geeksfino avatar

Event Driven Detector

This scans Chinese A-share markets for event-driven trading opportunities like M&A, asset injections, buybacks, SOE reforms, and index rebalancing. You give it a scope (event type, sector, risk appetite), and it returns ranked opportunities with probability-weighted returns, completion timelines, and regulatory approval risks. The workflow is thorough: it quantifies price spreads, assesses downside scenarios if deals fall through, and pulls comparable historical cases. Honestly, the real value is in how it handles A-share-specific friction like approval uncertainty and trading halts during restructuring. It integrates with findata-toolkit-cn for live market data. Built for analysts running special situations portfolios, though it rightly warns that information asymmetry in A-shares means prices often move before public announcements.

skills.sh installs
232
GitHub stars
286
last updated
Aug 21, 2026

Install

$ npx -y skills add geeksfino/finskills --skill event-driven-detector --agent claude-code

Installs into .claude/skills of the current project.

Files

事件驱动机会识别器

扮演特殊情况分析师。识别和分析可能在A股创造临时定价偏差的公司事件——包括并购重组、资产注入、回购增持、管理层变更和指数调整——并评估每个机会的风险收益比。

工作流程

第一步:界定范围

与用户确认:

  1. 事件类型 — 全部(默认)或特定类别(并购重组、回购增持等)
  2. 市场 — A股全市场(默认)、特定行业、或特定公司
  3. 时间窗口 — 活跃事件(默认)或历史分析
  4. 风险偏好 — 保守(高确定性机会)或积极(较高风险催化剂)
  5. 资金规模 — 组合配置背景(如相关)
  6. 结果数量 — 呈现的机会数量(默认:5个)

第二步:扫描活跃事件

在各类别中筛选公司事件。详细分类参见 references/event-framework.md。

事件类别扫描内容
并购重组已公告的重大资产重组、吸收合并、借壳上市
资产注入控股股东/集团资产注入承诺或计划
回购增持公司回购计划、大股东/高管增持
国企改革混合所有制改革、资产证券化、整体上市
指数调整沪深300、中证500、MSCI中国等指数成分调整
管理层变更核心高管变动及其战略影响
分拆上市子公司分拆至科创板/创业板/境外上市
解禁减持大额限售股解禁及减持计划

第三步:逐个分析

对每个识别的事件提供:

  1. 事件概述 — 发生了什么,时间线,关键方
  2. 价差/机会 — 量化上行空间(如并购价差、重组前后估值差)
  3. 完成概率 — 预估成功或完成的可能性
  4. 时间线 — 关键里程碑的预期日期
  5. 风险因素 — 可能出错的方面
  6. 风险收益比 — 年化收益率 vs 概率加权下行
  7. 历史可比案例 — 类似过往事件及其结果

第四步:风险评估

对每个机会评估:

风险因素评估内容
监管审批风险证监会审批、反垄断审查、行业主管部门审批
资金风险交易对价是否已落实?支付方式(现金/股份/组合)
股东风险是否需要股东大会审议?反对可能性
市场风险持有期内对整体市场波动的敏感度
时间风险资金占用多久?机会成本
下行风险事件失败或反转时,股价回到哪里?
信息不对称A股内幕交易风险,价格可能已反映预期

第五步:排序与呈现

Sponsors

Details

Repository
github.com/geeksfino/finskills
First seen
Jun 3, 2026

More from geeksfino/finskills

All 6

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs