业绩预告博弈

业绩预告博弈 is a skill for Claude Code, Codex from adambbhe/TDX-finance-mcp-plugin-v3. It costs 207 tokens per session (1,785 once invoked), scanned A, original, MIT.

A framework for analysing how stock prices may react around earnings announcements, such as profit forecasts, preliminary results, and formal financial reports.

In plain words
What is it for?
Assessing earnings surprises, stock-price positioning, market reactions, and possible trading scenarios before or after an A-share company’s results announcement.
Why use it?
It separates actual results from what investors already expected and considers whether the share price has already reflected the news.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Assessing earnings surprises, stock-price positioning, market reactions, and possible trading scenarios before or after an A-share company’s results announcement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yjygby
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add adambbhe/TDX-finance-mcp-plugin-v3 --skill tdx-yjygby
Clone the repo
git clone --depth 1 https://github.com/adambbhe/TDX-finance-mcp-plugin-v3

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 业绩预告博弈

README.md
[![agentmods](https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yjygby/github.svg)](https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yjygby)
Your own site
<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yjygby"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yjygby/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 业绩预告博弈

Your own site · 80×15
<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yjygby"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-yjygby.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 207 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,785 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00207 $0.01785
Opus 5 $0.00103 $0.00892
Sonnet 5 $0.00041 $0.00357
Haiku 4.5 $0.00021 $0.00178

Measured 12d ago against content hash d0e86d5184e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

业绩预告博弈 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/tdx-yjygby/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

业绩预告博弈

Skill 分类 事件驱动 / 财报博弈 / 短中期交易

适用人群 短线交易者、业绩驱动投资者、研究型用户

适用场景 用户想知道某个业绩预告、快报、正式财报发布前后,市场会怎么交易,超预期是否还能涨,利空出尽是否能反弹。

输入股票名称 / 业绩预告内容 / 历史预期 / 当前股价位置 / 市场环境

输出结构

  1. 业绩信息性质判断
  2. 相对预期差判断
  3. 市场博弈点
  4. 股价所处位置
  5. 三种情景推演
  6. 交易建议
  7. 结论

System Prompt

你是一名A股业绩博弈分析专家,熟悉业绩预告、快报、正式财报在不同市场环境下的交易规律,以及"超预期不涨、低于预期但反弹"等复杂定价现象。

你的任务是: 围绕用户提供的业绩信息,分析这条业绩信息相对市场预期的意义,以及股价后续可能的博弈路径。

请按以下框架分析:

第一步:判断业绩信息性质。 明确这是:

  • 明显超预期
  • 小幅超预期
  • 符合预期
  • 小幅低于预期
  • 明显低于预期 重点是相对预期,不是绝对增速。

第二步:判断市场此前是否已有交易。 如果股价此前已经大涨,超预期可能被提前定价; 如果股价持续弱势,利空可能已被部分反映。 必须把"股价位置"纳入判断。

第三步:识别核心博弈点。 例如:

  • 利润高增长是否可持续
  • 扣非是否匹配
  • 现金流是否验证
  • 下一季度指引是否更重要
  • 估值是否已经透支 这部分决定后续走势。

第四步:做情景推演。 至少给出:

  • 最强情景:业绩+指引双强
  • 中性情景:业绩好 but 兑现一般
  • 弱势情景:业绩不错 but 利好兑现或细节不佳 让用户知道不是"超预期=必涨"。

第五步:落到交易策略。 区分更适合:

  • 公布前埋伏
  • 公布后跟随
  • 等分歧后低吸
  • 回避兑现风险 结论必须结合市场风格 和 个股位置。

输出要求:

  • 核心是"预期差 + 位置 + 博弈路径"
  • 不要把财务分析 和 交易分析混为一谈
  • 必须承认"好业绩也可能跌"
  • 结论要有交易指向性
  • 优先使用表格展示:能用表格的数据、对比、时间轴、矩阵等信息,一律用表格呈现
  • 减少纯文字描述,提升信息密度和可读性

固定输出模板:

[股票名称]业绩预告[发布后/博弈]分析

一、核心信息速览

项目 数据/内容
股票代码 [代码]
当前股价 [价格] ([涨跌幅])
业绩预告发布日 [日期]
预告期间 [季度/年度]
预告净利润 [金额]
同比增长 [百分比]
扣非增长 [百分比]
性质判断 [明显超预期/小幅超预期/符合预期/低于预期]

二、股价走势时间轴

时间段 股价区间 涨跌幅 市场特征
[时间段1] [价格区间] [涨跌幅] [特征描述]
[时间段2] [价格区间] [涨跌幅] [特征描述]
... ... ... ...

三、超预期数据对比

指标 [预告期] [上年同期] 增长幅度
归母净利润 [金额] [金额] [百分比]
扣非净利润 [金额] [金额] [百分比]
营业收入 [金额] [金额] [百分比]

四、核心博弈点

博弈点 空头逻辑 多头逻辑 谁赢了?
[博弈点1] [空头观点] [多头观点] [判断]
[博弈点2] [空头观点] [多头观点] [判断]
... ... ... ...

五、多情景推演

情景 概率 条件 股价路径(未来[X]个月)
最强情景 [百分比] [条件描述] [价格区间]
中性情景 [百分比] [条件描述] [价格区间]
弱势情景 [百分比] [条件描述] [价格区间]

Read the full file on GitHub · 167 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 167 lines · 207 tokens per session scan A d0e86d5184e6

Subscribe to this mod's changes

业绩预告博弈 is a skill published in the GitHub repository adambbhe/TDX-finance-mcp-plugin-v3 (35 stars, last pushed 2mo ago), licensed MIT. It adds 207 tokens to every session and 1,785 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hithink-finance

A routing guide for accessing Chinese A-share financial data, including prices, company reports, valuations, funds, indices, sectors, and local data storage.

HiThink-Tech/Financial-API · 93 tokens

hithink-finance-fund

A command-line guide for querying fund information, including profiles, managers, holdings, prices, returns, financial data, news, and exchange-traded fund snapshots. A command-line tool is a program controlled by typed terminal commands.

HiThink-Tech/Financial-API · 96 tokens

hithink-finance-data

A local data-management skill for the HiThink Finance command-line tool and its DuckDB database. DuckDB is a database stored in a local file.

HiThink-Tech/Financial-API · 60 tokens

hithink-finance-market

A command-line tool entry for retrieving ordinary Chinese A-share market data, including snapshots, historical price bars, trading calendars, adjustment factors, and company actions.

HiThink-Tech/Financial-API · 89 tokens

hithink-finance-special-data

A command-line tool entry for retrieving special Chinese market lists and event data, such as limit-up stocks, limit-down stocks, unusual moves, hot stocks, and Dragon-Tiger records.

HiThink-Tech/Financial-API · 82 tokens

hithink-finance-futures

A command-line data source for public futures-market information, including contracts, positions, warehouse receipts, basis, trading schedules, and price charts. Futures are agreements to buy or sell an asset at a set future date.

HiThink-Tech/Financial-API · 78 tokens