a-stock-operator-v2
Skill16 starsChanged 2 months agoNo licenceView on GitHub
生成 A 股「行情复盘报告」与「个股诊断报告」(Markdown 文档,带日期,红涨绿跌,结论前置)。 行情模式:市场全景(核心指数 / 情绪周期定位 / 连板 / 主线题材 / 政策 / 热点)+ 近一月板块轮动专题(日期列头 × 每日 Top7 板块、动态色标记轮动、全量标注涨幅% 与涨停数 ×N + 资金轮动四象限 + 板块多因子趋势榜)。 情绪周期定位:基于「情绪温度计」(Model 04,温度+风险双维、五阶段、仓位建议)研判情绪阶段(冰点/启动/发酵/高潮/分歧)+ 短线操作建议 + 仓位参考;主线题材采用「动态热点发现引擎」(Model 01,五因子评分 + 每日动态 Top N,新热点自动纳入)+ 题材生命周期定位(Model 02,萌芽/启动/发酵/高潮/退潮五阶段 + 短线/中线策略);板块轮动采用「资金轮动四象限」(Model 03,主线/接力/脉冲/退潮 + 轮动速度 + 扩散指数)与「板块趋势多因子」(Model 06,15日涨幅+5日动量+资金持续+涨停持续加权,标记启动/加速/减速/回落)。 个股模式:单只个股六维诊断(评分 / SWOT / 估值 / 龙虎榜 / 筹码 / 关键价位)+ 最终诊断操作建议(渐变环形评分 + 关键价位双栏 + 操作策略 3 卡 + 避坑提示),卡片化、有层次。 自包含:脚本全在技能目录内,相对路径免配置;产物(采集数据/过程脚本)默认写到**当前会话/工作目录**下的 `<cwd>/a-stock-operator-v2/` 子目录,**报告统一输出为 Markdown(带日期)写到 `<cwd>` 根目录**(`A_STOCK_WORK`/`A_STOCK_OUT` 可指定工程目录),不写回技能目录;「今日」默认真实交易日(--date 可覆盖),联网实时采集。 加载后先让用户选择模式。适用:行情复盘、个股诊断、生成股票报告、板块轮动、情绪周期、短线/中线操作建议、重新生成报告。
In this repository22 other files it gives its agents.
- agnes-image-gen-2Skill
- agnes-video-gen-2Skill
- a-stock-board-washoutSkill
- a-stock-lhb-recSkill
- a-stock-operatorSkill
- a-stock-yiyangzhiSkill
- cinematic-music-videoSkill
- deep-profileSkill
- dev-lifecycleSkill
- dev-twinSkill
- enterprise-portal-generatorSkill
- learning-handbook-pipelineSkill
- music-downloaderSkill
- short-drama-studioSkill
- strategic-advisorSkill
- suno-cn-musicSkill
- talkshowSkill
- talkshow-studio-klingSkill
- talkshow-studioSkill
- tech-article-craftSkill
- timeless-weddingSkill
- timeless-wedding-volcSkill
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.

