Agent skill

Chijiuzhan San Jieduan

by kangarooking in kangarooking/mao-selected-works-skill

当用户面对明显强于自己的对手(巨头入场、资源差距、品牌劣势)需要规划长期竞争策略时激活. An agent skill from kangarooking/mao-selected-works-skill.

MITAuto-check passed

Install Chijiuzhan San Jieduan

skills CLI
$ npx skills add kangarooking/mao-selected-works-skill --skill chijiuzhan-san-jieduan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kangarooking/mao-selected-works-skill chijiuzhan-san-jieduan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kangarooking/mao-selected-works-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/chijiuzhan-san-jieduan .claude/skills/chijiuzhan-san-jieduan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
chijiuzhan-san-jieduan
GitHub stars
115
Token cost
~1k tokens
SKILL.md length
110 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

当用户面对明显强于自己的对手(巨头入场、资源差距、品牌劣势)需要规划长期竞争策略时激活. An agent skill from kangarooking/mao-selected-works-skill.

  • Works in 5 steps: 面对强敌,不要幻想速胜(速胜论),也不要认为必败(亡国论)。正确认知是:弱者可以通… → 三阶段模型 → 三阶段的驱动力不是时间而是矛盾转化:强/弱、大/小、进步/退步、多助/寡助四对矛盾… → …
  • SKILL.md covers R — 原文 (Reading), I — 方法论骨架 (Interpretation), A1 — 书中应用 (Past Application) and A2 — 触发场景 (Future Trigger), plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Chijiuzhan San Jieduan is an agent skill from kangarooking/mao-selected-works-skill. 当用户面对明显强于自己的对手(巨头入场、资源差距、品牌劣势)需要规划长期竞争策略时激活。 典型触发信号:"大公司也要做我们这个赛道了""他们的资源是我们的100倍""打不过怎么办"。 不调用场景:势均力敌或自身占优的竞争态势、短期可以解决的挑战、非竞争性决策。 与"集中优势兵力"的区别:本skill规划整体时间线和阶段策略,后者规划具体战役的资源投放方式。

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `test-prompts.json`).

The repository describes itself as: An AI skill pack distilling Selected Works of Mao Zedong into reusable cognition, strategy, organization, and execution modules. The licence is MIT.

Example prompts

  • “大公司也要做我们这个赛道了”
  • “他们的资源是我们的100倍”
  • “打不过怎么办”
  • “/chijiuzhan-san-jieduan”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 面对强敌,不要幻想速胜(速胜论),也不要认为必败(亡国论)。正确认知是:弱者可以通过持久战最终获胜,但过程漫长且分阶段。
  2. 三阶段模型
  3. 三阶段的驱动力不是时间而是矛盾转化:强/弱、大/小、进步/退步、多助/寡助四对矛盾在动态变化。强者消耗、弱者积累,力量对比最终逆转。
  4. 每个阶段的战略任务和操作原则不同——不能在防御期用反攻期的打法,反之亦然。
  5. 第二阶段(相持期)最痛苦但也最关键。能否熬过相持期决定了最终的胜负。

What it can do on your machine

Read from SKILL.md and the folder at commit 5058fe4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Chijiuzhan San Jieduan loads about 1k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 110 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kangarooking/mao-selected-works-skill at commit 5058fe4, republished under its MIT licence (© kangarooking). 110 words, ~1,012 tokens.

Download SKILL.mdSave it as .claude/skills/chijiuzhan-san-jieduan/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
chijiuzhan-san-jieduan
description
当用户面对明显强于自己的对手(巨头入场、资源差距、品牌劣势)需要规划长期竞争策略时激活。 典型触发信号:"大公司也要做我们这个赛道了""他们的资源是我们的100倍""打不过怎么办"。 不调用场景:势均力敌或自身占优的竞争态势、短期可以解决的挑战、非竞争性决策。 与"集中优势兵力"的区别:本skill规划整体时间线和阶段策略,后者规划具体战役的资源投放方式。
source_book
《毛泽东选集第1-5卷》 毛泽东
source_chapter
论持久战(1938); 中国革命战争的战略问题(1936); 星星之火可以燎原(1930)
tags
持久战, 三阶段模型, 以弱胜强, 长期战略, 阶段规划

R — 原文 (Reading)

"中国由劣势到平衡到优势,日本由优势到平衡到劣势,中国由防御到相持到反攻,日本由进攻到保守到退却——这就是中日战争的过程,中日战争的必然趋势。" — 《论持久战》(1938年5月)

I — 方法论骨架 (Interpretation)

  1. 面对强敌,不要幻想速胜(速胜论),也不要认为必败(亡国论)。正确认知是:弱者可以通过持久战最终获胜,但过程漫长且分阶段。
  2. 三阶段模型:
    • 防御期:敌强我弱,核心任务是"活下来"。守住基本盘,不硬碰硬,积蓄力量。
    • 相持期("转变的枢纽"):双方力量趋于平衡,最痛苦也最关键。深耕细分领域,积累数据和信任,等待对手犯错。
    • 反攻期:我方积累的优势开始释放,对手的弱点暴露。在对手力所不及的领域全面扩张。
  3. 三阶段的驱动力不是时间而是矛盾转化:强/弱、大/小、进步/退步、多助/寡助四对矛盾在动态变化。强者消耗、弱者积累,力量对比最终逆转。
  4. 每个阶段的战略任务和操作原则不同——不能在防御期用反攻期的打法,反之亦然。
  5. 第二阶段(相持期)最痛苦但也最关键。能否熬过相持期决定了最终的胜负。

A1 — 书中应用 (Past Application)

应用1:论持久战 — 三阶段模型的构建与验证
  • 问题:抗战初期,"亡国论"(中国必亡)和"速胜论"(三个月结束)两种错误观点盛行,无法形成正确战略。
  • 方法使用:毛泽东在抗战仅10个月时就构建了三阶段模型。他不是凭直觉,而是基于四对矛盾在时间维度上的变化规律推导出来:第一阶段敌之优势会被消耗,第二阶段双方趋于平衡,第三阶段中国积累的优势释放。
  • 结论:持久战三阶段,防御->相持->反攻,最终胜利属于中国。关键是不要在第一阶段就全面对攻(速胜论),也不要觉得打不过就放弃(亡国论)。
  • 结果:八年抗战的实际进程(1937-1945)基本按三阶段模型发展,验证了这一框架的预见力。
应用2:星星之火可以燎原 — 弱小力量的长期发展预判
  • 问题:1930年红军极度弱小,党内弥漫"红旗到底打得多久"的悲观。
  • 方法使用:毛泽东没有用鸡汤安慰,而是用矛盾分析法论证弱小力量的发展必然性:统治阶级内部矛盾不可调和->军阀混战->农村权力真空->红色政权可以存在和发展。
  • 结论:不是"希望"会赢,而是"逻辑上必然"会赢。力量对比会随时间转化。
  • 结果:从1930年不到1万人的红军,经过波浪式推进,最终在1949年取得全国胜利。

A2 — 触发场景 (Future Trigger)

  1. 巨头入场:大公司宣布进入你的赛道,团队恐慌或想要投降。用户会说:"Google/腾讯/字节也要做这个了""他们有钱有人我们怎么打""是不是该转型了"。
  2. 资源极度劣势:竞争对手的资金、团队、品牌远超自己。用户会说:"对手资源是我们的10倍""他们可以亏三年我们不能"。
  3. 陷入消耗战:与对手的竞争陷入拉锯,看不到终局。用户会说:"打了一年还在拉锯""这样下去谁先死""什么时候能赢"。
  4. 团队士气低落:长期处于劣势导致团队怀疑方向。用户会说:"团队开始怀疑能不能赢""有人想放弃""士气很低"。
  5. 急于一搏的冲动:形势稍有好转就想全面对攻。用户会说:"机会来了,该全力进攻了吧""我觉得可以正面对抗了"。

语言信号:用户提到"打不过""巨头""以弱胜强""长期竞争""熬过去""什么时候能翻盘"等词汇时,应激活此skill。

与相邻skill区分:

  • vs 集中优势兵力歼灭战:本skill = 整体战争的时间规划(战略层面),后者 = 具体战役的打法(战术层面)
  • vs 矛盾分析法:本skill是矛盾分析法在"以弱对强"场景下的具体应用
  • vs 战略-战术辩证法:本skill规划宏观阶段节奏,后者处理每个阶段内"防守中的进攻"等辩证问题

E — 可执行步骤 (Execution)

步骤1:判断当前所处阶段
  • 用四对矛盾(资源对比、规模对比、增长势能/创新力对比、外部支持/生态优势对比)评估敌我力量对比。
  • 判断当前处于三阶段中的哪一段:如果对手在全面进攻且我方在收缩=防御期;如果双方在拉锯且力量趋于平衡=相持期;如果我方在某些领域开始主动出击=反攻期。
  • 完成标准:明确回答"我们当前处于___期,判断依据是___。"
步骤2:制定阶段性策略
  • 防御期策略:守住核心客户群和差异化壁垒,不全面对攻。目标是"活下来",指标是现金流和核心客户留存率。砍掉非核心支出,把资源集中到防守核心。
  • 相持期策略:深耕细分领域,积累对手无法复制的数据/用户信任/行业know-how。目标是"建立不对称优势",指标是垂直市场占有率和用户粘性。这是最痛苦的阶段,要提前做好心理准备。
  • 反攻期策略:在对手力所不及的领域全面扩张。目标是"扩大战果",指标是市场份额和收入增长。利用积累的信任和数据优势快速推进。
  • 判停点:如果在防御期就想全面对攻(速胜论冲动),立即叫停——退回防御。如果在反攻期还缩手缩脚(怯懦),立即加码——机会窗口有限。
  • 完成标准:产出阶段性策略卡——"当前阶段___,核心目标___,关键指标___,绝对不做___。"
步骤3:设定阶段转化条件和复盘节点
  • 为每个阶段设定明确的"转化信号":什么数据/事件出现意味着可以进入下一阶段?
  • 防御->相持:对手放缓进攻节奏 + 我方核心客户流失率趋稳
  • 相持->反攻:我在细分领域市占率第一 + 对手在细分领域投入减少或退出
  • 设定季度复盘节点,重新评估四对矛盾的力量对比。
  • 完成标准:写出"阶段转化条件清单"——当___出现时,我们从___期进入___期。

B — 边界 (Boundary)

不要使用的场景
  1. 势均力敌或自身占优:三阶段模型是为"以弱对强"设计的。如果双方实力相当或自身占优,用更直接的竞争策略即可。
  2. 短期可解决的挑战:如果问题可以在3-6个月内解决,不需要长期的三阶段规划,用集中兵力速战速决。
  3. 非竞争性决策:内部管理、产品开发等非竞争场景不需要三阶段模型。
失败模式(来自反例)
  • 速胜论(ce05):在防御期就急于决战——"急性病的速胜论者熬不过持久战的艰难路程,企图速胜"。稍有成绩就想"一举拿下"更大目标。这恰好中了强者的计:强者最怕持久战,最希望弱者急于决战。
  • 亡国论/投降主义(ce06):面对强敌直接放弃——"打不过,不如投降或转型"。没有分析强弱背后的四对矛盾,只看到表面的资源差距。
  • 八月失败(ce03):在条件不成熟时冒进——不分析当前所处阶段就采取下一阶段的打法。在对手暂时稳定的时期采取了对手内部分裂时期才适用的冒进策略。
  • 逃跑主义(ce16):遇到挫折就从冒进极端跳到逃跑极端——不做理性分析就全面放弃。
作者盲点
  • 毛泽东的三阶段模型基于抗战时期的特殊条件(正义/非正义、大国/小国等),不能机械套用。商业竞争中,"强者"可能变得更强(赢者通吃的互联网效应),"弱者"未必能自然积累优势。必须在分析矛盾转化的实际条件后才能应用。

相关 skills

  • 矛盾分析法 (depends-on): 持久战三阶段模型是矛盾分析法在"以弱对强"场景下的具体应用——用四对矛盾(强/弱、大/小、进步/退步、多助/寡助)的转化推导出三阶段战略。先掌握矛盾分析法,才能理解持久战的推导逻辑。
  • 战略-战术辩证法 (composes-with): 持久战规划宏观三阶段的时间线,战略-战术辩证法处理每个阶段内"防守中进攻"的微观操作。宏观阶段规划与微观攻守辩证的配合。
  • 战略藐视战术重视 (composes-with): 持久战的长期性要求团队保持战略信心("最终能赢"),同时每个阶段的操作要求战术谨慎(不可冒进不可畏缩)。战略藐视战术重视提供贯穿三阶段的心态管理。

© kangarooking, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in chijiuzhan-san-jieduan of kangarooking/mao-selected-works-skill.

  • SKILL.md
  • test-prompts.json

Open the folder on GitHubat commit 5058fe4

Compare with similar skills

Chijiuzhan San Jieduan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Chijiuzhan San Jieduan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Chijiuzhan San Jieduan this skillkangarooking/mao-selected-works-skill115—~1kAutomated safety check: PassMIT
Azure Elastic SanMicrosoftDocs/Agent-Skills776—~2kAutomated safety check: PassCC-BY-4.0
20 Brief Client Intakeminhnv0807/ai-business-skills609—~2.9kAutomated safety check: PassMIT
Triaging Security Incidentmukul975/Anthropic-Cybersecurity-Skills34k—~2.3kAutomated safety check: PassApache-2.0
Implementing Ot Incident Response Playbookmukul975/Anthropic-Cybersecurity-Skills34k—~4.2kAutomated safety check: PassApache-2.0
Exploiting Adcs With Certipymukul975/Anthropic-Cybersecurity-Skills34k—~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Azure Elastic San

    MicrosoftDocs/Agent-Skills

    Official

    Expert knowledge for Azure Elastic SAN development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations…

    776 GitHub stars~2k tokensUpdated 5 days ago
    DevelopmentAuto-check passed
  • 20 Brief Client Intake

    minhnv0807/ai-business-skills

    Dung khi agency hoac freelancer nhan khach moi va can CHINH KHACH DIEN thong tin dau vao — form 11 phan ve san pham, muc tieu, ngan sach, kenh dang chay, doi thu, tai san san co, kem 20 ban toi uu…

    609 GitHub stars~2.9k tokensUpdated 29 days ago
    Product & Project ManagementAuto-check passed
  • Triaging Security Incident

    mukul975/Anthropic-Cybersecurity-Skills

    Performs initial triage of security incidents using the NIST SP 800-61r3 and SANS PICERL frameworks, classifying incident type, assigning priority by business impact, and routing to the appropriate…

    34k GitHub stars~2.3k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Implementing Ot Incident Response Playbook

    mukul975/Anthropic-Cybersecurity-Skills

    Develops OT-specific incident response playbooks using a SANS PICERL-based Python engine that classifies incident severity (safety, process, access, recon) and coordinates IT SOC, OT engineering…

    34k GitHub stars~4.2k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Exploiting Adcs With Certipy

    mukul975/Anthropic-Cybersecurity-Skills

    Use Certipy to enumerate AD CS certificate authorities and templates over LDAP/RPC, then exploit ESC1-ESC16 misconfigurations - SAN abuse, NTLM relay to web enrollment (ESC8), Shadow Credentials…

    34k GitHub stars~2.7k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Product Marketing Context

    minhnv0807/ai-business-skills

    Dung khi bat dau lam viec voi mot san pham hoac khach hang moi — skill nay tao FILE CONTEXT ma hon 60 skill khac se doc, gom san pham, khach hang, dinh vi, proof, objection, brand voice va KPI.

    609 GitHub stars~2.1k tokensUpdated 29 days ago
    Writing & ContentAuto-check passed

More from kangarooking/mao-selected-works-skill

All 13 skills in this repo
  • Buduicheng Zhanlue

    kangarooking/mao-selected-works-skill

    当用户作为弱势方面对强势竞争者、感觉"处处被动无法招架"时激活此skill. An agent skill from kangarooking/mao-selected-works-skill.

    115 GitHub stars~892 tokensUpdated 5 mo ago
    Auto-check passed
  • Diaocha Yanjiu

    kangarooking/mao-selected-works-skill

    当用户即将基于二手信息(报告、传闻、他人的总结)做重大决策,或团队出现了"坐在办公室拍脑袋"的倾向时激活. An agent skill from kangarooking/mao-selected-works-skill.

    115 GitHub stars~905 tokensUpdated 5 mo ago
    Auto-check passed
  • Jianmiezhan Jizhong Bingli

    kangarooking/mao-selected-works-skill

    当用户资源有限但面临多个机会/威胁,需要在多个方向间做取舍时激活。典型触发信号: "5个客户机会同时出现""要不要同时做ToB和ToC""资源不够分怎么办"。

    115 GitHub stars~1.1k tokensUpdated 5 mo ago
    Auto-check passed
  • Maodun Fenxi

    kangarooking/mao-selected-works-skill

    当用户面对多个相互交织的问题、无法判断优先级、陷入"什么都重要"的决策瘫痪时激活此skill. An agent skill from kangarooking/mao-selected-works-skill.

    115 GitHub stars~914 tokensUpdated 5 mo ago
    Auto-check passed
  • Maodun Techuxing

    kangarooking/mao-selected-works-skill

    当用户准备套用一个成功方法论(别人的或自己过去的)到新场景时激活此skill。典型触发信号: "某公司用了X方法成功了,我们也该试试""我之前这么做有效,继续做""行业最佳实践是Y"。

    115 GitHub stars~811 tokensUpdated 5 mo ago
    Auto-check passed
  • Shijian Renshilun

    kangarooking/mao-selected-works-skill

    当用户陷入"分析瘫痪"(想做但不敢行动)或"盲目行动"(做了但不总结不提升)时激活此skill. An agent skill from kangarooking/mao-selected-works-skill.

    115 GitHub stars~961 tokensUpdated 5 mo ago
    Auto-check passed

Questions about Chijiuzhan San Jieduan

What does Chijiuzhan San Jieduan do?

当用户面对明显强于自己的对手(巨头入场、资源差距、品牌劣势)需要规划长期竞争策略时激活. An agent skill from kangarooking/mao-selected-works-skill. Chijiuzhan San Jieduan is an agent skill from kangarooking/mao-selected-works-skill.

How do I install Chijiuzhan San Jieduan in Claude Code?

Run `npx skills add kangarooking/mao-selected-works-skill --skill chijiuzhan-san-jieduan -a claude-code`. Or copy the skill folder (chijiuzhan-san-jieduan in kangarooking/mao-selected-works-skill) into .claude/skills/chijiuzhan-san-jieduan in your project. Claude Code loads it when a task matches its description.

How do I install Chijiuzhan San Jieduan in Codex?

Run `npx skills add kangarooking/mao-selected-works-skill --skill chijiuzhan-san-jieduan -a codex`. Or copy the skill folder (chijiuzhan-san-jieduan in kangarooking/mao-selected-works-skill) into .agents/skills/chijiuzhan-san-jieduan in your project. Codex loads it when a task matches its description.

Can I use Chijiuzhan San Jieduan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kangarooking/mao-selected-works-skill --skill chijiuzhan-san-jieduan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chijiuzhan-san-jieduan, .gemini/skills/chijiuzhan-san-jieduan, .github/skills/chijiuzhan-san-jieduan and .opencode/skills/chijiuzhan-san-jieduan in your project.

What does Chijiuzhan San Jieduan need to run?

SKILL.md names no scripts, command-line tools or credentials: Chijiuzhan San Jieduan is instructions for the agent only.

Does Chijiuzhan San Jieduan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Chijiuzhan San Jieduan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Chijiuzhan San Jieduan use?

Chijiuzhan San Jieduan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Chijiuzhan San Jieduan use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Chijiuzhan San Jieduan?

Skills that share tags, products or a category with Chijiuzhan San Jieduan: Azure Elastic San (MicrosoftDocs/Agent-Skills, 776 stars), 20 Brief Client Intake (minhnv0807/ai-business-skills, 609 stars), Triaging Security Incident (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Implementing Ot Incident Response Playbook (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chijiuzhan San Jieduan?

kangarooking (a GitHub user) maintains it in kangarooking/mao-selected-works-skill, which has 115 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on May 2, 2026.

Source: kangarooking/mao-selected-works-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.