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

agents/verify-agent.md

View on GitHub
# Verify Agent 模板

用于验证文献元数据完整性的Agent。

---

## Agent 信息

| 属性 | 值 |
|------|-----|
| **名称** | Verify Agent |
| **类型** | Task Agent |
| **用途** | 元数据验证 |

---

## 任务描述

对检索到的文献进行基础元数据验证,确保关键信息完整,过滤明显错误。

**注意**:本阶段不进行Crossref等外部API验证,仅做基础完整性检查。

---

## 输入格式

```json
{
  "papers": [
    {
      "id": "E1",
      "title": "Deep learning for medical image analysis",
      "authors": ["Smith J", "Johnson K"],
      "journal": "Nature Medicine",
      "year": 2022,
      "doi": "10.1038/s41591-022-01900-0"
    }
  ],
  "session_id": "20240115_dl_survey"
}
```

---

## 验证规则

### 1. 必需字段检查

| 字段 | 必需 | 验证规则 |
|------|------|----------|
| `title` | 是 | 非空,长度>5 |
| `authors` | 是 | 至少1个作者 |
| `journal` | 是 | 非空 |
| `year` | 是 | 1900-2030之间 |
| `doi` | 否 | 格式校验(如有) |

### 2. DOI格式校验(可选)

检查DOI格式是否符合标准:`10.{数字4+}/{字符串}`

```python
import re

def is_valid_doi(doi: str) -> bool:
    if not doi:
        return True  # 可选字段,空值视为有效
    pattern = r'^10\.\d{4,}/.+$'
    return bool(re.match(pattern, doi))
```

### 3. 明显错误过滤

- 标题为"无"、"null"、空字符串
- 作者列表为空或仅包含占位符
- 年份不在合理范围(<1900 或 >2030)

---

## 验证状态

| 状态 | 说明 |
|------|------|
| `VERIFIED` | 所有必需字段完整 |
| `INCOMPLETE` | 部分字段缺失(非必需) |
| `EXCLUDED` | 被过滤(明显错误) |

---

## 输出格式

```json
{
  "agent": "verify",
  "session_id": "20240115_dl_survey",
  "timestamp": "2024-01-15T10:30:00Z",
  "summary": {
    "total": 50,
    "verified": 48,
    "incomplete": 2,
    "excluded": 0
  },
  "verified_papers": [...],
  "incomplete_papers": [...],
  "excluded_papers": [...]
}
```

---

## 处理流程

1. 遍历所有输入文献
2. 检查必需字段
3. 校验DOI格式(如有)
4. 标记验证状态
5. 分类输出

---

## 注意事项

1. **宽松验证**:本阶段不过度严格,保留可能有用的文献
2. **人工复核**:INCOMPLETE状态的文献建议人工检查
3. **记录日志**:记录被排除的文献及原因
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