Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tsinghua-fib-lab/agentsociety-literature-search
Use when academic literature needs to be gathered or refreshed for a research topic, especially at the beginning of a project.
7 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 7 comparable cases; this report requires 8.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
In `papers/literature_index.json`, where should the primary `file_path` field point, and where should the PDF file path be stored?
| Checked | Without skill | With skill |
|---|---|---|
| Points top-level file path to markdown document | Passed | Passed |
| Places PDF path inside extra_fields full_text file_path | Missed | Passed |
The instructions your model reads when the skill loads.
Search academic literature through the academic literature search gateway (MCP) and save results to the workspace papers/ directory. Queries all configured data sources (local, arXiv, CrossRef, OpenAlex) by default.
The runtime connects via MCP using workspace .env only. You do not need Claude mcp.json for this skill.
| Need | Where |
|---|---|
| Topic / keyword search across sources | This skill (literature-search) — requires MCP key |
| Open-access PDF helpers for search hits | This skill (literature-full-text) |
| Upload PDF/MD, paste DOI/arXiv, sync metadata, BibTeX import/export | VS Code extension literature library UI (public APIs + local files; no MCP) |
Do not reimplement DOI paste / local upload / Bib sync with this skill.
TOPIC.md does not yet existTOPIC.md needs enrichment with more referencespapers/literature_index.json via searchDo NOT use when:
Use the Python interpreter from .env. See CLAUDE.md for setup.
Run commands from the workspace root through .agentsociety/bin/ags.py.
| Action | Command |
|---|---|
| Basic search | $PYTHON_PATH .agentsociety/bin/ags.py literature-search "query" |
| Year range | $PYTHON_PATH .agentsociety/bin/ags.py literature-search "query" --year-from 2020 --year-to 2024 |
| Complex topic | $PYTHON_PATH .agentsociety/bin/ags.py literature-search "complex query" --multi-query |
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.