Agent skill

Shishiqiushi Sigao

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

当用户面对大量杂乱信息(用户反馈、竞品数据、市场报告、内部指标)需要从中提取决策信号时激活. An agent skill from kangarooking/mao-selected-works-skill.

MITAuto-check passed

Install Shishiqiushi Sigao

skills CLI
$ npx skills add kangarooking/mao-selected-works-skill --skill shishiqiushi-sigao -a claude-code

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

GitHub CLI
$ gh skill install kangarooking/mao-selected-works-skill shishiqiushi-sigao --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/shishiqiushi-sigao .claude/skills/shishiqiushi-sigao && 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
shishiqiushi-sigao
GitHub stars
115
Token cost
~899 tokens
SKILL.md length
115 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

当用户面对大量杂乱信息(用户反馈、竞品数据、市场报告、内部指标)需要从中提取决策信号时激活. An agent skill from kangarooking/mao-selected-works-skill.

  • Works in 4 steps: 原始信息(用户反馈、数据报表、市场观察)只是"感觉材料",不等于认知。必须经过主动… → 加工分四步,每步不可跳过,且是递进关系 → 四步不是一次性完成,而是反复迭代。每走一轮,认知就更深一层。 → …
  • 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

Shishiqiushi Sigao is an agent skill from kangarooking/mao-selected-works-skill. 当用户面对大量杂乱信息(用户反馈、竞品数据、市场报告、内部指标)需要从中提取决策信号时激活。 典型触发信号:"数据太多了不知道信哪个""用户说什么的都有""收到了一堆反馈但不知道结论是什么"。 不调用场景:信息已经结构化清晰、只需简单判断;或完全没有信息需要凭直觉决策。 与"调查研究法"的区别:本skill是信息处理(拿到原料后怎么加工),后者是信息采集(怎么拿到好的原料)。

Its SKILL.md is about 900 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

  • “数据太多了不知道信哪个”
  • “用户说什么的都有”
  • “收到了一堆反馈但不知道结论是什么”
  • “/shishiqiushi-sigao”

Workflow steps

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

  1. 原始信息(用户反馈、数据报表、市场观察)只是"感觉材料",不等于认知。必须经过主动加工才能变成决策依据。
  2. 加工分四步,每步不可跳过,且是递进关系
  3. 四步不是一次性完成,而是反复迭代。每走一轮,认知就更深一层。
  4. 跳过前面步骤直奔结论("我觉得就是这样")是主观主义;只做到前两步就停下(有干净数据但没有洞察)是经验主义。

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

Shishiqiushi Sigao loads about 899 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 115 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~899

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). 115 words, ~899 tokens.

Download SKILL.mdSave it as .claude/skills/shishiqiushi-sigao/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
shishiqiushi-sigao
description
当用户面对大量杂乱信息(用户反馈、竞品数据、市场报告、内部指标)需要从中提取决策信号时激活。 典型触发信号:"数据太多了不知道信哪个""用户说什么的都有""收到了一堆反馈但不知道结论是什么"。 不调用场景:信息已经结构化清晰、只需简单判断;或完全没有信息需要凭直觉决策。 与"调查研究法"的区别:本skill是信息处理(拿到原料后怎么加工),后者是信息采集(怎么拿到好的原料)。
source_book
《毛泽东选集第1-5卷》 毛泽东
source_chapter
实践论(1937); 中国革命战争的战略问题(1936); 改造我们的学习(1941)
tags
信息加工, 去粗取精, 去伪存真, 决策分析, 数据提炼

R — 原文 (Reading)

"要完全地反映整个的事物,反映事物的本质,反映事物的内部规律性,就必须经过思考作用,将丰富的感觉材料加以去粗取精、去伪存真、由此及彼、由表及里的改造制作工夫,造成概念和理论的系统,就必须从感性认识跃进到理性认识。" — 《实践论》(1937年7月)

I — 方法论骨架 (Interpretation)

  1. 原始信息(用户反馈、数据报表、市场观察)只是"感觉材料",不等于认知。必须经过主动加工才能变成决策依据。
  2. 加工分四步,每步不可跳过,且是递进关系:
    • 去粗取精:过滤噪音,保留关键信号。1000条反馈中可能只有50条是有价值的信息。
    • 去伪存真:识别并排除虚假/失真的数据。水军评论、自嗨式调研、美化过的汇报都是伪。
    • 由此及彼:建立关联。用户反馈与使用数据之间、竞品动态与市场趋势之间的因果和关联。
    • 由表及里:从表面现象深入到深层规律。"用户说想要X"的深层是"用户实际需要Y"。
  3. 四步不是一次性完成,而是反复迭代。每走一轮,认知就更深一层。
  4. 跳过前面步骤直奔结论("我觉得就是这样")是主观主义;只做到前两步就停下(有干净数据但没有洞察)是经验主义。

A1 — 书中应用 (Past Application)

应用1:论持久战 — 从纷繁情报中提炼战略判断
  • 问题:抗战初期各方信息混乱——有说中国必亡的,有说三个月能赢的,战场消息时好时坏。
  • 方法使用:毛泽东用四步加工中日双方的全部信息:去粗取精(过滤情绪化言论,保留硬数据)-> 去伪存真(排除虚假战报和夸大宣传)-> 由此及彼(建立双方强/弱、大/小、进步/退步、多助/寡助的关联分析)-> 由表及里(从表面军事力量对比深入到战争性质、人心向背、国际格局的深层规律)。
  • 结论:持久战三阶段,最终胜利属于中国。
  • 结果:论持久战的预判被八年抗战的实际进程基本验证。
应用2:改造我们的学习 — 用对比法推动认知升级
  • 问题:党内干部用主观主义态度对待信息——不做调查就下结论,割断历史就做判断。
  • 方法使用:毛泽东提出"实事"="客观存在的一切事物","是"="事物的内部联系","求"="去研究"。用"墙上芦苇/山间竹笋"的形象比喻让干部自检信息加工质量。
  • 结论:只有经过"实事求是"加工的信息才能作为决策依据。
  • 结果:改造我们的学习成为延安整风的纲领性文件,推动全党从主观主义向实事求是转变。

A2 — 触发场景 (Future Trigger)

  1. 用户反馈洪水:产品上线后收到大量用户反馈,情绪化抱怨和理性建议混在一起。用户会说:"用户说什么的都有""反馈太多了看不过来""不知道哪些该听哪些不该听"。
  2. 数据矛盾:不同数据源给出矛盾信号——销售说市场很好但留存数据在下降,用户说满意但续费率在降。用户会说:"数据打架了""不知道该信哪个数据"。
  3. 竞品信息过载:竞品动态频繁、行业报告太多,信息量大但可行动的结论少。用户会说:"报告看了一堆但不知道结论""竞品信息太杂了"。
  4. 汇报失真:下级汇报"报喜不报忧",数据被美化,真问题被掩盖。用户会说:"总感觉汇报的东西不真实""数据好看但问题在暗处"。
  5. 决策信息不足:需要在信息不完备的情况下做判断,需要从有限线索中推理。用户会说:"信息不够但必须决策""只能靠这些线索判断"。

语言信号:用户提到"噪音太多""信号""核心信息""数据打架""表面和深层""本质"等词汇时,应激活此skill。

与相邻skill区分:

  • vs 调查研究法:本skill = 加工信息(得到原料后怎么做),后者 = 采集信息(怎么得到好的原料)
  • vs 实践认识论:本skill = 单轮认知加工的技术,后者 = 多轮循环的哲学框架
  • vs 矛盾分析法:本skill = 处理信息的通用步骤,后者 = 找瓶颈的分析框架

E — 可执行步骤 (Execution)

步骤1:去粗取精 + 去伪存真(信息清洗)
  • 将所有原始信息列出来源清单。标注每条信息的:(1) 来源可信度 (2) 是否可交叉验证 (3) 是否情绪化/主观。
  • 过滤掉:情绪化表达、无法验证的单一来源、明显美化/丑化的数据。保留:可交叉验证的硬数据、多来源一致指向的信号。
  • 完成标准:原始信息量缩减到20%以内,剩余信息都有来源标注和可信度评级。
步骤2:由此及彼(建立关联)
  • 将清洗后的信息按维度分类(用户端/产品端/市场端/竞争端),寻找跨维度的关联和因果链。
  • 画出信息关联图:A变化 -> B变化 -> C变化,找出关键的传导路径。
  • 完成标准:至少发现3条跨维度的关联关系,且每条关联都有至少2个独立证据支持。
步骤3:由表及里(深入本质)
  • 对每条关键关联追问"为什么"至少3层:用户为什么这样做?因为___。为什么___?因为___。为什么___?
  • 区分表层需求(用户说的)和深层需求(用户实际需要的),确认你找到的是后者。
  • 判停点:如果追问到第3层仍然只是重复表面的"因为用户喜欢/不喜欢",说明信息深度不够,需要回到步骤1补充更深层的信息(用户访谈而非问卷数据)。
  • 完成标准:产出"表层-深层"对照表,且每条深层洞察都能指导一个具体的行动决策。

B — 边界 (Boundary)

不要使用的场景
  1. 信息已经清晰时:如果数据已经结构化、因果链已经清晰,不需要再过一遍四步法,直接决策。
  2. 需要快速反应时:紧急情况下用直觉和经验做即时判断,事后再用四步法复盘。
  3. 创造性工作:设计、创意等需要发散思维的场景,四步法会压制创造力。
失败模式(来自反例)
  • 党八股(ce08):信息加工变成了形式主义的表演——报告越写越长但核心结论没有,用甲乙丙丁罗列现象但缺乏因果分析。"装腔作势借以吓人"——用权威腔调代替真正的分析。
  • 经验主义(ce02):止步于"去粗取精"阶段,满足于干净的原始数据,但不做"由此及彼、由表及里"的深度思考。结果是有数据没洞察。
  • 表面现象迷惑(ce23):跳过"由表及里"步骤,把暂时现象当作长期趋势。一次败仗就认为"全完了",一次胜仗就以为"势不可挡"。
作者盲点
  • 毛泽东强调"实事求是"但在大跃进时期自己也相信了虚假的亩产数据("去伪存真"环节失效)。教训:信息加工者的立场和愿望会影响"去伪"的判断——越想相信的信息越要严格验证。

相关 skills

  • 实践认识论 (composes-with): 实事求是信息加工法是实践认识论中"感性认识→理性认识"这一飞跃的具体操作技术。实践认识论提供认知循环的整体框架,实事求是四步法提供单次循环中信息加工的具体步骤。
  • 调查研究法 (composes-with): 调查研究法负责"采集高质量的一手信息"(原料获取),实事求是信息加工法负责"把原料加工成决策依据"(原料加工)。先调查采集,再实事求是加工,构成完整的信息处理链条。

© 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 shishiqiushi-sigao of kangarooking/mao-selected-works-skill.

  • SKILL.md
  • test-prompts.json

Open the folder on GitHubat commit 5058fe4

Compare with similar skills

Shishiqiushi Sigao next to the 3 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.

Shishiqiushi Sigao compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Shishiqiushi Sigao this skillkangarooking/mao-selected-works-skill115—~899Automated safety check: PassMIT
Market Analysisqusong0627/QuantMind1.7k—~1kAutomated safety check: PassAGPL-3.0
Jianmiezhan Jizhong Binglikangarooking/mao-selected-works-skill115—~1.1kAutomated safety check: PassMIT
Maodun Techuxingkangarooking/mao-selected-works-skill115—~811Automated safety check: PassMIT

Similar skills

  • Market Analysis

    qusong0627/QuantMind

    市场分析报告(大盘快照版)— 复用市场分析页面全部数据能力:核心指数、市场广度与情绪温度、行业板块/热门概念热力图、行业多日涨跌幅对比(1/3/5日)、板块资金流(1日/5日/10日)、个股主力资金 Top20、标签体系统计。用户说「市场分析」「大盘分析」「行情分析」「今天市场怎么样」「市场报告」时使用:跑取数脚本(marketanalysis.py)→ AI 基于 facts 撰写解读 →…

    1.7k GitHub stars~1k tokensUpdated today
    Documents & OfficeAuto-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 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

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
  • Chijiuzhan San Jieduan

    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.

    115 GitHub stars~1k 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
  • 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
  • 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
  • Shiliuzijue

    kangarooking/mao-selected-works-skill

    当用户需要根据竞争对手的状态选择自己的行动节奏时激活此skill. An agent skill from kangarooking/mao-selected-works-skill.

    115 GitHub stars~951 tokensUpdated 5 mo ago
    Auto-check passed

Questions about Shishiqiushi Sigao

What does Shishiqiushi Sigao do?

当用户面对大量杂乱信息(用户反馈、竞品数据、市场报告、内部指标)需要从中提取决策信号时激活. An agent skill from kangarooking/mao-selected-works-skill. Shishiqiushi Sigao is an agent skill from kangarooking/mao-selected-works-skill.

How do I install Shishiqiushi Sigao in Claude Code?

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

How do I install Shishiqiushi Sigao in Codex?

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

Can I use Shishiqiushi Sigao 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 shishiqiushi-sigao -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shishiqiushi-sigao, .gemini/skills/shishiqiushi-sigao, .github/skills/shishiqiushi-sigao and .opencode/skills/shishiqiushi-sigao in your project.

What does Shishiqiushi Sigao need to run?

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

Does Shishiqiushi Sigao 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 Shishiqiushi Sigao 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 Shishiqiushi Sigao use?

Shishiqiushi Sigao 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 Shishiqiushi Sigao use?

About 899 tokens (SKILL.md is roughly 3.6k 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 Shishiqiushi Sigao?

Skills that share tags, products or a category with Shishiqiushi Sigao: Market Analysis (qusong0627/QuantMind, 1.7k stars), Jianmiezhan Jizhong Bingli (kangarooking/mao-selected-works-skill, 115 stars) and Maodun Techuxing (kangarooking/mao-selected-works-skill, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Shishiqiushi Sigao?

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.