Skip to content

LeoYeAI/agent-master-skills / skills/ai-powered-literature-review-skills

literature-reviewer-skill

Unverified

根据用户提供的论文主题,进行系统性中英文文献回顾(Literature Survey)。 采用8阶段工作流,支持CNKI、Web of Science、ScienceDirect等主流数据库, 无需API配置,通过浏览器自动化获取文献信息。 输出包含GB/T 7714-2015引文、标题、摘要的Markdown文档。 当用户提到"文献回顾"、"文献综述"、"帮我找文献"、"中英文文献搜索"、"写综述"等关键词时触发。 NOTE: The 'examples/' folder contains sample outputs and is not included in skill installation.

FileKindSize
AGENTS.mdmarkdown12.8 KB
README.mdmarkdown19.7 KB
SECURITY.mdmarkdown5.1 KB
SKILL.mdskill md22.1 KB
_meta.jsonconfig316 B
agents/explore-agent.mdmarkdown4.2 KB
agents/orchestrator.mdmarkdown17.3 KB
agents/synthesize-agent.mdmarkdown12.4 KB
agents/verify-agent.mdmarkdown2.3 KB
docker-compose.ymlconfig3.3 KB
install.yamlconfig2.6 KB
mcp.jsonconfig5.6 KB
references/cnki-guide.mdmarkdown10.0 KB
references/database-access.mdmarkdown3.1 KB
references/gb-t-7714-2015.mdmarkdown10.8 KB
scripts/__init__.pyscript519 B
scripts/citation_formatter.pyscript5.3 KB
scripts/deduplicate_papers.pyscript4.8 KB
scripts/models.pyscript2.6 KB

install.yaml

View on GitHub
# Literature Reviewer Skill - 安装配置
# 明确声明依赖和安装要求

name: literature-reviewer-skill
version: 3.1.0
description: 系统性学术文献回顾(Literature Survey)Skill

# 必需的依赖技能
required_skills:
  - name: browser
    version: ">=1.0.0"
    description: 浏览器自动化(Playwright)
    required: true
    reason: 用于访问 CNKI、Web of Science 等数据库
    
  - name: web_search
    version: ">=1.0.0"
    description: 网页搜索
    required: false
    reason: 辅助获取文献信息(可选)
    
  - name: docx
    version: ">=1.0.0"
    description: Word 文档处理
    required: false
    reason: 生成 .docx 格式综述(可选)

# 运行时依赖
runtime_dependencies:
  system:
    - python3
    - nodejs
    - git
    
  python_packages:
    - name: playwright
      version: ">=1.40.0"
      reason: 浏览器自动化控制
      
  node_packages:
    - name: playwright
      version: ">=1.40.0"
      reason: 浏览器驱动

# 权限声明
permissions:
  filesystem:
    read:
      - ./agents/
      - ./references/
      - ./scripts/
      - ./examples/
    write:
      - ./sessions/
      - ./output/
      
  network:
    allowed_hosts:
      - kns.cnki.net
      - www.webofscience.com
      - www.sciencedirect.com
      - scholar.google.com
      - pubmed.ncbi.nlm.nih.gov
      - api.crossref.org
      - doi.org
      
  browser:
    actions:
      - navigate
      - click
      - fill_form
      - evaluate
      - screenshot
      - download
    restrictions:
      - "不允许访问 file:// 协议"
      - "不允许访问 localhost/127.0.0.1"
      - "仅允许访问声明的网络域名"

# 安全配置
security:
  sandbox:
    recommended: true
    docker_support: true
    
  network_isolation:
    recommended: true
    
  resource_limits:
    cpu: "2.0"
    memory: "4G"
    max_downloads_per_session: 50
    max_concurrent_browsers: 1

# 安装步骤
installation:
  method: git_clone
  url: https://github.com/stephenlzc/AI-Powered-Literature-Review-Skills.git
  target_dir: literature-reviewer-skill
  
  pre_install:
    - "检查 browser skill 是否已安装"
    - "检查 Playwright 是否已安装"
    
  post_install:
    - "创建 sessions 目录"
    - "创建 output 目录"
    - "设置目录权限"
    
  verify:
    - "检查 SKILL.md 是否存在"
    - "检查 agents/ 目录是否存在"
    - "测试 browser skill 可用性"

# 更新配置
updates:
  auto_check: true
  channel: stable

# 作者信息
author:
  name: stephenlzc
  github: https://github.com/stephenlzc
  
# 许可证
license: MIT-0
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall