Skip to content
Get packs

Literature Search Methodology

Guides the agent through systematic literature reviews: search strategy, screening, PRISMA flow, and synthesis.

Source Download skill
Repository
aiming-lab/AutoResearchClaw
Stars
14,802
Licence
MIT
Files
1 file

What it does

When installed, this skill gives the AI agent a structured playbook for finding and reviewing academic papers. It tells the agent to turn a research question into a PICO-style framing, build search terms and Boolean queries, choose suitable databases (such as PubMed, arXiv, or Google Scholar), set inclusion criteria before screening, screen papers in two passes, and summarize findings with a PRISMA-style record. It is written as methodology guidance only; it does not itself connect to any database.

Great for

  • Graduate students writing a systematic or scoping review who want a checklist-driven process
  • Researchers drafting background sections who need a clear, reproducible search method
  • Teams in AI or ML research who want a reminder to document search strings and screening criteria

Skip it if

  • Anyone expecting the agent to automatically query PubMed or arXiv and return verified results: the file contains no search tools or scripts, so the agent relies on its own knowledge and any tools it already has, and may invent citations or details.
  • Medical or clinical decisions that depend on evidence: the guidance is general and does not replace expert review or formal systematic review training.

Try asking

  • “Help me design a search strategy with PICO terms and Boolean operators for a review on transformer efficiency.”
  • “Create a PRISMA flow outline for my scoping review and tell me what counts I need to record.”
  • “Write a background section on diffusion models, organized thematically with research gaps at the end.”
  • “Which databases should I search for a computer science literature review, and what inclusion criteria should I document first?”
Step-by-step guide: how to use Literature Search MethodologyInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    literature-search.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip literature-search.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip literature-search.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent your research question up front so it can build PICO terms and search strings from it.
  • Ask the agent to list the exact search strings and databases used, then verify them yourself in each database.
  • Treat any citations the agent produces as leads to check against the original papers, since this skill does not verify sources.

What's inside

  • SKILL.md

Redistributed unmodified from aiming-lab/AutoResearchClaw under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.