard/Framework | Purpose | Timeline |
|---|---|---|---|
| Systematic Review | PRISMA 2020 | Intervention effectiveness, policy evidence synthesis | 6-12 months |
| Scoping Review | JBI Scoping Review, PRISMA-ScR | Research area mapping, gap identification, concept clarification | 4-8 months |
| Meta-Synthesis | Noblit & Hare (Meta-ethnography), Thematic synthesis | Qualitative research integration, theory development | 8-12 months |
| Realist Synthesis | RAMESES standard | Complex intervention context-mechanism-outcome analysis | 8-14 months |
| Narrative Review | Traditional, Critical, Integrative | Theory development, concept clarification, critical analysis | 3-6 months |
test cases passed, vs 7 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.