aipoch/open-science / resources/skills/literature-review
literature-review
VerifiedFind, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.
| File | Kind | Size |
|---|---|---|
| .catalog_stamp | other | 13 B |
| SKILL.md | skill md | 12.4 KB |
| kernel.py | script | 21.3 KB |
| kernel.test.ts | script | 685 B |
| test_kernel.py | script | 2.8 KB |
test_kernel.py
View on GitHubimport time
import unittest
from unittest.mock import patch
from kernel import extract_dois, verify_dois
class VerifyDoisRetractionTests(unittest.TestCase):
def test_retraction_markers_and_non_retraction_updates(self) -> None:
cases = [
({"updated-by": [{"type": "expression_of_concern"},
{"type": "retraction", "DOI": "10.1126/science.1124926"}]}, True),
({"updated-by": [{"type": "retraction", "source": "publisher"},
{"type": "retraction", "source": "retraction-watch"}]}, True),
({"updated-by": [{"type": "Retraction"}]}, True),
({"updated-by": [{"type": "correction"}]}, False),
({"updated-by": [{"type": "expression_of_concern"}]}, False),
({"updated-by": [{}]}, False),
({"updated-by": None, "update-to": None}, False),
({}, False),
({"update-to": [{"type": "retraction"}]}, True),
({"subtype": "retraction"}, True),
({"title": ["RETRACTED ARTICLE: Example"]}, True),
]
doi = "10.1126/science.1112286"
for fields, expected in cases:
with self.subTest(fields=fields), \
patch("kernel.litrev_get", return_value={"message": {
"title": ["Example"], **fields
}}) as fetch, \
patch("kernel.litrev_head") as head, \
patch("kernel.time.sleep"):
result = verify_dois([doi])[doi]
self.assertIs(result["retracted"], expected)
self.assertIs(result["ok"], True)
self.assertEqual(result["registry"], "crossref")
fetch.assert_called_once()
head.assert_not_called()
def test_resolver_fallback_keeps_unknown_retraction_status(self) -> None:
for status, ok in [(302, True), (None, None)]:
with self.subTest(status=status), \
patch("kernel.litrev_get", return_value=None), \
patch("kernel.litrev_head", return_value=status), \
patch("kernel.time.sleep"):
result = verify_dois(["10.1234/example"])["10.1234/example"]
self.assertIs(result["ok"], ok)
self.assertIsNone(result["retracted"])
class ExtractDoisTests(unittest.TestCase):
def test_strips_trailing_markdown_emphasis(self) -> None:
self.assertEqual(extract_dois("**10.1234/foo**"), ["10.1234/foo"])
def test_rejecting_a_long_markdown_like_suffix_stays_fast(self) -> None:
candidate = "10.1234/" + "*" * 8_000 + "A"
started = time.monotonic()
result = extract_dois(candidate)
elapsed = time.monotonic() - started
self.assertEqual(result, [candidate])
self.assertLess(elapsed, 0.25)
if __name__ == "__main__":
unittest.main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |