literature-review
Skill1 starsChanged 7 months agoMITView on GitHub
Conduct systematic literature reviews using PubMed, bioRxiv, and other scientific databases. Use this skill when researchers need to develop a search strategy, define inclusion criteria, extract data from papers, synthesize findings, or identify gaps in the literature. Trigger with "literature review", "search the literature", "what papers exist on", "systematic review", "find studies about", or "gap analysis".
92 other projects use a version of this.
Adopted by
Most recently taken up by
- BraveDistribution/claude-skillstheir own version, first seen Nov 16, 2026
- KPISTOLAS/claude-skillstheir own version, first seen Nov 16, 2026
- Ivan-propio/claude-skillstheir own version, first seen Nov 16, 2026
- tatashbar/Economic-Modeling-Studiotheir own version, first seen Nov 16, 2026
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- PerryLink/dsh-research-skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use pdf-explore, paper-narrative and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JimLiuSkillpdf-explore
Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Skip it only for a single lookup of 1–4 pages quoted in your very next response — `read_file(pages=[...])` attaches pages as images that are dropped from context after one turn, so multi-section answers end up re-reading the same ranges repeatedly. Parses the PDF once in the Python kernel: `pdf_pages` (pages as persistent text), `pdf_outline` (TOC), `pdf_scan` (rank pages by relevance), `pdf_map`/`pdf_extract` (per-page summary / structured fields via parallel haiku calls). For PDF creation/manipulation, use reportlab/pypdf directly.
Also in 9 projects that use this
JimLiuSkillpaper-narrative
Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. `derive_paper_brief(abstract, captions)` extracts pitch/vision/per-figure-claims; a handling-editor reviewer on the full deck returns hook_verdict (would Fig 1 make me send this for review?), arc (hook→mechanism→evidence→application), figure_moves (panels in the wrong figure), missing_panels (concrete analyses to RUN), kill_list, and boldest_defensible_fig1. Hands per-figure claims to `figure-composer`. Load when writing or revising a paper.
Also in 5 projects that use this
Norman-burySkillbrainstorming-research
Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue
Also in 4 projects that use this
lingzhi227Skilllatex-formatting
Handle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage packages, and ensure venue-specific compliance. Use when the user needs to set up a paper template, fix LaTeX formatting, or prepare for submission.
Also in 4 projects that use this
lingzhi227Skillnovelty-assessment
Assess research idea novelty through systematic literature search. Multi-round search-evaluate loops with harsh critic persona. Binary novel/not-novel decision with justification. Use before committing to a research direction.
Also in 4 projects that use this
- +6 more from JimLiu
- +1 more from lingzhi227
Other versions92 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 92
- advaitpaliwal/feynman★ 10ksame name
- companion-inc/feynman★ 10ksame name
- getcompanion-ai/feynman★ 10ksame name
- Norman-bury/research-writing-skill★ 3.4ksame name
- Norman-bury/articlewriting-skill★ 3.4ksame name
- HughYau/AcademicForge★ 2.6ksame name
- K-Dense-AI/claude-scientific-writer★ 2.6ksame name
- xuzhougeng/wisp-science★ 1.1ksame name
- wu-yc/LabClaw★ 1.1ksame name
- LeonChaoX/qinyan-academic-skills★ 910same name
82 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- generate-guidelinesSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- ticket-triageSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- design-systemSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- tutoringSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- incident-responseSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 72 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 58
PubMed: Use search_articles with the constructed query.
- Very specific: line 59
bioRxiv/medRxiv: Use search_preprints to capture recent work not yet indexed in PubMed.
- Very specific: line 60
Citation chasing: Use find_related_articles on key papers to find additional relevant work.
- Very specific: line 61
Full text retrieval: Use convert_article_ids to find PMCIDs, then get_full_text_article for open-access full text.
- Very specific: line 81
Title/abstract screen: Use get_article_metadata to retrieve abstracts.
- Distinctive: line 174
Always document the search strategy completely.
- Distinctive: line 177
Use the PRISMA flow diagram framework even for non-systematic reviews.
- Distinctive: line 178
When synthesizing, focus on the weight of evidence rather than individual studies.
- Distinctive: line 179
Always note the limitations of the review itself: search database coverage, language restrictions, date range, single-reviewer screening.
- Distinctive: line 182
Check for retracted papers using PubMed's retraction notices before including studies.
“Common” is measured: kept by at least 6 in 10 of the 72 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Systematic Literature Review
Conduct structured literature reviews from search strategy development through synthesis and gap analysis. Use PubMed and bioRxiv tools to search, retrieve, and analyze scientific publications systematically.
Workflow
Step 1: Define the Review Question
Structure the research question using the PICO(S) framework:
- P (Population): What organism, cell type, patient group, or system?
- I (Intervention/Exposure): What treatment, gene, pathway, or variable?
- C (Comparison): What is the control or alternative condition?
- O (Outcome): What is measured or observed?
- S (Study design): What types of studies are relevant (RCT, cohort, in vitro)?
Convert the PICO elements into search terms with synonyms and MeSH terms.
Step 2: Develop the Search Strategy
Build a structured search query for PubMed:
(term1 OR synonym1 OR "MeSH term"[MeSH]) AND
(term2 OR synonym2) AND
(outcome_term OR outcome_synonym) AND
("2020/01/01"[Date - Publication] : "3000"[Date - Publication])Search execution plan:
- PubMed: Use
search_articleswith the constructed query. Apply date filters as needed. - bioRxiv/medRxiv: Use
search_preprintsto capture recent work not yet indexed in PubMed. - Citation chasing: Use
find_related_articleson key papers to find additional relevant work. - Full text retrieval: Use
convert_article_idsto find PMCIDs, thenget_full_text_articlefor open-access full text.
Step 3: Screen and Select Papers
Apply inclusion/exclusion criteria to search results:
Inclusion criteria (define before screening):
- Relevant population/model system
- Addresses the research question
- Published within the date range
- Acceptable study design
- English language (or specified languages)
Exclusion criteria:
- Reviews, editorials, letters (unless specifically sought)
- Retracted publications
- Insufficient methodological detail
- Duplicate publications from the same dataset
Screen in two passes:
- Title/abstract screen: Use
get_article_metadatato retrieve abstracts. Apply inclusion/exclusion criteria. - Full-text screen: For papers passing abstract screening, retrieve full text when available. Assess methodological quality.
Step 4: Extract Data
For each included paper, extract structured information:
| Field | Description |
| Citation | Authors, year, journal, DOI |
| Study design | RCT, cohort, case-control, in vitro, etc. |
| Population/model | Species, cell type, patient cohort details |
| Sample size | N per group, replicates |
| Key methods | Assays, techniques, statistical approaches |
| Main findings | Primary outcomes with effect sizes |
| Limitations | As reported by authors and as assessed |
| Relevance to question | How this paper addresses the review question |
Step 5: Synthesize Findings
Organize extracted data into a narrative synthesis:
- Thematic grouping: Cluster papers by sub-topic, methodology, or finding direction.
- Consensus assessment: Identify where studies agree (strong evidence) and disagree (contested areas).
- Methodological comparison: Note differences in experimental design that may explain conflicting results.
- Temporal trends: Track how understanding has evolved over time.
- Gap identification: Explicitly state what has NOT been studied or remains unresolved.
Step 6: Produce the Review Report
Assemble findings into a structured report with proper citations.
Output Format
## Literature Review: <Topic>
**Question**: <PICO-formatted question>
**Scope**: <rapid/standard/comprehensive>
**Databases searched**: <list>
**Date range**: <start> to <end>
**Search date**: <date conducted>
### Search Strategy
<Query used for each database>
**Results**: <n> papers found, <n> after deduplication, <n> included after screening
### PRISMA Flow
- Identified: <n>
- Duplicates removed: <n>
- Title/abstract screened: <n>
- Excluded at screening: <n> (reasons: ...)
- Full-text assessed: <n>
- Excluded at full-text: <n> (reasons: ...)
- **Included**: <n>
### Key Findings
#### Theme 1: <Title>
<Narrative synthesis of 3-10 papers with citations>
#### Theme 2: <Title>
<Narrative synthesis>
### Evidence Summary Table
| Study | Design | N | Key Finding | Effect Size |
|--------------|---------|------|--------------------|-------------|
| Author 2024 | RCT | 200 | <finding> | <value> |
### Gaps and Future Directions
1. <Gap identified> -- Suggested approach: <recommendation>
2. <Gap identified> -- Suggested approach: <recommendation>
### Limitations of This Review
- <limitation of the review methodology>
### References
<Numbered reference list with DOIs>Examples
User: "What do we know about CRISPR base editing efficiency in primary T cells?" Action: Define PICO (P: primary T cells, I: base editing, O: efficiency), search PubMed and bioRxiv, screen results, extract editing efficiency data across studies, synthesize findings by editor type (ABE vs CBE).
User: "Do a rapid literature review on GLP-1 agonists and neurodegeneration" Action: Rapid scope (10-20 papers), search PubMed for recent reviews and key primary studies, focus on clinical and preclinical evidence, produce a concise synthesis with gap analysis.
User: "I need a comprehensive review for my grant introduction on tumor microenvironment and immunotherapy resistance" Action: Comprehensive scope, search PubMed with MeSH terms, include bioRxiv preprints, extract mechanistic data from 50+ papers, organize by resistance mechanism, identify underexplored areas suitable for grant aims.
Best Practices
- Always document the search strategy completely. Another researcher should be able to reproduce your search exactly.
- Define inclusion/exclusion criteria BEFORE screening to avoid bias. Do not adjust criteria to include or exclude specific papers after seeing results.
- For rapid reviews, prioritize recent reviews and meta-analyses to get an overview, then read key primary studies they cite.
- Use the PRISMA flow diagram framework even for non-systematic reviews. It provides transparency about how papers were selected.
- When synthesizing, focus on the weight of evidence rather than individual studies. One paper with a surprising result does not override 10 papers showing the opposite.
- Always note the limitations of the review itself: search database coverage, language restrictions, date range, single-reviewer screening.
- Distinguish between preprints (not peer-reviewed) and published papers when citing. Note this distinction explicitly.
- For topics with extensive literature (>500 results), narrow the search with additional terms or date restrictions rather than trying to screen everything.
- Check for retracted papers using PubMed's retraction notices before including studies.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

