Literature Review Skills for AI Agents
Literature review skills turn a pile of papers into a map of a conversation. They belong to the deliverable category because the output is a document a reader can follow, not a research process you keep to yourself. Skills in this topic cover the full arc: search, so the map is not accidental; screening, so inclusion and exclusion are deliberate; reading for claims and methods rather than titles; synthesis that shows how sources relate and where they disagree; gap identification that makes the next study legitimate; and citation, so every claim has a source a reader can open. Use the ranked list by scanning titles and descriptions for the stage you are stuck on, then read the skill's SKILL.md to confirm its inputs and outputs match your material. Pick one, run it on a small slice of your sources, and judge the output before committing your whole review.
3 to start with20 top options
Start with these.
A literature review is a map of a conversation: search, screen, read, synthesize, and show the gap — not an annotated pile of PDFs.
These are the closest matches for this work. Start with the first one and open it to install.
- Rank 01View Agent SkillDirect
firecrawl-research-papers
Finds and synthesizes research papers via Firecrawl's paper index (PubMed, bioRxiv, medRxiv, arXiv) with semantic search, related-paper expansion, and in-body claim verification. Purpose-built for literature reviews and systematic reviews.
33,101 · popularity - Rank 02View Agent SkillDirect
literature-review
Systematic literature review workflow covering question definition, search planning, deduplication, staged screening, data extraction, thematic synthesis, and citation verification, with a search log and output template.
6,447 · popularity - Rank 03View Agent SkillDirect
academic-search
Helps formulate academic search queries, recommends databases and strategies, analyzes abstracts, explains methodologies, and structures literature reviews with citation management. Directly targets the search and screening facets.
5,583 · popularity
Explore 17 more Agent Skills
- Rank 09View Agent SkillPossible
firecrawl-workflows
Router for outcome-focused Firecrawl workflows including research reports, literature reviews, SEO audits, and knowledge bases. Points to the dedicated research-papers skill for literature review work.
32,186 · popularity - Rank 10View Agent SkillPossible
firecrawl
NotableAny live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse. For papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.
- Rank 11View Agent SkillPossible
academic-paper
12-agent academic paper writing pipeline with modes including lit-review, citation-check, and revision, plus LaTeX/DOCX/PDF output. Includes a literature review mode but is primarily a paper-writing system.
10,067 · popularity - Rank 12View Agent SkillPossible
nature-paper-card
Builds a structured deep-reading Paper Card for one scientific paper, analyzing methods, evidence chains, limitations, and research ideas. Covers the reading facet of literature review for individual papers.
8,798 · popularity - Rank 13View Agent SkillPossible
bmad-deep-recon
Research director skill that drafts research prompts, processes finished reports into cited summaries, or runs parallel web research, with an academic-lit research type. Supports literature review research but is a general research orchestr
7,000 · popularity - Rank 14View Agent SkillPossible
ljg-paper
Explains a single research paper to non-specialist readers, covering what it studies, its contributions, and what the evidence does not establish, saving an Org note. Covers the reading facet but not search or synthesis.
6,802 · popularity - Rank 15View Agent SkillPossible
research
Spins up a background agent to investigate a question against primary sources and write findings to a cited Markdown file. General research delegation, applicable to literature review but not paper-specific.
629,500 · popularity - Rank 16View Agent SkillPossible
academic-pipeline
Orchestrates a full academic pipeline from research through writing, integrity checks, review, and revision, coordinating deep-research, academic-paper, and reviewer skills. Includes literature review as a stage but is a broad orchestrator.
6,661 · popularity - Rank 17View Agent SkillPossible
scholar-evaluation
Evaluates academic work (papers, proposals, literature reviews) against a reproducible rubric covering problem, literature, methodology, evidence, analysis, and citations. Supports critical appraisal within a review.
5,761 · popularity - Rank 18View Agent SkillPossible
notion-research-documentation
OfficialResearch across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
- Rank 19View Agent SkillPossible
just-scrape
Searches, scrapes, crawls, extracts structured data, and monitors web pages via the ScrapeGraph AI CLI. Supports source gathering for literature review but is a general web-scraping tool.
244,988 · popularity - Rank 20View Agent SkillPossible
web-search
Web search and content extraction via Tavily and Exa through the inference.sh CLI, with research and RAG use cases. Covers the search facet but is a generic search tool, not a review workflow.
87,691 · popularity - Rank 21View Agent SkillPossible
academic-paper-reviewer
Simulates a multi-perspective peer review panel with journal-fit, methodology, and devil's-advocate roles, producing an editorial decision and revision roadmap. Reviewing papers, not conducting literature reviews.
9,151 · popularity - Rank 22View Agent SkillPossible
paper-audit
Reviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf, producing issue bundles, revision roadmaps, and readiness decisions. Reviews a single paper, not a literature body.
Needs (stated): Python
3,219 · popularity - Rank 23View Agent SkillPossible
nature-writing
Drafts and restructures scientific manuscript sections and submission materials in Nature style, routing by task, paper type, section, and journal. Writing-focused, adjacent to literature review but not search or synthesis.
13,796 · popularity - Rank 24View Agent SkillPossible
pptx
OfficialUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.
- Rank 25View Agent SkillPossible
firecrawl-search
NotableFind web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.
83,108 · popularity
What this topic covers
Each sub-topic groups Agent Skills for a specific situation.
- Search
- Where you looked and with which terms, so the map is not accidental.
- Screening
- What counted, and what was left out, on purpose.
- Reading
- Pull claims and methods, not just titles.
- Synthesis
- How the sources relate, including where they disagree.
- Gap
- What this review now makes it legitimate to study next.
- Citation
- Every claim in the map has a source a reader can open.
Frequently asked questions
- What separates a literature review skill from a reference manager?
- A reference manager stores and formats sources; a literature review skill produces a map of the conversation across search, screening, reading, synthesis, gap, and citation. The deliverable is an argument about how the sources relate, including where they disagree.
- How is this list ordered?
- It is ranked by observed search demand, with direct matches to the topic placed first and a cap on how many skills any single publisher can occupy. Work down the list until a skill's scope matches the stage you need.
- Can a skill handle the screening stage without me deciding what counts?
- Screening is about what counted and what was left out on purpose, so the criteria are yours to set. A skill can apply and document those decisions, but you supply the inclusion and exclusion rules.
- What should I check in a skill before running it on my sources?
- Read its SKILL.md to see which of the six stages it covers and what it expects as input. Then test it on a small subset of sources and check whether the citations it produces are ones a reader can actually open.
How to install an Agent Skill
Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:
- Claude Code — copy the SKILL.md for firecrawl-research-papers into ~/.claude/skills/firecrawl-research-papers/ for yourself, or .claude/skills/firecrawl-research-papers/ to share it with a project.
- From the registry — run npx skills add firecrawl/firecrawl-workflows@firecrawl-research-papers.
- Or download firecrawl-research-papers from its source and place that SKILL.md in the directory above.
How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.