industry-deep-research
Skill4 starsChanged 17 days agoNo licenceView on GitHub
默认*不读* prompts/ 全文;只在生成对应章节时读取该章节那一个 prompt 文件。 路由(三态):先查产业链(市场主题 + 标准产业)→ 无高相关则查产业指数 → 有高相关指数出产业指数报告,否则回退中相关产业链,仍无则提示未找到。 统一标题:《{{主体名称}}产业深度分析报告》(产业链取 TYPE_NAME,产业指数取 INDEX_ABBR)。不得使用其他形式标题。 无感路由:不得向用户暴露「市场主题 / 标准产业 / 产业指数」「走了哪条链路」等内部术语;仅在存在*多个候选*需消歧时展示候选编号(不标注类型)。单一候选直接生成,不询问确认。 两条实测红线(原版未覆盖,务必遵守): 报表路径可能随报表体系重构变化。若上表路径报「报表不存在/无结果/字段不存在」,按 MQL 工具链标准顺序(生成参考 → 业务知识 → 上下文检索)重检索一次 indicatorPath,并优先选择分支说明与本次一致的变体(同名的 API专题报表函数\... 变体常带…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ai-eastmoney/EastmoneySkillsword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- ai-eastmoney/EastmoneySkills★ 4100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository46 other files it gives its agents.
- choice-quantapi-skillSkill
- comparable-company-analysisSkill
- convertible-bond-deep-researchSkill
- credit-bond-deep-researchSkill
- credit-spread-deep-researchSkill
- enterprise-alert-monitoringSkill
- enterprise-deep-researchSkill
- etf-deep-researchSkill
- fund-deep-researchSkill
- fund-diagnosisSkill
- fund-manager-researchSkill
- fund-researchSkill
- futures-deep-researchSkill
- government-bond-deep-researchSkill
- industry-research-reportSkill
- industry-sector-analysisSkill
- industry-stock-trackerSkill
- initiation-of-coverage-or-deep-diveSkill
- local-government-debt-analysisSkill
- market-liquidity-deep-researchSkill
- meeting-minutes-comparisonSkill
- mql-querySkill
- mx-finance-dataSkill
- mx-finance-searchSkill
- mx-financial-assistantSkill
- mx-macro-dataSkill
- mx-personal-kb-searchSkill
- mx-self-selectSkill
- mx-stocks-screenerSkill
- on-the-run-bond-deep-researchSkill
- primary-bond-deep-researchSkill
- research-report-reviewSkill
- sellside-research-refresh-with-excelSkill
- stock-capital-analysisSkill
- stock-deep-researchSkill
- stock-diagnosisSkill
- stock-earnings-reviewSkill
- stock-fundamental-analysisSkill
- stock-institutional-opinionSkill
- stock-market-hotspot-discoverySkill
- stock-news-analysisSkill
- stock-price-anomaly-analysisSkill
- stock-price-movement-analysisSkill
- stock-technical-analysisSkill
- top-holdings-pressure-insightSkill
- topic-research-reportSkill
The file
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.

