政策解读与受益分析

政策解读与受益分析 is a skill for Claude Code, Codex from adambbhe/TDX-finance-mcp-plugin-v3. It costs 248 tokens per session (5,443 once invoked), scanned A, original, MIT.

A research assistant for interpreting Chinese policies and tracing how they may affect industries and companies. It is designed for policy research, thematic investing, event-driven analysis, and mapping policy changes to potential beneficiaries.

In plain words
What is it for?
Use it to analyse policy documents, regulatory changes, meeting records, and industry support measures. It can support investment reports and related financial analysis, but the description does not establish that its conclusions are investment advice.
Why use it?
It helps turn a policy document or meeting statement into an assessment of what is genuinely new, how its effects may spread, and which companies may benefit or merely attract attention.

Skill for Claude CodeCodex

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

Good fit Use it to analyse policy documents, regulatory changes, meeting records, and industry support measures. It can support investment reports and related financial analysis, but the description does not establish that its conclusions are investment advice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-zzjdysyfx
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-zzjdysyfx
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 政策解读与受益分析

README.md
[![agentmods](https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-zzjdysyfx/github.svg)](https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-zzjdysyfx)
Your own site
<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-zzjdysyfx"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-zzjdysyfx/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 政策解读与受益分析

Your own site · 80×15
<a href="https://agentmods.dev/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-zzjdysyfx"><img src="https://agentmods.dev/badge/skills/adambbhe/tdx-finance-mcp-plugin-v3/tdx-zzjdysyfx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 248 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,443 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 $0.00248 $0.05443
Opus 5 $0.00124 $0.02721
Sonnet 5 $0.00050 $0.01089
Haiku 4.5 $0.00025 $0.00544

Measured 12d ago against content hash 12da95f349e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

政策解读与受益分析 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-zzjdysyfx/SKILL.md · 456 lines

How it starts

The opening of the file, as written. The whole thing — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.

政策解读受益映射

Skill 分类

政策研究 / 主题投资 / 事件驱动 / 产业映射

适用人群

主题投资者、行业研究员、政策敏感型投资者、短中期交易用户

适用场景

用户看到政策文件、会议表述、产业扶持、监管变化后,最关心的是: 政策含金量有多高,是真增量还是旧话重提,受益链条如何传导,哪些标的是核心受益方,哪些只是题材跟风。

输入

政策全文 / 政策摘要 / 会议纪要 / 监管文件 / 用户关注方向

调用tool

web_search tdx_api_data(entry="tdxf10_gg_rdtc", fixedTag="sjcd") tdx_api_data(entry="tdxf10_gg_ybpj", fixedTag="yjyg")

信息获取策略(重要)

🎯 搜索优先级与时间范围

第一步:精准搜索(3个月内)

  1. 使用具体文件名核心关键词搜索
  2. 搜索词格式:"主题词" + "文件类型/关键词"
    • 示例:"低空经济" + "标准体系建设指南"
    • 示例:"低空经济" + "建设指南"
    • 示例:"低空经济" + "十部门"
  3. 避免使用过于宽泛的关键词如"政策""最新""2026年"

第二步:时间范围递进策略

优先级1:最近3个月(当前时间 ± 3个月)
优先级2:最近6个月
优先级3:最近1年
优先级4:往前扩展到2年

第三步:多工具组合使用

  1. tdx_api_data(entry="tdxf10_gg_ybpj", fixedTag="yjyg"):查找官方政策文件、公告、业绩预告(权威性最高)[已切换为 F10 替代方案]

    • 搜索词:"主题词" + "具体文件名"
    • 搜索词:"主题词" + "发布" + "年份/月份"
  2. tdx_api_data(entry="tdxf10_gg_rdtc", fixedTag="sjcd"):查找政策解读、会议报道、重大事件(时效性最强)[已切换为 F10 替代方案]

    • 搜索词:"主题词" + "会议"
    • 搜索词:"主题词" + "重大事件"
    • 搜索词:"主题词" + "政策梳理"
    • 搜索词:"部门名称" + "主题词" + "2026"
  3. web_search:补充搜索,查找综合报道和深度分析

    • 当以上两个工具结果不足时使用
    • 搜索词:"主题词" + "最新政策" + "2026"

📅 相关会议识别规则

高层级会议(必须包含):

  • 中央经济工作会议(每年12月)
  • 全国两会(每年3月)
  • 党的中央全会(不定期)
  • 国务院常务会议(每周)
  • 部委新闻发布会(不定期)

行业会议(选择性包含):

  • 产业发展峰会
  • 行业博览会
  • 专题研讨会

搜索会议关键词:

"主题词" + "会议"
"主题词" + "座谈会"
"主题词" + "发布会"
"主题词" + "峰会"
"部门名称" + "会议" + "主题词"

🔍 搜索失败时的回退策略

如果3个月内无结果:

  1. 扩展到6个月,使用相同关键词
  2. 如果仍无结果,扩展到1年
  3. 添加时间限定词重新搜索:
    "主题词" + "2025年12月"
    "主题词" + "第四季度"
    "主题词" + "下半年"
    

如果搜索结果过多且相关性低:

  1. 添加文件类型限定:

    "主题词" + "指导意见"
    "主题词" + "实施方案"
    "主题词" + "行动计划"
    "主题词" + "建设指南"
    
  2. 添加部门限定:

    "发改委" + "主题词"
    "工信部" + "主题词"
    "国务院" + "主题词"
    

✅ 搜索结果验证标准

找到政策文件后,必须确认:

  1. 发布时间:是否在合理时间范围内(优先3个月内),并明确标注距离当前的时间跨度
  2. 发布机构:是否为权威部门(国务院、各部委、地方政府)
  3. 文件性质:是否为正式文件(非新闻报道、非评论文章)
  4. 增量内容:是否有新提法、新措施、新目标

时效性说明规范:

  • 必须准确计算时间跨度:从政策发布日期到当前日期(搜索日期)的实际月数
  • 如果找到的政策不在3个月内,必须在搜索记录中明确说明实际时间跨度
  • 例如:"找到《XXX方案》(2024-07-05),距离当前21个月,不在3个月范围内"
  • 如果3个月内无新政策,应说明:"3个月内无重大新政策,最新政策为X个月前的《XXX》"
  • 禁止错误归类:不得将6个月前或更早的政策归入"3个月内"或"6个月内"

Read the full file on GitHub · 456 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 456 lines · 248 tokens per session scan A 12da95f349e7

Subscribe to this mod's changes

政策解读与受益分析 is a skill published in the GitHub repository adambbhe/TDX-finance-mcp-plugin-v3 (35 stars, last pushed 2mo ago), licensed MIT. It adds 248 tokens to every session and 5,443 once invoked, about $0.0012 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