market-info-recording
Skill10 starsChanged 6 months agoMITView on GitHub
沉淀市场分析信息到知识库(asset_market_info),以及回查已记录的市场评级、财报分析、投资观点。 当用户说"把这条分析记下来"、"保存到市场信息"、"XX 我之前记录过什么评级"、"更新一下这个资产的市场信息", 或你刚完成一段有价值的分析、用户表示认可并希望下次复用时,**务必使用此技能**。
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-learningSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- event-driven-analysisSkill
- fundamental-analysisSkill
- investment-notesSkill
- macro-analysisSkill
- market-data-lookupSkill
- portfolio-managementSkill
- report-consultingSkill
- risk-assessmentSkill
- sentiment-analysisSkill
- stock-analysisSkill
- task-managementSkill
- technical-analysisSkill
- transaction-managementSkill
- valuation-modelsSkill
The file
Files
市场信息沉淀与回查
回查(读)
stockRecallMarketInfoTool:按symbol查询知识库中该资产已记录的市场评级、财报分析、投资笔记。dbQueryTool查表asset_market_info(列:symbol, sentiment, importance, createdAt)可看最近入库记录:
{"table": "asset_market_info", "whereColumn": "symbol", "whereValue": "AAPL", "orderBy": "created_at", "limit": 10}保存(写):marketInfoSaveTool
用户明确同意保存后调用。必填参数:
| 参数 | 必填 | 说明 |
asset_meta_ids | ✅ | 数组,已存在的资产元数据 ID。先用 dbQueryTool 查 asset_meta(whereColumn: symbol)拿 ID,禁止发明不存在的 ID |
title | ✅ | 信息标题 |
symbol | ✅ | 资产代码 |
sentiment | ✅ | 情绪评级:positive / neutral / negative(应用 UI 按这三个取值展示) |
importance | ✅ | 重要性评分,1-10 的数字字符串(如 "7") |
summary | ✅ | 一段式摘要(供复用与分析时召回) |
market_impact | ✅ | 市场影响描述 |
key_topics | 可选 | 关键主题 |
key_data_points | 可选 | 关键数据(如 P/E、目标价) |
source_url / source_name | 可选 | 来源(来自互联网搜索时必填,标注出处) |
流程
- 分析/检索得到结论 → 主动给出拟保存的摘要内容让用户确认。
- 确认后:先查
asset_meta拿资产 ID → 调用marketInfoSaveTool→ 复述保存结果。 - sentiment / importance 不要放主观空话,写清楚理由("negative:库存数据背离 + 高盛下调")。
例外
- 保存失败(asset_meta 不存在该标的)时,告知用户该资产尚未纳入资产库,先在应用中添加资产。
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.

