lit-review

文献综述

围绕给定主题开展结构化文献检索与综述。

输入： $ARGUMENTS——要调查的主题、论文标题、研究问题或现象。

---

步骤

1. 解析主题： 从 $ARGUMENTS 中解析主题。如果指定了某篇论文，则以该论文为锚点。

2. 使用可用工具检索相关研究：

   • 检查 master_supporting_docs/supporting_papers/ 中是否有上传的论文
   • 使用 WebSearch 查找近期发表的论文（如果可用）
   • 使用 WebFetch 访问工作论文库（如果可用）
   • 阅读项目中现有的任何 .bib 文件，了解已有论文

3. 按以下类别整理发现：

   • 理论贡献——模型、框架、机制
   • 实证发现——关键结果、效应量、数据来源
   • 方法创新——新估计量、识别策略、推断方法
   • 公开争议——文献中尚未解决的分歧

4. 找出空白与机遇：

   • 还有哪些问题尚未解答？
   • 哪些数据或方法可以解决这些问题？
   • 哪些发现存在冲突？
   • 证据的独立性如何？ 对于你称为一致或已复现的发现，给出表面研究数量和独立研究数量——共享同一实验、数据集、样本或研究团队的研究只计为一项。
   • 有哪些相反结果？ 对每项主要发现，搜索无效结果和复现失败，并报告检索结果；如果未发现，则说明未找到，并列出使用的搜索词。

5. 提取引用： 以 BibTeX 格式列出所有讨论论文的引文。

6. 保存报告： 保存至 quality_reports/lit_review_[sanitized_topic].md

---

输出格式

# Literature Review: [Topic]

**Date:** [YYYY-MM-DD]
**Query:** [Original query from user]

## Summary

[2-3 paragraph overview of the state of the literature]

## Key Papers

### [Author (Year)] — [Short Title]
- **Main contribution:** [1-2 sentences]
- **Method:** [Identification strategy / data]
- **Key finding:** [Result with effect size if available]
- **Relevance:** [Why it matters for our research]

[Repeat for 5-15 papers, ordered by relevance]

## Thematic Organization

### Theoretical Contributions
[Grouped discussion]

### Empirical Findings
[Grouped discussion with comparison across studies]

### Methodological Innovations
[Methods relevant to the topic]

## Gaps and Opportunities

1. [Gap 1 — what's missing and why it matters]
2. [Gap 2]
3. [Gap 3]

## Suggested Next Steps

- [Concrete actions: papers to read, data to obtain, methods to consider]

## BibTeX Entries

```bibtex
@article{...}

---

## Post-Flight Verification (mandatory, CoVe)

Before returning the draft literature review to the user, run the Post-Flight Verification protocol from [`.claude/rules/post-flight-verification.md`](../../rules/post-flight-verification.md). Literature reviews are **very high** hallucination risk because WebSearch can return plausible-sounding fabricated citations. CoVe catches this architecturally.

### Steps

1. **Extract claims** from the draft. Each cited paper, each paraphrased finding ("Smith 2019 shows X"), each negative-literature assertion ("no prior work studies Y") is a claim.
2. **Generate verification questions** per claim. Specific ones: "Does Smith (2019, *JEL*) Section 3 actually report the finding that X implies Y? Is the venue correct?"
3. **Spawn `claim-verifier`** via the `Agent` tool with `subagent_type=claim-verifier`, in a fresh context — a named `Agent` call, not a conversation fork, which would inherit the draft. Pass: the claims table, the verification questions, the source-material pointers (paper URLs, DOIs, `master_supporting_docs/` paths). **Do NOT pass the draft text itself** — the fresh-context independence is what makes CoVe work.
4. **Reconcile:** if the verifier reports PASS, attach a green Post-Flight block to the output. If PARTIAL, mark the unverifiable claims with uncertainty flags in the BibTeX block. If FAIL, **remove or rewrite the contradicted citations** using the verifier's evidence before returning.

### Skip conditions

- `--no-verify` flag — user opts out for speed.
- User hands you ≤3 papers they already have read and confirmed; CoVe is overhead for content they've personally verified.

### Output contract

Append a Post-Flight block to the report (collapsed by default). See rule doc for the format.

---

## Important

- **Be honest about uncertainty.** If you cannot verify a citation, say so.
- **Prioritize recent work** (last 5-10 years) unless seminal papers are older.
- **Note working papers vs published papers** — working papers may change.
- **Do NOT fabricate citations.** If you're unsure about a paper's details, flag it for the user to verify. Post-Flight Verification catches most fabrications automatically; this rule is the backup.