Academic Researchv1.2.0
Find, read and summarise peer-reviewed papers and build a short cited literature review. Use when the user asks what the research says, wants papers on a topic, needs a literature review, or asks to evaluate a study's methods.
- Author
- Velonx
- License
- MIT
- Updated
- Sep 25, 2026
Overview
Search scholarly sources, screen papers by relevance and quality, and synthesise them into a literature review with proper citations and an honest read of the evidence.
When to Use
- "What does the research say about…", "find papers on…", "literature review of…"
- Evaluating a specific study ("is this paper any good?").
- Preparing background for a thesis, grant or technical decision.
Installation
velonx install academic-researchGet the skill folder
The skill isgit clone --depth 1 https://github.com/velonx/agent-skills.gitagent-skills/skills/academic-research/. Or open it on GitHub and download the files.Give SKILL.md to your agent as instructions
Add it to the system prompt, custom instructions or rules file your agent reads. Keep the rest of the folder next to it if the skill refers to examples or scripts.Ask for the task in your own words
The agent follows the skill when your request matches it. You can also name it: “use academic-research”.
Get the skill folder
The skill isgit clone --depth 1 https://github.com/velonx/agent-skills.gitagent-skills/skills/academic-research/. Or open it on GitHub and download the files.Claude Code: copy it into a skills folder
Usecp -R agent-skills/skills/academic-research ~/.claude/skills/.claude/skills/inside a project instead to share it with your team through git.Claude apps: upload it
Zip the folder and upload it under Settings → Capabilities → Skills.Ask for the task in your own words
The agent follows the skill when your request matches it. You can also name it: “use academic-research”.
Get the skill folder
The skill isgit clone --depth 1 https://github.com/velonx/agent-skills.gitagent-skills/skills/academic-research/. Or open it on GitHub and download the files.ChatGPT: add it to a GPT or project
PasteSKILL.mdinto the instructions, and upload files from the folder as knowledge if the skill uses them.API: send it as instructions
UseSKILL.mdas the system / developer message, or as agent instructions in your SDK.Ask for the task in your own words
The agent follows the skill when your request matches it. You can also name it: “use academic-research”.
Get the skill folder
The skill isgit clone --depth 1 https://github.com/velonx/agent-skills.gitagent-skills/skills/academic-research/. Or open it on GitHub and download the files.Gemini app: create a Gem
PasteSKILL.mdinto the Gem’s instructions.Gemini CLI or API
Add the contents to your project’sGEMINI.md, or pass it as thesystem_instructionin the API.Ask for the task in your own words
The agent follows the skill when your request matches it. You can also name it: “use academic-research”.
Get the skill folder
The skill isgit clone --depth 1 https://github.com/velonx/agent-skills.gitagent-skills/skills/academic-research/. Or open it on GitHub and download the files.Add it as a project rule
Create.cursor/rules/academic-research.mdcand paste the body ofSKILL.md. Use the skill’s description as the rule description so the agent applies it when relevant.Keep the folder in your repo
Only needed if the skill refers to examples or scripts.Ask for the task in your own words
The agent follows the skill when your request matches it. You can also name it: “use academic-research”.
Agents move these settings between versions — if a path doesn’t match, check your agent’s docs.
Usage
- Scope. Define the question, the time window and inclusion criteria (study type, population, field). Confirm with the user if unclear.
- Search scholarly indexes (Google Scholar, Semantic Scholar, PubMed, arXiv, SSRN — whichever fit the field). Use 2–3 query variants plus the key authors' names once you find them.
- Screen titles and abstracts. Keep 5–15 papers. Prefer systematic reviews and meta-analyses, then large or well-controlled studies.
- Read each kept paper's abstract, methods and results. For each record: design, sample size, main finding, effect size, limitations, funding/conflicts.
- Synthesise by theme, not paper by paper. Note where findings agree, conflict, or where evidence is thin.
- Output:
- One-paragraph summary of the state of evidence.
- Themed sections with in-text citations
(Author, Year). - A table: paper · design · n · finding · quality note.
- Reference list in the style the user asks for (default APA).
- Mark preprints as not peer-reviewed.
Examples
Prompt: "Summarise the research on spaced repetition for learning programming."
The agent finds reviews on the spacing effect, narrows to studies in computing education, builds a table of 8 papers, and concludes that evidence is strong for factual recall but limited for problem-solving skills.
Requirements & compatibility
Your agent needs
- Web access — search and open pages
Written for
Limitations
- Full text may be paywalled; the agent says when it only read the abstract.
- Never invents citations — if a reference can't be found again, it is dropped.
- Not a substitute for a formal systematic review.
Files
Changelog
- 1.2.0 — Preprints are now flagged explicitly; added quality-note column.
- 1.1.0 — Themed synthesis instead of per-paper summaries.
- 1.0.0 — Initial release.
Contributing
This skill lives in velonx/agent-skills. Improvements go through a pull request, reviewed by maintainers.