Policy Keyword Tracker logo

Policy Keyword Tracker

Community
zhaohui-yang
policy-keyword-tracker

围绕一个关键词/主题(如「创新药」「低空经济」「数据要素」)检索各中央国家部委的相关政策、措施与动态,汇总成一份《情况专报》。Use when 用户想跟踪某一主题在各部委的政策口径、做专题政策梳理与研判。采集→核实→按「情况专报」文种成稿,可导出 Word。文体固定为情况专报。

Overview

Publisherzhaohui-yang
Repositoryofficial-document-drafting
Skill namepolicy-keyword-tracker
Stars
148
Forks
19
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zhaohui-yang on GitHub. Read the source before you install it.

Installation

Install the Policy Keyword Tracker AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zhaohui-yang/official-document-drafting/tree/main/skills/policy-keyword-tracker
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zhaohui-yang/official-document-drafting.git /tmp/official-document-drafting
mkdir -p .claude/skills
cp -r /tmp/official-document-drafting/skills/policy-keyword-tracker .claude/skills/policy-keyword-tracker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Policy Keyword Tracker in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Policy Keyword Tracker on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Policy Keyword Tracker is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

关键词政策跟踪

给定一个关键词或主题,跨中央国家部委官网检索该主题的相关政策、措施、规划与动态,汇总成一份《情况专报》,用于专题政策梳理与研判。与 ministry-news-daily(按日汇总全量动态)互补:本 skill 是按主题纵向聚焦。

文件索引

prompts/doc-types/special-report-情况专报/spec.md   # 「情况专报」文种的写作规则、撰写思路与模板(成稿依据)
prompts/core/doc-type-guardrails.md                 # 防编造强制约束(采集核实的底线)
skills/_common/web-collection.md               # 采集类共享约束(信源/访问/保存/降级/底线)
src/scripts/generate_docx.py                            # 成稿导出机关版式 .docx(--doc-type 情况专报)
样例/online/policy-keyword-tracker-创新药政策跟踪/   # 完整样例:task / materials / 成稿 / README

共享约束(硬性)

采集类 skill 的硬性底线:只用只读 WebSearch / WebFetch、逐站串行低频、遵守 robots 与版权、有来源才写绝不编造。完整条款(信源基线/访问约束/保存路径/离线降级/边界底线)见 ../_common/web-collection.md,冲突时以该文件为准。按单 skill 目录 symlink/拷贝安装本 skill 时,须把 skills/_common/ 一并链入同一父目录,否则该相对路径失效(见 skills/README.md「约定」)。本 skill 的任务差异:

  • 信源侧重:按主题对口部委——中国政府网 www.gov.cn(政策库、最新文件、部门文件检索),以及与主题相关的对口部委官网,例如「创新药」对应:国家药监局、国家卫生健康委、国家医保局、科技部、工业和信息化部、国家发展改革委等。
  • 检索方式:先用 WebSearch 以「关键词 + 部委/政策」命中具体页面,再用 WebFetch 取该页,减少无谓请求。
  • 子目录:policy-tracking/<关键词>/(如 .../policy-tracking/创新药/),按主题归档;同一主题多次跟踪 -vNN 递增、不覆盖,便于对比政策演进。
  • 成稿命名:YYYYMMDD-关于<关键词>相关政策动态的情况专报-vNN.{md,docx}。
  • 离线降级:人工围绕关键词检索素材后,用 dist/offline/default/doc-types/special-report-情况专报/prompt.md成稿。
  • 校验:成稿后可转 document-qa 校验(src/scripts/check_sections.py special-report)。

默认流程

  1. 定主题与口径:确认关键词(如「创新药」)、时间范围(如近 1–3 年)、关注角度(审评审批、医保支付、产业支持等)。
  2. 检索:围绕关键词逐个对口部委检索相关政策与动态,逐条记录「发布机关 + 政策标题 + 核心要点 + 发布日期 + 来源 URL」,落成 materials.md。
  3. 核实:每条都要有可追溯来源 URL;检索不到或无法确认的,宁可不写,绝不编造机关、数字、文号、日期(见 doc-type-guardrails.md);存疑项标「待核实」。
  4. 成稿(情况专报):按 prompts/doc-types/special-report-情况专报/spec.md 谋篇——标题(《关于「关键词」相关政策动态的情况专报》)、报送对象、一、事项概况(主题与政策总体格局)、二、最新进展(按部委/时间梳理最新政策,括注来源)、三、风险研判(趋势、影响、待关注问题,与事实分开)、四、工作建议,结尾「特此报告。」。
  5. 导出(可选):
bash
python3 src/scripts/generate_docx.py <成稿>.md -o <成稿>.docx --doc-type 情况专报

Frequently asked questions

What does the Policy Keyword Tracker AI skill do?

围绕一个关键词/主题(如「创新药」「低空经济」「数据要素」)检索各中央国家部委的相关政策、措施与动态,汇总成一份《情况专报》。Use when 用户想跟踪某一主题在各部委的政策口径、做专题政策梳理与研判。采集→核实→按「情况专报」文种成稿,可导出 Word。文体固定为情况专报。

Why use Policy Keyword Tracker on TypingMind?

Because you install it once and use it with any model. Policy Keyword Tracker is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Policy Keyword Tracker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhaohui-yang/official-document-drafting/tree/main/skills/policy-keyword-tracker. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Policy Keyword Tracker?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Policy Keyword Tracker?

As many as you like. As long as a model supports skills, you can use Policy Keyword Tracker with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Policy Keyword Tracker AI skill free?

It is published on GitHub by zhaohui-yang. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇