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 Use for literature reviews, finding papers or evidence on a question, checking that a citation exists, was retracted, or is supported or contradicted by later work, or locating an OA PDF.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/crossref.md

View on GitHub
# Crossref

Keyless DOI metadata: the `verify` fallback and the main source of
retraction, correction and expression-of-concern notices (Retraction Watch
data, acquired by Crossref in 2023). Adapter:
`scripts/scholar_backends/crossref.py`. Docs fetched 2026-10-02: REST API overview
(https://www.crossref.org/documentation/retrieve-metadata/rest-api/), access and
authentication
(https://www.crossref.org/documentation/retrieve-metadata/rest-api/access-and-authentication/),
Retraction Watch
(https://www.crossref.org/documentation/retrieve-metadata/retraction-watch/).

## Auth

None required. Pools:

| Pool | How | Rate | Concurrency |
|------|-----|------|-------------|
| Public | nothing | 5 req/s | 1 |
| Polite | `mailto` param or User-Agent contact | 10 req/s | 3 |
| Plus | paid `Crossref-Plus-API-Token` | 150 req/s | none |

The tool uses the polite pool only when the user sets
`SCHOLARLY_CONTACT_EMAIL` (sent as `mailto`; replaced by
`[SCHOLARLY_CONTACT_EMAIL]` in logged params, raw artifacts, digests,
MANIFEST rows and printed lines).
Unset → public pool, with a one-line note. No address is hard-coded.

## Endpoints used

| Use | Request | Command |
|-----|---------|---------|
| DOI record | `GET /works/{doi}` | `verify`, `oa` (title), `retractions` |
| Title match | `GET /works?query.bibliographic=<title>&rows=5` | `verify title:"…"` |
| Topical search | `GET /works?query=<q>&rows` (+ `from-pub-date`/`until-pub-date`) | `find --backends …,crossref` |
| Notices updating a DOI | `GET /works?filter=updates:{doi}` | `retractions` |

## Cost and limits

Free. 429 when over the pool rate; 403 on a manual block. Headers
`x-rate-limit-limit`, `x-rate-limit-interval`, `x-concurrency-limit` (and
`x-api-pool` on Plus) are recorded in the MANIFEST cost field. The tool gates
the lane at 0.25 s container-wide (public pool, one at a time).

## Measured behavior (2026-10-02)

- **Retraction signals agree:** for the Wakefield 1998 Lancet paper
  (`10.1016/S0140-6736(97)11096-0`) both the work's `updated-by` list and
  `filter=updates:{doi}` returned the 2010 retraction
  (`10.1016/s0140-6736(10)60175-4`) and a 2004 correction, each with
  `source: retraction-watch`. The adapter de-duplicates by (notice DOI, type)
  and records every path that surfaced a notice (`via`). That merge came
  after this run, whose digest listed each notice once per path; the merged
  form (`via updated-by+updates-filter`) was confirmed in the 2026-10-11
  `retractions` run.
- For the QJE school-spending paper (`10.1093/qje/qjv036`) both signals were
  empty → status `none` ("no notice on record", not "sound").
- Abstracts arrive as JATS XML; the mapper strips tags.

## Retraction status values

`retraction_check` maps each notice's `type` through `UPDATE_KINDS` and
reports the most severe:

| Status | Notice types |
|--------|--------------|
| `retracted` | `retraction`, `withdrawal`, `removal` |
| `expression of concern` | `expression_of_concern` |
| `corrected` | `correction`, `erratum`, `corrigendum` |
| `updated` | at least one notice exists, but none of the kinds above (e.g. `addendum`, `new_version`) — read the notice; not a hard flag |
| `none` | no notice on record at Crossref (not proof the paper is sound) |

The mapper also marks a record `retracted` when the work's own `updated-by`
list carries a retraction-kind notice, so `verify` (Crossref fallback) and
`find --backends …,crossref` tag it "[RETRACTED per Crossref]". No such
notice leaves `retracted` unknown, never false.

## Storage and ToS

"almost none of the metadata is subject to copyright, and you may use it for
any purpose. Some abstracts … may be subject to copyright". Retraction Watch
data is publicly available through Crossref. `LICENSE_CLASS = "open"`; no
attribution required (courtesy credit is fine).

## Exit mapping

404 on `/works/{doi}` → NOT FOUND leg (verify continues/records it);
429/5xx after retries → 11; network → 4; timeout → 6.

## Minimal smoke test

```
bash /daaf/scripts/scholar_search.sh retractions '10.1016/S0140-6736(97)11096-0' {PROJECT_DIR}/lit_search   # expect RETRACTED
```
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