将 deep 调研结果汇总为小说创作者可直接使用的 Markdown 研究报告,覆盖所有字段,跳过不确定值。报告落盘到项目或题材的 `写作研究/` 目录。
npx skills add https://github.com/lornshrimp/Lorn.NovelWriteSkills --skill 通用-深度研究-研究报告
<!-- ===== Layer 1: 永久缓存 ===== -->
/research-report
在当前工作目录查找 */outline.yaml,读取 topic、research_domain 和 output_dir 配置。
读取所有 JSON 结果,提取适合在目录中显示的字段(数值型、简短指标),例如:
使用 AskUserQuestion 询问用户:
在 {topic}/ 目录下生成 generate_report.py,脚本要求:
[不确定] 的字段{topic}/report.md目录格式要求:
1. 读者偏好迁移 - 增长趋势: ↑15% | 搜索热度: 高1. JSON 结构兼容
支持两种 JSON 结构:
{"name": "xxx", "market_share": "xxx"}{"市场数据": {"name": "xxx"}, "内容特征": {...}}字段查找顺序:顶层 → category 映射 key → 遍历所有嵌套 dict
2. Category 多语言映射
fields.yaml 的 category 名与 JSON 的 key 可能是任意组合(中中、中英、英中、英英)。必须建立双向映射:
CATEGORY_MAPPING = {
"市场数据": ["market_data", "市场数据"],
"内容特征": ["content_features", "内容特征"],
"读者反馈": ["reader_feedback", "读者反馈"],
"专业知识": ["domain_knowledge", "professional_knowledge", "专业知识"],
"人物特征": ["character_traits", "人物特征"],
"场景细节": ["scene_details", "场景细节"],
"技法要素": ["technique_elements", "技法要素"],
"创作可迁移": ["transferable_insights", "创作可迁移"],
}
3. 复杂值格式化
| 分隔 kv<br> 或使用 blockquote 格式,提高可读性4. 额外字段收集
收集 JSON 中有但 fields.yaml 中没定义的字段,放入"其他信息"分类。注意过滤:
_source_file、uncertain市场数据、内容特征 等uncertain 数组:需要逐行显示每个字段名,不要压缩成一行5. 不确定值跳过
跳过条件:
[不确定] 字符串uncertain 数组中6. 创作可迁移总结(新增,强制)
报告末尾必须生成一个 "创作可用结论与抓手" 部分,将全部研究发现翻译成小说创作者可以直接使用的行动建议:
报告生成完成后,执行以下自检清单(借鉴 nuwa-skill Phase 4 质量验证方法论):
## 报告质量自检清单
### 结构完整性
- [ ] 包含 `## 研究课题`
- [ ] 包含 `## 研究方法与来源`
- [ ] 包含 `## 核心发现`(区分核心/参考/待验证三级)
- [ ] 包含 `## 创作可用的结论与抓手`(≥3 条具体建议)
- [ ] 包含 `## 诚实边界`(信息截止日期 + 信息缺口 + 不确定项 + 置信度总评)
- [ ] 包含 `## 信息来源`(区分一手/二手,标注可信度)
### 质量验证(三重验证)
- [ ] 每条"核心发现"有 ≥2 个独立来源支撑?
- [ ] "创作可用的结论与抓手"中的每条建议都具体到"可写什么场景/怎么用/用在哪类情节"?
- [ ] 超过 50% 的核心发现通过"有区分度"验证(不是常识)?
### 诚实边界
- [ ] 明确写了信息截止日期?
- [ ] 列出了所有 `[不确定]` 和 `[待验证]` 条目?
- [ ] 给出了整体置信度总评(高/中/低)及理由?
- [ ] 标注了信息不足的维度?
### 矛盾处理
- [ ] 报告中的矛盾发现已保留(未强行统一)?
- [ ] 矛盾双方都标注了来源类型与可信度?
使用 AskUserQuestion 询问用户:
写作研究/ 下)运行 python {topic}/generate_report.py
{topic}/generate_report.py - 转换脚本{topic}/report.md - 完整研究报告{写作研究目录}/{研究域简称}_{课题简述}.md - 最终落盘文件(可选精简版)Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
Take lornshrimp/通用-深度研究-研究报告 from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.