← 返回 Skills 市场

Academic Research Skip

Name: Academic Research Skip
Author: mmyg11

作者 mmyg11 · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ✓ 安全检测通过

157

总下载

当前安装

版本数

在 OpenClaw 中安装

/install academic-research-skip

功能描述

Search academic papers and conduct literature reviews using OpenAlex API (free, no key needed). Use when the user needs to find scholarly papers by topic/aut...

使用说明 (SKILL.md)

Academic Research

Search 250M+ academic works via OpenAlex. No API key required.

Built by Topanga — AI Research Consultant

Quick Start

Search papers by topic

python3 scripts/scholar-search.py search "transformer architectures" --limit 10

Search by author

python3 scripts/scholar-search.py author "Yann LeCun" --limit 5

Look up by DOI

python3 scripts/scholar-search.py doi "10.1038/s41586-021-03819-2"

Get citation chain (papers that cite a work)

python3 scripts/scholar-search.py citations "10.1038/s41586-021-03819-2" --direction both

Deep read (fetch abstract + full text when available)

python3 scripts/scholar-search.py deep "10.1038/s41586-021-03819-2"

JSON output for programmatic use

python3 scripts/scholar-search.py search "CRISPR" --json

Literature Review Workflow

Automated multi-step literature review:

python3 scripts/literature-review.py "algorithmic literacy in education" --papers 30 --output review.md

This will:

Search for papers across multiple query variations
Deduplicate and rank by relevance + citations
Identify thematic clusters
Generate a structured synthesis in markdown

Options:

--papers N — Target number of papers (default: 20)
--output FILE — Write review to file (default: stdout)
--years 2020-2025 — Restrict publication year range
--json — Output structured JSON instead of markdown

Output Format

All search commands return structured data per paper:

Title and publication year
Authors (up to 5)
Abstract (when available)
Citation count
DOI
Open access URL (when available)
Source journal/venue

Tips

OpenAlex sorts by relevance by default; use --sort citations for most-cited
Combine search + deep for quick triage: search first, deep-read promising hits
The literature review script caches results in /tmp/litreview_cache/ to avoid re-fetching
For full-text PDFs, pipe DOIs to your PDF extraction tool

安全使用建议

This skill appears to do what it says: run Python scripts that query OpenAlex (and optionally Unpaywall) and produce literature-review output. Before installing, ensure you have a Python runtime and the 'requests' library available (the manifest doesn't declare this dependency). Note the scripts will perform outbound network requests and include the hard-coded email ([email protected]) as the 'mailto' parameter to third-party APIs; if you prefer not to surface your queries with that contact, inspect/modify the MAILTO value in the scripts. The tool caches results under /tmp/litreview_cache — review or clear that cache if it will contain sensitive query info. Run the scripts in an isolated environment if you want to limit network or file access. Overall there are no requests for credentials or unexpected endpoints, and the functionality matches the description.

功能分析

Type: OpenClaw Skill Name: academic-research-skip Version: 1.0.1 The skill provides legitimate tools for academic research and literature synthesis using the OpenAlex and Unpaywall APIs. The Python scripts (scripts/scholar-search.py and scripts/literature-review.py) implement standard API interaction patterns, including the recommended 'polite pool' mailto parameter and local disk caching in /tmp. No evidence of data exfiltration, malicious execution, or prompt injection was found; the code logic strictly aligns with the stated purpose in SKILL.md.

能力评估

ℹ Purpose & Capability

The scripts and SKILL.md implement OpenAlex-based search and a literature-review pipeline as advertised. Minor inconsistencies: the package/registry metadata claims 'instruction-only' with no install spec, but this bundle includes Python scripts that require the 'requests' library and a Python runtime. That missing dependency declaration is a bookkeeping issue but does not change the skill's purpose.

✓ Instruction Scope

Runtime instructions and the Python code only perform searches against api.openalex.org and (optionally) api.unpaywall.org, parse results, cluster themes, and write a local cache under /tmp/litreview_cache. The code does not read other system files, environment variables, or call arbitrary external endpoints beyond OpenAlex/Unpaywall. It also does not exfiltrate secrets or request unrelated data.

ℹ Install Mechanism

No install spec is provided (lowest-risk install model). However, the shipped scripts require Python and the third-party 'requests' package; these requirements are not declared in the manifest. This is an operational omission (user/agent must have Python + requests available) rather than an active security risk.

✓ Credentials

The skill requests no environment variables or credentials. The only notable constant is a built-in MAILTO ([email protected]) used as a polite parameter to OpenAlex/Unpaywall; this means queries will include that email but does not expose any user secrets or require tokens.

✓ Persistence & Privilege

always is false and the skill does not request persistent privileged presence. It writes cache files to /tmp/litreview_cache (local, non-privileged) and does not modify other skills or system-wide settings.

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 academic-research-skip
安装完成后，直接呼叫该 Skill 的名称或使用 /academic-research-skip 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

v1.0.1

- Metadata file updated; no changes to functionality or user-facing documentation. - Version incremented to 1.0.1.

v1.0.0

- Initial release of academic-research skill. - Search 250M+ academic papers using the OpenAlex API without an API key. - Supports paper search by topic, author, or DOI; citation chain exploration; and deep reading for abstracts and full texts (when available). - Provides structured metadata including title, authors, abstract, citation count, DOI, open access URL, and source. - Features an automated literature review workflow with thematic clustering and synthesis. - Outputs results in markdown or JSON for programmatic use.

元数据

Slug academic-research-skip

版本 1.0.1

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 2

常见问题