Priorwork: agent-assisted social-science literature reviews

Repository-documented toolkit for social-science literature reviews using an external AI agent, with CLI and VS Code interfaces. It documents literature searching, screening with reasons, citation chasing, evidence cards and report export.

Workflow level n/a Source Repository-documented Outcome Not empirically evaluated here

Evidence & verification

Source level

Repository-documented
Grounded in a maintainer repository/README. Availability, stars and forks do not establish research benefit or correctness.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-17 (UTC)

Primary README-only source-semantic review. Capability assertions attributed to documentation; not-evaluated describes the adopted outcome claims, not an assertion the authors never evaluated their tool.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (1)

Research applicability

Getting started

Editorial suggestion, not executed: read the README setup, create a private workspace, define a narrow review question and check every inclusion reason and evidence card before reusing an exported report.

Maintenance

Live mutable HEAD README reviewed; no pinned release/commit or maintenance guarantee.

License

README states MIT; separate licence file not audited.

Workflow & human oversight

Resource-level automation varies; no fixed workflow level assigned. Researchers define criteria, oversee data access and validate outputs. AI roles are not human editorial review.

Workflow level is not an evidence score; higher is not better evidence.

Approach

The README describes Semantic Scholar searches, OpenAlex metadata checks and citation links, persisted survey JSON and researcher corrections in a sidebar. Standard mode pauses for scope approval and before paper cards; full-auto and manual modes are alternatives.

Limitations

README-only review; no software run or research outcomes reproduced. Citation checks are pattern-based, not proof of claim truth. Database coverage excludes some domestic journals; SSCI status may be guessed without the licensed list. Abstract-only cards and unavailable full texts limit inference. Keep abstracts and manuscripts private, protect keys and respect text/database rights and the external agent provider policy.

Reproducibility

Source content saved and hashed; no install, execution or independent outcome experiment.

Adoption requirements

Python 3.10+ or the extension-managed Python environment; an external AI agent and its terms/costs; Git for the documented private-workspace workflow. Semantic Scholar API key recommended; Zotero and licensed SSCI data optional.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.