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 Use when: conducting any type of literature review, systematic reviews, meta-analyses, scoping reviews, finding prior research
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill b1 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill develops and executes comprehensive literature search strategies across six major review methodologies, applying VS-Research methodology to create reproducible search plans tailored to the review type. It supports systematic reviews (PRISMA 2020), scoping reviews (JBI/PRISMA-ScR), meta-synthesis, realist synthesis, narrative reviews, and rapid reviews.
How it works
It follows the VS-Research 5-Phase Process:
- Phase 0: Context Collection (MANDATORY) to gather review_type, research_question, and key_concepts before applying the strategy.
- Phase 1: Modal Search Strategy Identification, with guidance on typical modal strategies and warnings for each review type.
- Phase 2: Long-Tail Strategy Sampling, presenting three directions with different T-scores and search emphases.
- Phase 3: Low-Typicality Selection, selecting the appropriate strategy based on comprehensiveness, reproducibility, efficiency, and PRISMA alignment.
- Phase 4: Execution, detailing database-specific search strings, supplementary searches, and a PRISMA flow diagram.
- Phase 5: Originality/Comprehensiveness Verification, confirming avoidance of biases and ensuring PRISMA 2020 compliance and reproducibility.
The agent uses the provided prerequisites, triggers, and contextual inputs to shape the search strategy, and emphasizes iterative, theory-driven approaches for realist synthesis and breadth through scoping and narrative reviews.
When to use it
Use when conducting any type of literature review, including systematic reviews, scoping reviews, meta-analyses, realist synthesis, narrative reviews, and rapid reviews, especially when prior research broadness, methodological rigor, or reproducibility are important.
What it can touch
- Tools: claude-code
- It references: Required Context including review_type, research_question, key_concepts, and optional criteria like inclusion/exclusion criteria, target databases, and timeline for rapid reviews.
Caveats
- Prerequisites require approved status via diverga_check_prerequisites("b1"). If not approved, it prompts for missing checkpoints according to MCP enforcement.
- Checkpoints during execution include CP_SCREENING_CRITERIA, CP_SEARCH_STRATEGY, and CP_VS_001, each logged via diverga_mark_checkpoint with decision and rationale.
- Fallback is reading .research/decision-log.yaml directly if MCP is unavailable.
- License: NOASSERTION.
## ⛔ Prerequisites (v8.2 — MCP Enforcement) `diverga_check_prerequisites("b1")` → must return `approved: true` If not approved → AskUserQuestion for each missing checkpoint (see `.claude/references/checkpoint-templates.md`) ### Checkpoints During Execution - 🟠 CP_SCREENING_CRITERIA → `diverga_mark_checkpoint("CP_SCREENING_CRITERIA", decision, rationale)` - 🟡 CP_SEARCH_STRATEGY → `diverga_mark_ch
What does the b1 skill do?
VS-Enhanced Literature Review Strategist - Comprehensive support for multiple review methodologies Full VS 5-Phase process: Prevents Mode Collapse and presents creative search strategies Use when: conducting any type of literature review, systematic reviews, meta-analyses, scoping reviews, finding prior research
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill b1 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.