Install
$ agentstack add skill-shikaijieskj-science-skills-science-citation ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Science Citation
Use this skill to turn manuscript claims into defensible citation candidates. It is a search and verification workflow, not a license to invent support.
Chinese request patterns such as "find citations", "add supporting references", and "Science-series references" should be treated as citation-support tasks.
Default scope
Default journals:
ScienceScience AdvancesScience ImmunologyScience RoboticsScience SignalingScience Translational Medicine
Keep the default retrieval scope focused on Science-family journals. If the user explicitly asks for a wider literature search, use general academic-search tools and label the broader scope separately from this Science-family citation workflow.
Open extra files
| File | Open when | |---|---| | [references/journal-scope.md](references/journal-scope.md) | Need exact journal-family boundaries or scope labels | | [references/search-strategy.md](references/search-strategy.md) | Need to convert claims into search queries and support grades | | [references/ris-endnote.md](references/ris-endnote.md) | Need RIS/EndNote export rules | | [scripts/sciencecitation.py](scripts/sciencecitation.py) | Need a quick candidate search/export using OpenAlex and Crossref |
Workflow
- Split the user's text into citable claims.
- For each claim, identify:
topic, mechanism, system, evidence type, date window, and journal scope.
- Search authoritative sources in this order:
- publisher page or DOI metadata for known references
- Crossref / OpenAlex for broad DOI discovery
- PubMed for biomedical claims
- Semantic Scholar or Google Scholar only as secondary discovery
- Filter by journal scope, year, article type, title relevance, and DOI reliability.
- Assign support grade:
direct: the paper directly supports the claimpartial: same topic but narrower, broader, or different systembackground: useful context but not enough for the claimreject: not suitable
- Return a claim-reference map with DOI links and uncertainty notes.
- Export RIS/EndNote if requested.
Script quick start
When internet access is available:
python scripts/science_citation.py --claim "perovskite solar cells ligand charge extraction stability" --rows 8 --out science_refs.ris
The script queries OpenAlex for natural-language recall and Crossref for DOI metadata fallback. It is a candidate finder. Always read titles/abstracts or source pages before declaring that a reference directly supports a manuscript claim.
Output format
Claim-reference map
| Claim | Candidate reference | Journal | Year | DOI | Support grade | Note |
Export
- [path if created, otherwise "Not requested"]
Search caveats
- [rate limits, inaccessible pages, weak support, or "None"]
For Chinese users, write the final map in Chinese unless the citation strings or manuscript text need English.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: shikaijieskj
- Source: shikaijieskj/science-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.