Humanities Skills — scholarly retrieval and human evaluation

Research applicability

Repository documentation describes AI-assistant skills for East Asian historical data, library and scholarly retrieval, with a separately documented human-evaluation builder for reviewing model matches and corrections. This supports an intended humanities-research workflow, not verified database coverage or demonstrated scholarly accuracy.

Getting started

Read the retained primary snapshot and its limitations first. Any suggested installation/provider/database use is untested and requires separate authorization.

Maintenance

Snapshot checked 2026-10-20; ongoing maintenance and version parity were not established.

License

License statements were not separately audited; source access is not reuse clearance.

Workflow & human oversight

L2 for this documented use: An AI assistant uses documented retrieval or analysis skills to propose results; a self-contained review file lets a scholar confirm, correct or score items and export judgments as JSON. Human control: The human-evaluation instructions explicitly require a person to review proposed matches, corrections or scores before trusting results, with JSON export and resumable decisions. Boundary: README and human-eval-review v1.0.0 instructions were read as source data, never invoked. API coverage and counts were not tested. The linked archival-entity-linking/SKILL.md returned 404 and was not retried; its detailed implementation is not asserted from the catalogue line alone.

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

Approach

An AI assistant uses documented retrieval or analysis skills to propose results; a self-contained review file lets a scholar confirm, correct or score items and export judgments as JSON.

Outcomes (as reported by the originating team)

No empirical research benefit is established by this documentary review.

Limitations

README and human-eval-review v1.0.0 instructions were read as source data, never invoked. API coverage and counts were not tested. The linked archival-entity-linking/SKILL.md returned 404 and was not retried; its detailed implementation is not asserted from the catalogue line alone.

Reproducibility

Primary-source documentation was read, with source snapshots and hashes retained. No candidate code, skill, model, experimental system or claimed outcome was executed or reproduced.

Adoption requirements

Untested editorial suggestion: inspect the exact sources and select a bounded authorized task; check data rights, provider terms and outputs before relying on them. No installation or trial was run.