Science Reader
Build source-grounded Chinese-English readers, structured notes, and figure-aware study guides for Science/AAAS-family papers from PDFs, DOI pages, abstracts, publisher HTML, preprints, or pasted text. Use when the user asks to read, translate, or explain a Science paper, make a bilingual reader, create figure/table-aware Markdown, prepare journal-club notes, or extract claim-evidence structure.
Install
$ agentstack add skill-shikaijieskj-science-skills-science-reader ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-shikaijieskj-science-skills-science-reader) 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 Reader
Use this skill to help users understand a paper without collapsing it into a generic summary. Preserve source grounding and figure logic.
Chinese trigger examples include 中英文对照, 原文对照, and 全文翻译解读.
Defaults
- Do not invent text not present in the source.
- Do not provide full copyrighted article text unless the user supplied it and the use is allowed.
- For paywalled or inaccessible papers, work from accessible metadata, abstract, figures supplied by
the user, or open versions, and state the limitation.
- Keep figure/table placement near the relevant prose when possible.
- For Chinese users, explain scientific logic in Chinese while preserving technical terms.
Open extra files
| File | Open when | |---|---| | [references/output-spec.md](references/output-spec.md) | Need the Markdown reader structure | | [references/grounding-rules.md](references/grounding-rules.md) | Need source anchors, copyright limits, or figure/table handling |
Workflow
- Identify source type: PDF, DOI, publisher HTML, preprint, abstract, or pasted text.
- Extract metadata: title, authors, journal, year, DOI, article type.
- Build a paper map:
question -> gap -> approach -> main results -> figures -> limitations -> reuse.
- Place each figure/table near the section it supports.
- Produce bilingual blocks only when source text is provided or lawful to use; otherwise produce
Chinese explanation and concise paraphrase.
- Finish with a claim-evidence table and discussion questions.
Output contract
Use Markdown:
# [Title]
## Metadata
## One-sentence takeaway
## Paper map
## Section-by-section reader
## Figure and table guide
## Claim-evidence map
## Limitations and open questions
## Journal-club discussion promptsIf the user explicitly asks for full bilingual translation and provides the source PDF/text, preserve source anchors for every block.
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.