Nie Grassroots Logic logo

Nie Grassroots Logic

Community
ayi-ai
nie-grassroots-logic

聂辉华《基层中国的运行逻辑》方法论工具箱:政治经济学/组织经济学视角解释基层权力与治理, 并落到个人抉择(求学/考公/投资/养老/创业)。 核心框架:内外冲突的双均衡、条块结合以块为主、等级制资源配置(人跟资源走、资源跟权力走)、 职务含权量三因子、县委书记三座大山(维稳/招商/借债)、压力型体制与注意力分配、 政企四象限博弈、土地财政闭环、活力—秩序城市化权衡、上下同治。 当用户要理解基层/县域/乡镇治理、条块矛盾、属地责任、央地关系、官员晋升与考核、 一票否决、形式主义、招商引资、土地财政、地方债、街道办与村官、考公选岗、 高考志愿/选城读书、买房与区域投资风险、回哪养老、创业对接园区政府、 撤县设区/县改市对家庭影响、谁适合当村支书、大学生村官值不值得去、 新型职业农民/致富能手/回乡创业、昆山式改革/自下而上推项目/西气东输式立项、 营商环境比较、投资不过山海关、政商关系亲清、容错创新/基层敢不敢干、 抢高铁站/重大工程争夺、政策为何落地难、解读地方新闻、 或提到聂辉华/基层中国的运行逻辑/上下同治/含权量/条块结合/双均衡时使用。

Overview

Publisherayi-ai
Repositorynie-grassroots-logic
Skill namenie-grassroots-logic
Stars
566
Forks
65
Bundled files
20
LicenseMIT
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.

  • 20 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ayi-ai on GitHub. Read the source before you install it.

Installation

Install the Nie Grassroots Logic 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/ayi-ai/nie-grassroots-logic/tree/main
  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/ayi-ai/nie-grassroots-logic.git \
  .claude/skills/nie-grassroots-logic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nie Grassroots Logic 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 Nie Grassroots Logic 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 Nie Grassroots Logic 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.

基层中国的运行逻辑

可执行 AI Skill · 安装 ID:nie-grassroots-logic
来源:聂辉华《基层中国的运行逻辑》(组织经济学 + 政治经济学 + 实地调研)
本 skill 提纯结构、不写摘要;忠于原著命名与因果,不编造原书没有的框架/数字/案例。
开源包不含原书全文;请购买正版。一页索引见 INDEX.md。

哲学(先记住)

  1. 中国的问题,归根结底都是政治经济学问题。 先找权力与激励,再谈道德与情怀。
  2. 公说公有理,婆说婆有理;究竟谁有理,关键看逻辑;逻辑要自洽,关键看框架。
  3. 人跟资源走,资源跟权力走,权力本质是等级体系。 市场与等级并存;基层很多事不是价格配置的。
  4. 理解基层,才能理解中国。 基层是底色与基本盘;国家治理与基层治理必须上下同治。
  5. 有限权力 + 无限责任(政治承包制) 是基层主官的结构性张力;别把县委书记简单画成「土皇帝」或「包青天」。

调用本 skill 时必须做的

  1. 先判断用户问题落在哪一层(见下方「三层地图」),再打开对应 references/。
  2. 优先用原书命名框架分析,不要改写成泛化政治学口号。
  3. 输出结构默认:
    • 这是什么问题(条/块?级?激励?财权?)
    • 用哪个框架切
    • 因果链(谁激励谁、权责是否对称)
    • 可执行判断/选项(选岗、读新闻、写分析时)
    • 反模式提醒(见 anti-patterns-voice.md)
  4. 不确定的制度细节标「[原书有述·具体现行规定请核最新文件]」;不假装掌握最新人事口径。

三层地图(全书骨架)

层内容何时用深读
I 国家制度背景条块结合;内外冲突双均衡;上下同治;行政区划犬牙/山川解释「为什么总是这样」、央地博弈、集权分权切换dual-equilibrium.md + tiaokuai-and-rank.md
II 权力运行县委书记权界;双一把手;常务副职/高配;含权量;街道/乡镇/村选岗、读懂职位、权力边界、谁管谁power-and-positions.md
III 基层治理三座大山;乡镇难题;考核与晋升;数字化监督;招商/土地财政/债;城市化与营商理解主官压力、地方经济模式、政策后果local-governance.md + development-dilemmas.md

一页总索引图(14 reference 全图) → INDEX.md

包文件
个人抉择五场景life-decisions.md
村支书/村官适合度village-fit.md
撤县设区家庭影响rezoning-household.md
推项目(昆山/西气东输)bottom-up-project.md
营商环境比较business-environment.md
容错创新边界innovation-risk-boundary.md
抢高铁/重大工程mega-project-contest.md
场景快路径 A–Lplaybooks.md
反模式 + 作者声音anti-patterns-voice.md

框架速查(一句话)

框架一句话何时用
内外冲突的双均衡内稳↔外稳冲突 → 集权/分权两套兼容体系;制度僵化=兴亡之谜宏观国策、巡视/考核转向、数字技术与集权
条块结合,以块为主矩阵治理;属地责任落在块;条管与属地要分清权责不对等、「上面千条线」、条管单位
央地 = 委托—代理非兄弟、非父子;下级服从+地方有自利博弈政策变形、差序信任、试点与推广
等级制配置资源城市/官员金字塔;财政漏斗;行政级别抬 TFP 也抬错配城市差距、撤县设区/市、资源为何向上集中
职务含权量三因子级别 + 管什么人 + 管多少钱同级职位比权、隐性台阶、晋升非线性
县委书记三座大山维稳、招商、借债县域主官行为、地方新闻动机
压力型体制 + 注意力分配指标膨胀、一票否决、棘轮;部门抢考核权形式主义、迎检、指标越来越多
激励→监督转向数字技术降信息不对称 → 过程监督+多元一票否决十八大后新常态、指尖形式主义
政企四象限合作/分治/伤害/合谋(干预×合法)招商、营商环境、亲清+平
土地财政闭环低价工业地换税源 + 高价商住地抽血 + 基建交叉补贴房价、债务、园区、卖地依赖
活力—秩序城市化大城/小城之争的权衡框架;主张第三条道路区域政策、收缩城市、统一大市场
上下同治顶层设计 + 摸着石头过河;两个积极性改革试点、地方创新如何上位
昆山三板斧先做不说 → 做了再说 → 先上车再买票基层创新、企业/地方推政策
西气东输九步想法→汇报→视察→批示→论证→审批→领导小组→实施国家级/跨省重大项目
政商亲清指数亲近(服务)+ 清白(可预期);不完全契约选城、投资、区域黑话校准
容错创新三色边界红线/灰区/绿区;问责时代创新补丁敢不敢干、躺平与乱作为
重大工程争夺五幕进规划→抢站→注意力→配套→实施虹吸高铁站、枢纽、国家级项目

决策树(先问这三句)

  1. 这是权力结构问题还是激励/考核问题?
    • 结构(谁管谁、条还是块)→ 层 I/II
    • 激励(为什么拼命干/不干/搞形式)→ 层 III 考核与晋升
  2. 主角是哪一级? 中央/省/市/县/乡/村/街道 → 权界与天花板不同
  3. 用户要解释还是要选?
    • 解释现象 → 框架因果
    • 个人选择(求学/考公/投资/养老/创业)→ 先读 life-decisions.md,再补对应框架 reference

关键原则(调用时守住)

  1. 分清属地 vs 垂直、领导 vs 指导、分管 vs 联系。
  2. 权力边界 ≠ 辖区边界。 条管单位在地理上在县里,行政上未必归县委书记。
  3. 有权必有责,但基层常是权小责大。 分析时写清「无限责任政治承包」是否在起作用。
  4. 集权/分权要素不要混搭。 集权配:监督、忠诚、一刀切、犬牙交错;分权配:激励、能力、多样化、山川形便。
  5. 十八大前后规律不同。 勿用唯 GDP 锦标赛一套讲今天;要用政绩→问责、激励→监督。
  6. 物证纪律。 框架名、命题、案例来自原书;数字与人事以原书/用户补充为准。

何时读哪个 reference

完整一页图 + 14 文件表 + Mermaid → 必看 INDEX.md

用户说法/任务打开
条块、属地责任、央地、省界犬牙、皇权不下县、双均衡、上下同治dual-equilibrium.md + tiaokuai-and-rank.md
城市等级、官员级别、晋升锦标赛/新常态、重大政策如何出台tiaokuai-and-rank.md
县委书记权力、常务副职、高配、含权量、街道办、村官、选岗power-and-positions.md
谁适合当村支书、一肩挑、大学生村官、致富能手、回乡当村干部village-fit.md(必读)+ power-and-positions.md
撤县设区/县改市对生活/房价/学区/考公影响、我们县要设区了rezoning-household.md(必读)+ tiaokuai-and-rank.md
三座大山、乡镇书记难题、考核指标、一票否决、数字化、形式主义local-governance.md
招商、土地财政、地方债、电商救县城、大城小城development-dilemmas.md
营商环境、投资不过山海关、政商关系亲清、两城比较选哪落户business-environment.md(必读)
怎么推项目/改革、昆山三板斧、先上车再买票、重大工程立项、专家内参bottom-up-project.md(必读)
容错、敢不敢创新、基层躺平/不作为、问责下怎么试点innovation-risk-boundary.md(必读)
抢高铁/设站/枢纽争夺、大项目为何落在那、通车后空站mega-project-contest.md(必读)
求学/高考选城、考公选岗、买房投资、养老落脚、创业对接政府life-decisions.md(必读)+ 下表联动
帮我选岗/读这条新闻/写分析/给建议怎么跟政府打交道playbooks.md
别写成 AI 空话 / 要像聂老师怎么讲anti-patterns-voice.md

五场景 → 框架联动(个人抉择)

用户场景必读加深
求学life-decisions.md §1tiaokuai-and-rank.md;若涉区划 → rezoning-household.md
考公life-decisions.md §2power-and-positions.md + local-governance.md;村官 → village-fit.md
投资life-decisions.md §3development-dilemmas.md + business-environment.md;设区 → rezoning-household.md
养老life-decisions.md §4tiaokuai-and-rank.md + local-governance.md;设区 → rezoning-household.md
创业life-decisions.md §5development-dilemmas.md + business-environment.md;推项目 → bottom-up-project.md;回乡 → village-fit.md

质量闸门(自检)

  • 用了原书命名框架,不是空泛「要重视基层」
  • 说清了条/块、级、激励中至少一环
  • 给出可执行判断,而非仅情绪共鸣
  • 没把县委书记简化成绝对权力
  • 没编原书没有的数据与制度细节

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Nie Grassroots Logic AI skill do?

聂辉华《基层中国的运行逻辑》方法论工具箱:政治经济学/组织经济学视角解释基层权力与治理, 并落到个人抉择(求学/考公/投资/养老/创业)。 核心框架:内外冲突的双均衡、条块结合以块为主、等级制资源配置(人跟资源走、资源跟权力走)、 职务含权量三因子、县委书记三座大山(维稳/招商/借债)、压力型体制与注意力分配、 政企四象限博弈、土地财政闭环、活力—秩序城市化权衡、上下同治。 当用户要理解基层/县域/乡镇治理、条块矛盾、属地责任、央地关系、官员晋升与考核、 一票否决、形式主义、招商引资、土地财政、地方债、街道办与村官、考公选岗、 高考志愿/选城读书、买房与区域投资风险、回哪养老、创业对接园区政府、 撤县设区/县改市对家庭影响、谁适合当村支书、大学生村官值不值得去、 新型职业农民/致富能手/回乡创业、昆山式改革/自下而上推项目/西气东输式立项、 营商环境比较、投资不过山海关、政商关系亲清、容错创新/基层敢不敢干、 抢高铁站/重大工程争夺、政策为何落地难、解读地方新闻、 或提到聂辉华/基层中国的运行逻辑/上下同治/含权量/条块结合/双均衡时使用。

Why use Nie Grassroots Logic on TypingMind?

Because you install it once and use it with any model. Nie Grassroots Logic 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 Nie Grassroots Logic in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ayi-ai/nie-grassroots-logic/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Nie Grassroots Logic?

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 Nie Grassroots Logic?

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

Is the Nie Grassroots Logic AI skill free?

Yes. It is published on GitHub by ayi-ai under the MIT license. 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 👇