source-grounded-research
Skill9 starsChanged 21 days agoMITView on GitHub
为人文社科报告进行可追溯的联网检索、优秀范例学习、政策与时效性事实核验、文献查找和引用整理。用户要求上网搜集、查最新信息、学习优秀范例、补充政策背景、查文献、核验出处或提供链接时使用。该 Skill 只负责外部资料的发现与证据控制,不替代报告统筹或 Word 排版。
3 other projects use a version of this.
Adopted by
Most recently taken up by
- xuedai-mayi/folio-deskword for word, first seen Nov 1, 2026
- laststance/skillstheir own version, first seen Sep 21, 2026
- Dokuganrryu/ai-agent-skills-and-subagentstheir own version, first seen May 26, 2026
Other versions3 projects use a version of this.
Word for word · 1
- xuedai-mayi/folio-desk★ 9100% same
Edited · 0
None found.
Wrote their own version · 2
- laststance/skills★ 1same name
- Dokuganrryu/ai-agent-skills-and-subagents★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- humanities-report-writerSkill
- humanizerSkill
- word-report-deliverySkill
The file
Files
有来源的人文社科检索
目标
为报告提供可以回到原网页、文件或数据库记录的外部证据。检索结果必须区分事实来源、学术研究、政策文件、优秀范例和一般观点。
开始前
从主任务中确定研究问题、时间范围、地域范围、需要核验的事实、需要学习的范例类型和引用格式。信息足够时直接检索。
如果当前环境不能联网或没有可用检索工具,明确说明限制,不得编造搜索过程、来源、链接、文献或访问日期。
检索顺序
- 政策、法律、统计数据、机构职责和项目事实,优先政府部门、法律法规数据库、统计机构和发布单位原文。
- 学术观点优先期刊官网、出版社、大学机构库、权威学术数据库和论文原文。
- 学校评选通知、报告要求和优秀成果,优先学校、学院、团委或项目主办方公开页面。
- 新闻报道和自媒体材料只能补充情境,不能替代原始文件或研究证据。
详细筛选规则见 references/source-and-example-rules.md。
范例学习
优秀范例用于识别章节组织、研究问题呈现、证据密度、段落节奏、图表使用和结语方式。不要复制范例的题目、句段、案例、数字和引用,也不要把范例中的事实写入用户报告,除非该事实另有适当来源且与任务相关。
检索后提炼可迁移的写作模式,例如“先呈现差异,再用访谈解释差异”,不要只摘录漂亮句子。
来源底表
对拟写入正文的外部材料记录:
- 支持的具体主张
- 来源类型与发布主体
- 标题、作者或机构、发布日期
- 原始链接或数据库标识
- 访问日期
- 原文位置或页码
- 允许使用的结论范围
- 是否需要直接引用
直接引语应短而必要,保持原意并遵守版权限制。能够转述时优先准确转述。
交叉核验
重要且容易变化的事实应回到最新的权威原文。来源相互矛盾时,比较发布日期、定义、统计口径、覆盖对象和原始程度,不用多数表决代替判断。仍无法确定的内容标记为待确认或不写。
写入报告
- 每个外部事实在正文或注释中紧邻标注来源。
- 政策规定、统计事实、学者观点和作者分析要用不同口吻表达。
- 不用“有研究表明”“专家认为”等模糊归因代替真实作者或机构。
- 不把搜索结果页当作来源,引用能够直接支持主张的原页面。
- 不为了显得资料丰富而堆砌无关文献。
交付给主 Skill
返回经过筛选的来源清单、每个来源支持的主张、可迁移的范例模式、冲突或缺口。主 Skill 负责决定结构和正文写法。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

