← Back to Skills Marketplace
lyt0302

文献助手

by lyt0302 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
125
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install literature-helper
Description
literature retrieval and single-pdf analysis for academic research. use when the user asks to find papers by topic, author, keyword, or latest papers in the...
README (SKILL.md)

\r \r

Literature Helper\r

\r

Literature retrieval\r

\r When the user asks for literature on a topic, author, keyword, research field, or latest papers:\r \r

  1. Identify:\r
    • topic\r
    • optional author\r
    • optional time range\r
    • optional language preference\r \r
  2. If the user asks for "latest literature" but gives no time range, default to the last 5 years.\r \r
  3. Generate:\r
    • Chinese keywords\r
    • English keywords\r
    • 2 to 4 useful search strings\r \r
  4. Search for relevant papers and return a structured result list.\r \r
  5. For each result, include:\r
    • title\r
    • authors\r
    • year\r
    • source or journal\r
    • one-sentence summary\r
    • link\r
    • availability label:\r
      • open access\r
      • repository pdf\r
      • abstract only\r
      • availability unconfirmed\r \r
  6. Never claim full-text availability unless it is actually confirmed.\r \r

Single PDF analysis\r

\r When the user uploads one PDF:\r \r

  1. Extract:\r
    • title\r
    • keywords\r
    • research question\r
    • methods\r
    • data or materials\r
    • main findings\r
    • conclusion\r
    • limitations\r \r
  2. Then give a clear Chinese summary unless the user asks for another language.\r \r
  3. If the user asks questions about the PDF:\r
    • answer primarily from the PDF\r
    • if the answer is not found in the PDF, say clearly that it was not found in the document\r
    • do not invent details\r \r

Output style\r

\r For literature retrieval, use:\r \r

Search terms\r

  • Chinese:\r
  • English:\r
  • Suggested search strings:\r \r

Results\r

  1. Title\r
    • Authors:\r
    • Year:\r
    • Source:\r
    • Summary:\r
    • Link:\r
    • Availability:\r \r For PDF analysis, use:\r \r

Basic information\r

Keywords\r

Research question\r

Methods\r

Data or materials\r

Main findings\r

Conclusion\r

Limitations\r

Answers to user questions\r

\r

Reliability rules\r

\r

  • Be explicit about uncertainty.\r
  • Never fabricate paper links, authors, journals, or availability.\r
  • Distinguish clearly between:\r
    • open access direct pdf\r
    • repository version\r
    • abstract page only\r
    • unconfirmed access
Usage Guidance
This skill appears coherent and low-risk: it needs no secrets or installs. Before enabling, confirm the agent environment actually provides web-search/browsing and PDF parsing (so the skill can find papers and read uploaded PDFs). Be cautious about uploading PDFs that contain sensitive or unpublished data, and always manually verify any paper links, availability labels, and extracted facts (LLMs can still hallucinate despite the 'do not invent' instruction). If you need searches to come from a specific source (e.g., Google Scholar, Semantic Scholar, arXiv, institution subscriptions), verify or configure which tool or API the agent will use.
Capability Analysis
Type: OpenClaw Skill Name: literature-helper Version: 1.0.0 The literature-helper skill bundle consists solely of metadata and markdown instructions for an AI agent to assist with academic research and PDF summarization. It contains no executable code, no network-related logic, and no instructions that attempt to exfiltrate data or bypass security controls. The instructions in SKILL.md specifically emphasize reliability and the prevention of data fabrication.
Capability Assessment
Purpose & Capability
Name and description (literature retrieval and single-PDF analysis) match the SKILL.md. However, the instructions assume the agent can perform web searches and fetch/confirm full-text PDFs and can parse uploaded PDFs; those capabilities are not declared in the skill metadata (no required tools or env). This is a functional gap rather than a security mismatch, but the user should confirm the agent has appropriate search/browsing and file-processing tools.
Instruction Scope
SKILL.md stays on task: it instructs how to build bilingual search strings, return structured search results, label availability, and to extract/analyze content from a single uploaded PDF. It does not direct the agent to read unrelated files, environment variables, or to transmit data to external endpoints beyond normal searching/fetching. It explicitly discourages fabrication.
Install Mechanism
No install spec and no code files — instruction-only skill (lowest install risk). Nothing is downloaded or written to disk by the skill itself.
Credentials
No required environment variables, credentials, or config paths are requested — proportional to the described functionality.
Persistence & Privilege
always is false and the skill does not request elevated or persistent privileges or modifications to other skills. Default autonomous invocation is allowed (normal for skills) but not combined with other concerning factors.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install literature-helper
  3. After installation, invoke the skill by name or use /literature-helper
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Literature skill v1.0.0 – Initial release with focused academic research tools: - Enables literature retrieval by topic, author, keyword, or time range, including Chinese and English search terms. - Returns structured results with title, authors, year, journal, summary, link, and clear availability status. - Provides detailed single PDF analysis: extracts and summarizes key information, answering user questions based only on the document. - Never fabricates paper details or full-text links; explicitly indicates access level and uncertainties.
Metadata
Slug literature-helper
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is 文献助手?

literature retrieval and single-pdf analysis for academic research. use when the user asks to find papers by topic, author, keyword, or latest papers in the... It is an AI Agent Skill for Claude Code / OpenClaw, with 125 downloads so far.

How do I install 文献助手?

Run "/install literature-helper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 文献助手 free?

Yes, 文献助手 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 文献助手 support?

文献助手 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 文献助手?

It is built and maintained by lyt0302 (@lyt0302); the current version is v1.0.0.

💬 Comments