Skip to content

DAAF-Contribution-Community/daaf / .claude/skills/scholarly-search

scholarly-search

Flagged

Searches and traces academic literature via DAAF's provenance CLI `bash /daaf/scripts/scholar_search.sh`, fusing OpenAlex, Semantic Scholar and ERIC (incl. EdWorkingPapers), merging paper versions, and saving raw responses, a fenced digest and a MANIFEST row for every call. Subcommands: citation verification (verify: catches fabricated references), forward/backward snowballing, more-like-this, passages inside OA papers, cached full text, legal OA copies and licenses (oa), retraction checks (Crossref/Retraction Watch, Scite notices), Scite citation-stance tallies (supporting/contradicting), and Elicit study-type-tagged search and paid async research reports (spend-gated). Use for literature reviews, finding papers or evidence on a question, checking that a citation exists, was retracted, or is supported or contradicted by later work, or locating an OA PDF. Strong for education and social science. Grey literature goes through the web-retrieval skill. NOT for dataset discovery (education-data-explorer).

references/licensing.md

View on GitHub
# Licensing, storage and attribution across backends

What may be stored, what may be shared, and what must be credited, per
backend. The tool enforces the storage split mechanically: every MANIFEST row
carries `license_class` (the most restrictive class among the backends the
command **selected** — the row's `backends_selected` — decided before any
request is sent, so a selected backend that then fails or is skipped still
sets the class; the one exception is split storage, below), and artifacts from `restricted` backends are written to
`lit_search/restricted/`, which is excluded from any shareable bundle and must
be named in the AI/data disclosure. Sources: vendor docs and terms pages fetched
from 2026-10-02 to 2026-10-28 (each backend's reference file names its docs and
the dates they were fetched).

**Split storage (`retractions`, tool 1.2.0).** `retractions` is the one
command whose digest holds facts only (status, notice DOIs, dates). When it
mixes restricted and open backends (by default OpenAlex + Crossref + Scite),
the restricted backends' raw responses go to `restricted/<base>.json` (row:
`restricted_raw_artifact`, `restricted_backends`, `restricted_storage`), the
open raw log and the digest stay in `lit_search/`, and the row's
`license_class` describes what stays in `lit_search/` (`open`). With only
restricted backends selected (`--skip openalex --skip crossref`) everything
goes to `restricted/` as usual; `--skip scite` keeps Scite out entirely.

## License classes

| Class | Meaning | Storage | Sharing |
|-------|---------|---------|---------|
| `open` | CC0 or "use for any purpose" metadata | `lit_search/` | Shareable with the project |
| `cc-by-nc` | Non-commercial with attribution | `lit_search/` | Research sharing with attribution; no commercial redistribution |
| `restricted` | Vendor terms bar redistribution or derived datasets | `lit_search/restricted/` | **Never** shared or bundled |

User-supplied PDFs are a separate, private class (`private`) handled
by the PDF layer: see the `pdf-reading` skill § Privacy.

## Matrix

| Backend | Class | Cache raw JSON? | OA PDFs | Attribution | Status |
|---------|-------|-----------------|---------|-------------|--------|
| OpenAlex | open | Yes — CC0, "no 'personal use only' carve-out" | Downloadable; "PDFs retain their original copyright" | Requested: Priem, Piwowar & Orr (2022), arXiv:2205.01833 | Built |
| Semantic Scholar | cc-by-nc | Yes, under S2 Data Licenses (the licenses that accompany the data, "such as CC BY-NC or ODC-BY") | Not via S2 | **Required**: credit "Semantic Scholar"; cite the Open Data Platform paper (arXiv:2301.10140) | Built |
| ERIC | open | Yes (U.S. federal metadata; abstracts may carry publisher rights) | `files.eric.ed.gov` PDFs: per-document rights | Courtesy: "ERIC, Institute of Education Sciences" | Built |
| Crossref | open | Yes — "use it for any purpose"; some abstracts copyrighted | n/a | Not required | Built |
| Unpaywall | open | Yes (same data as OpenAlex) | Points to PDFs that keep their own license | Not required | Built |
| arXiv (derived leg) | open | Metadata CC0 | Store and use "for research purposes"; no redistribution without the rights holder | — | Derived, no API call |
| **Scite** | restricted | **Restricted** (user decision 2026-10-11, "accepted for now"): Terms §8(b) bar storing, redistributing or making content (incl. Classifier Results = tallies) "or any dataset derived from it, available to any third party", keyless endpoints included. §8(c) also bars using that content "to train, fine-tune, evaluate or otherwise improve any machine learning or artificial intelligence model", and §4(v) allows Classifier Results only for "analyzing whether a scientific claim made in an Article has been supported or contradicted by subsequent Articles" (terms as fetched 2026-10-11; re-fetches on 2026-10-28 and 2026-10-30 answered HTTP 403, but a copy the user took from the live page on 2026-10-30 matches word for word). Keyless tallies and retraction notices on by default; `scite-search` behind `--ack-scite-license` (Pro key is "for evaluation"; research use of Search needs a separate license). `scite-tally`/`scite-search` artifacts all in `restricted/`; `retractions` splits (Scite raw in `restricted/`, facts-only digest open). The `tests/python/fixtures/scholar_search/scite_*.json` fixtures are synthetic (tool 1.4.0, 2026-10-12): live response shapes with invented values, no Scite content (see `scite.md`) | Not via Scite | No attribution clause; never remove author/licensor notices (§4(iii)) | Built |
| **Elicit** | restricted | "You may store and reuse API Outputs" (§3.5), but "You may not aggregate search results to build or contribute to a standalone search index, database, or corpus" (§3.5), and "you will delete any cached API Outputs within 30 days" of termination (§12.3). No submitting personal data, "includes names" (§2); no use of outputs "to train, fine-tune, evaluate, or improve any machine learning model or AI system" (§3.2(b)); outputs are non-deterministic (§4.2). Every `elicit-*` artifact is in `restricted/` (report bodies as `restricted/<base>_report.md`; presigned export links never leave it); the MANIFEST row holds counts, statuses and the sessionId only. Opt-in to `find` only. The `tests/python/fixtures/scholar_search/elicit_*.json` fixtures are synthetic (tool 1.4.0, 2026-10-12): the trial's response shapes with invented values, no Elicit output (see `elicit.md`) | `fullTextUrl` carries no license: never treated as OA (`oa` decides) | **Disclose AI generation** wherever a report or summary is used (§3.4); no citation clause | Built |

## Redistribution rule for papers

A PDF's license comes from its OA location (`oa` reports it). Share only
CC BY, CC BY-SA and CC0 items. Everything else — including "free to read"
publisher copies with no license (`license: unknown`) — is stored for private
research use and never redistributed.

## Attribution in deliverables

The literature-review deliverable's data-sources section must carry the
OpenAlex citation and the Semantic Scholar credit whenever those backends
contributed records (check `backends_selected` in MANIFEST rows). When any
part of an Elicit report (title, summary, abstract, body) is used, the
deliverable must disclose that it was AI-generated by Elicit (API Terms
§3.4), and the AI/data disclosure must name it. Elicit search hits are
bibliographic records: `verify` them and cite the papers themselves.
`bash /daaf/scripts/scholar_search.sh backends` prints each adapter's
attribution line to stdout, with or without a DEST_DIR (with one, the lines
are also in the digest).
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 198kUpdated Claude CodeCodexVerifiedInstall