- Home
- Skills
- Technical Documentation
- related-work
Works with the AI Agents you already use
Related Work
Write a related-work section that positions your paper; thematic, gap-focused, and reviewer-ready.
$7
related-work
Example session with this skill installed
Use related-work to write the related work section, positioning my paper on RAG evaluation against existing retrieval and evaluation work.
- Read your context and instructions
- Compiled the related-work
Wrote a 3-subsection related work section of about 1.5 pages, positioning the contribution, an evaluation framework for RAG faithfulness, against retrieval, RAG, and evaluation literature.
Related Work (draft)
Retrieval-augmented generation
RAG (Lewis et al., 2020) combines a retriever with a generator to ground outputs in external evidence. Follow-up work improved the retriever (DPR, Karpukhin et al., 2020; late interaction, Khattab and Zaharia, 2020) and the integration strategy (FiD, Izacard and Grave, 2021; Self-RAG, Asai et al., 2024). These focus on the quality of retrieval, not on measuring whether the generated answer is faithful to the retrieved evidence.
Faithfulness evaluation
Existing metrics fall into two families: token-overlap heuristics (ROUGE, BERTScore) that correlate weakly with human judgment and LLM-as-judge approaches (G-Eval, RAGAS) that are prompt-sensitive and rarely calibrated. Prior benchmarks (KILT, FreshQA) measure answer correctness, not attribution to sources.
Gap and our contribution
There is no benchmark that jointly measures faithfulness and citation precision with calibrated, human-validated scoring. We close this gap by releasing a human-annotated evaluation suite and a calibrated metric.
Next steps
- Run
reference-checkerto validate all citations above. - Run
reviewerto confirm the positioning reads as differentiated, not dismissive.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
A related-work section that reads like an annotated bibliography tells reviewers you do not understand your field. Most drafts list papers one by one without synthesis, which buries your contribution and invites "insufficient differentiation" critiques. This skill writes one that positions you in the field.
What it does
- Synthesizes relevant work into thematic subsections.
- Identifies the gaps that motivate your contribution.
- Clearly differentiates your work without disparaging others.
- Organizes by method, problem, chronology, or gap, depending on what fits.
- Audits citations so the closest competitors and originators are covered.
Why this beats prompting it yourself
General prompts produce a laundry list of summaries, one paper after another. This skill groups papers into a narrative, adds a differentiation paragraph, and runs a citation coverage audit so reviewers cannot accuse you of missing key work.
Use cases
- Writing the related-work section for a specific paper.
- Condensing a broad state-of-the-art synthesis into a focused 1 to 2 page section.
- Ensuring the paper clearly differentiates itself from prior work.
- Avoiding common pitfalls such as laundry lists and missing key citations.
Known limitations
The output is only as good as the literature you provide; it cannot cite work you have not collected. It produces a focused section, not a comprehensive survey, and you should verify every citation with reference-checker.
Important
It positions your paper within the literature; it does not run the literature search for you. Feed it papers from literature-discovery or state-of-the-art, then validate citations with reference-checker.
Why buy it
Use it when writing the related-work section of a specific paper. It is the first step of the Write Pack: position the paper before you discuss, conclude, and abstract it.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.
Requires a pre-collected literature list or SOTA summary. Does not perform live web searches for new papers.
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
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
No special permissions declared or detected