- Home
- Skills
- Research & Analysis
- literature-discovery
Works with the AI Agents you already use
Literature Discovery
Systematic discovery and landscape mapping of scientific literature with citation analysis and venue quality filtering.
Free
literature-discovery
Example session with this skill installed
Use the literature-discovery skill to map recent research on retrieval-augmented generation (RAG) for enterprise knowledge bases, focusing on the last 5 years and Q1/Q2 venues.
- Read your context and instructions
- Compiled the literature-discovery
Research clusters
| Cluster | Focus | Leading venues | Maturity |
|---|---|---|---|
| Retrieval architectures | Dense/sparse hybrid, late interaction | SIGIR, ACL, EMNLP | Mature |
| Enterprise grounding | Domain adaptation, access control | KDD, VLDB, ICML | Growing |
| Evaluation & benchmarking | RAG-specific metrics, human eval | ACL, TACL | Emerging |
| Long-context vs RAG | Context windows replacing retrieval | ICLR, NeurIPS | Hot |
Seminal papers
- Lewis et al. (2020) — Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (foundational)
- Karpukhin et al. (2020) — Dense Passage Retrieval
- Izacard & Grave (2021) — Fusion-in-Decoder
- Gao et al. (2023) — RAG survey + benchmarks (ACL)
- Asai et al. (2024) — Self-RAG / adaptive retrieval
Leading authors, datasets & metrics
- Institutions: Meta AI, Stanford, U. Waterloo, Berkeley, Tsinghua
- Datasets: Natural Questions, MS MARCO, KILT, HotpotQA, FinanceBench
- Metrics: EM/F1, recall@k, faithfulness, citation precision
Trend
Shift from "bigger retriever" toward
adaptive retrieval + factual-grounding evaluation, especially for private enterprise corpora.
Next steps
- Run
state-of-the-arton the 8 seminal papers for a narrative review. - Run
research-gapto confirm the evaluation gap before committing.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Starting a new research project and don't know where the field stands? This skill discovers and maps the scientific literature for any topic before you commit.
What it does:
- Searches recent publications (configurable 5–10 year window)
- Prioritizes Q1/Q2 journals and top conferences
- Identifies seminal papers and groups results into research clusters
- Detects trends and maps leading authors, institutions, datasets, tools, and metrics
What you get:
A structured literature map instead of an unstructured pile of PDFs, so you can see who's working on what, what's been done, and where the field is heading.
Why buy it:
It replaces hours of manual searching and reading with a ready-made expert workflow. Pair it with "state-of-the-art" and "research gap" to go from "I have a topic" to "I have a defensible contribution."
- Conducting a systematic literature review for a thesis or grant proposal.
- Onboarding a research team to a new technical domain or subfield.
- Identifying potential collaborators and high-impact venues for publication.
- Benchmarking new experimental results against established community datasets and metrics.
Known limitations
Initial search accuracy depends on the precision of the provided research topic and time window. The skill may have a language bias toward English-language publications, but I have tried with Spanish, and it worked very well too.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Requires specific research domain and time window inputs. Primary focus is on English-language publications and standard academic databases.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
19 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 2 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected