# 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.

- **Type:** Skill
- **Install:** `agentstack add skill-shikaijieskj-science-skills-science-reader`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [shikaijieskj](https://agentstack.voostack.com/s/shikaijieskj)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [shikaijieskj](https://github.com/shikaijieskj)
- **Source:** https://github.com/shikaijieskj/science-skills/tree/main/skills/science-reader

## Install

```sh
agentstack add skill-shikaijieskj-science-skills-science-reader
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## 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

1. Identify source type: PDF, DOI, publisher HTML, preprint, abstract, or pasted text.
2. Extract metadata: title, authors, journal, year, DOI, article type.
3. Build a paper map:
   `question -> gap -> approach -> main results -> figures -> limitations -> reuse`.
4. Place each figure/table near the section it supports.
5. Produce bilingual blocks only when source text is provided or lawful to use; otherwise produce
   Chinese explanation and concise paraphrase.
6. Finish with a claim-evidence table and discussion questions.

## Output contract

Use Markdown:

```text
# [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 prompts
```

If 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](https://github.com/shikaijieskj)
- **Source:** [shikaijieskj/science-skills](https://github.com/shikaijieskj/science-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-shikaijieskj-science-skills-science-reader
- Seller: https://agentstack.voostack.com/s/shikaijieskj
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.