← 返回 Skills 市场

Literature Review

Name: Literature Review
Author: jirboy

作者 JIRBOY · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install literature-review-cn

功能描述

Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user need...

使用说明 (SKILL.md)

Literature Review

Help write academic literature reviews using a multi-engine search integration (S2, OA, CR, PM).

Capabilities

Multi-Source Search: Find relevant academic papers using Semantic Scholar (S2), OpenAlex (OA), Crossref (CR), and PubMed (PM).
Full Abstracts: All sources now return complete abstracts (PubMed uses efetch for full XML records).
DOI Extraction: DOIs are extracted from all sources for cross-referencing and deduplication.
Automatic Deduplication: When searching multiple sources (--source all or --source both), results are automatically deduplicated by DOI.
Polite Access: Automatic email identification for OpenAlex/Crossref "Polite Pool" (via USER_EMAIL env var).
Abstract Reconstruction: Reconstructs abstracts from OpenAlex inverted index format.
Synthesis: Group papers by theme and draft review sections based on metadata.

Environment Variables

Variable	Purpose	Default
`USER_EMAIL`	Email for polite API access	`[email protected]`
`CLAWDBOT_EMAIL`	Fallback if USER_EMAIL not set	—
`SEMANTIC_SCHOLAR_API_KEY`	Optional S2 API key for higher rate limits	—
`OPENALEX_API_KEY`	Optional OpenAlex API key	—

Workflows

1. Broad Search (All Bases)

Get a comprehensive overview from all major academic databases. Results are automatically deduplicated by DOI.

python3 scripts/lit_search.py search "impact of glycyrrhiza on bifidobacterium" --limit 5 --source all

2. Targeted Search

OpenAlex (oa): Fast and comprehensive, good abstracts.
Semantic Scholar (s2): High-quality citation data and TL;DRs.
Crossref (cr): Precise DOI-based metadata (no abstracts).
PubMed (pm): Gold standard for biomedical research, full abstracts and PMIDs.

python3 scripts/lit_search.py search "prebiotic effects of liquorice" --source pm

3. Comparing Sources

Search both S2 and OA simultaneously to ensure nothing is missed. Deduplicated by default.

python3 scripts/lit_search.py search "Bifidobacterium infantis growth" --source both

4. Getting Full Details (S2)

Retrieve detailed metadata including TL;DR summaries.

python3 scripts/lit_search.py details "DOI:10.1016/j.foodchem.2023.136000"

5. Writing the Review

Extract: Pull key findings from the abstracts found.
Organize: Group findings into a logical structure (e.g., chronological or thematic).
Draft: Use the "Think step-by-step" approach to synthesize multiple sources into a coherent narrative.

Output Format

Each result includes:

id: Source-specific identifier (PMID for PubMed, OpenAlex ID, S2 paper ID, DOI for Crossref)
doi: DOI when available (used for deduplication)
title: Paper title
year: Publication year
authors: List of author names
abstract: Full abstract text (when available)
venue: Journal or conference name
citationCount: Citation count (S2, OA)
source: Which database the result came from

Tips for Success

Citations: Always cross-reference the DOI or PMID for accuracy in bibliography.
Filtering: Focus on papers with higher citationCount or recent years for a more modern review.
PubMed for Medicine: Use --source pm for the most reliable biomedical literature.
Deduplication: Multi-source searches automatically remove duplicates; use single sources if you need raw counts.

安全使用建议

This skill appears to do what it says: run a Python script to query Semantic Scholar, OpenAlex, Crossref, and PubMed. Before installing or running it: (1) verify the publisher/owner and resolve the version/ownerId mismatch between the registry and the included _meta.json/SKILL.md; (2) inspect the included scripts locally (they are short and readable) to be comfortable with network calls; (3) if you provide API keys or an email, prefer throwaway or rate-limited keys and avoid reusing high-privilege credentials; (4) run the script in an isolated environment (container or VM) if you have any doubt; (5) if you need higher assurance, ask the publisher to explain the metadata/version mismatch or provide a signed release.

功能分析

Type: OpenClaw Skill Name: literature-review-cn Version: 1.0.0 The skill bundle is a legitimate academic research tool designed to search and synthesize literature from Semantic Scholar, OpenAlex, Crossref, and PubMed. The Python script (scripts/lit_search.py) uses standard HTTP requests to interact with official academic APIs and includes proper deduplication logic. No evidence of malicious intent, data exfiltration, or prompt injection was found; the use of environment variables for API keys and email identification follows standard practices for these services.

能力标签

requires-sensitive-credentials

能力评估

ℹ Purpose & Capability

The name/description (literature review via Semantic Scholar, OpenAlex, Crossref, PubMed) align with the included Python script and SKILL.md which call those APIs and perform deduplication and synthesis. However, there are packaging/metadata inconsistencies: registry metadata/version (1.0.0, owner kn7024...) differs from SKILL.md/_meta.json (version 1.2.0, owner kn70465...), and the skill lists optional env vars in SKILL.md though the registry lists 'required env vars: none'. These mismatches are not proof of maliciousness but are unexpected and should be verified with the publisher.

✓ Instruction Scope

Runtime instructions only direct the agent to run the provided script to query the declared external APIs. The script only reads a few environment variables (SEMANTIC_SCHOLAR_API_KEY, OPENALEX_API_KEY, USER_EMAIL/CLAWDBOT_EMAIL) and does not access unrelated local files, system credentials, or arbitrary endpoints. No ambiguous 'gather whatever context you need' directives are present.

✓ Install Mechanism

No install spec is provided (instruction-only plus a script file). That is low risk compared to downloadable installers. The included Python script uses the requests library but there is no automatic package installation specified.

ℹ Credentials

The script optionally uses API keys and an email for polite API usage; these env vars are proportional to the stated purpose. It does not require high-privilege or unrelated credentials. Still, be cautious before supplying any API keys or an email—use keys with limited scope and avoid sharing secrets you need elsewhere.

✓ Persistence & Privilege

The skill is not always-enabled (always: false), does not request to modify other skills, and does not persist new credentials or change system settings. It appears not to require elevated or persistent privileges.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install literature-review-cn
安装完成后，直接呼叫该 Skill 的名称或使用 /literature-review-cn 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Version 1.2.0 adds major improvements for writing literature reviews with multi-database search support. - Now searches Semantic Scholar, OpenAlex, Crossref, and PubMed, with automatic DOI-based deduplication across sources. - Fetches full abstracts from all sources (including complete records from PubMed). - Polite API access supported via configurable email; optional API keys for higher rate limits. - Results are grouped, organized, and can be synthesized into review sections with metadata and citations. - Supports targeted, broad, and comparative searches, plus DOI-based detail retrieval.

元数据

Slug literature-review-cn

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题