Agent skill

Shijian Renshilun

by kangarooking in 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.

MITAuto-check passed

Install Shijian Renshilun

skills CLI
$ npx skills add kangarooking/mao-selected-works-skill --skill shijian-renshilun -a claude-code

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

GitHub CLI
$ gh skill install kangarooking/mao-selected-works-skill shijian-renshilun --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/shijian-renshilun .claude/skills/shijian-renshilun && 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
shijian-renshilun
GitHub stars
115
Token cost
~961 tokens
SKILL.md length
113 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 6 steps: 认识来源于实践,不是来源于书本、理论或想象。不亲口吃梨子,不可能真正知道梨子的滋味。 → 认识过程分两个飞跃:第一次飞跃是从感性认识(表面的、片面的、现象级的)到理性认识(… → 第二次飞跃是从理性认识回到实践——这是"更重要"的一次。理论不被实践验证就是空谈。… → …
  • 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

Shijian Renshilun is an agent skill from 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。 典型触发信号:"我需要先做完研究再开始""不知道够不够了解这个行业就创业""我们一直在做但没有方法论"。 不调用场景:已经有成熟方法论且在有效运转的场景、纯理论学习需求。 与"实事求是信息加工法"的区别:本skill关注完整的认知循环(实践-认识-再实践),后者关注单次循环中信息加工的具体技术。

Its SKILL.md is about 960 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

  • “(想做但不敢行动)或”
  • “(做了但不总结不提升)时激活此skill。 典型触发信号:”
  • “不知道够不够了解这个行业就创业”
  • “/shijian-renshilun”

Workflow steps

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

  1. 认识来源于实践,不是来源于书本、理论或想象。不亲口吃梨子,不可能真正知道梨子的滋味。
  2. 认识过程分两个飞跃:第一次飞跃是从感性认识(表面的、片面的、现象级的)到理性认识(本质的、全面的、规律级的)。这不是自动发生的,需要"去粗取精"的主动加工。
  3. 第二次飞跃是从理性认识回到实践——这是"更重要"的一次。理论不被实践验证就是空谈。"实践是检验真理的唯一标准"。
  4. 整体是螺旋上升而非线性进步:实践->认识->再实践->再认识,每次循环都比上一次更接近真相。
  5. 两个常见错误:(1) 停在感性阶段——做了但不总结,永远凭感觉做事(经验主义);(2) 停在理性阶段——研究了很多但不行动,纸上谈兵(教条主义)。
  6. "读书是学习,使用也是学习,而且是更重要的学习"——不是先学好了再干,而是干起来再学习。

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

Shijian Renshilun loads about 961 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 113 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~961

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). 113 words, ~961 tokens.

Download SKILL.mdSave it as .claude/skills/shijian-renshilun/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
shijian-renshilun
description
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。 典型触发信号:"我需要先做完研究再开始""不知道够不够了解这个行业就创业""我们一直在做但没有方法论"。 不调用场景:已经有成熟方法论且在有效运转的场景、纯理论学习需求。 与"实事求是信息加工法"的区别:本skill关注完整的认知循环(实践-认识-再实践),后者关注单次循环中信息加工的具体技术。
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
认识论, 感性到理性, 迭代思维, 反教条主义, 实践验证

R — 原文 (Reading)

"你要有知识,你就得参加变革现实的实践。你要知道梨子的滋味,你就得变革梨子,亲口吃一吃。你要知道原子的组织同性质,你就得实行物理学和化学的实验。你要知道革命的理论和方法,你就得参加革命。一切真知都是从直接经验发源的。" — 《实践论》(1937年7月)

I — 方法论骨架 (Interpretation)

  1. 认识来源于实践,不是来源于书本、理论或想象。不亲口吃梨子,不可能真正知道梨子的滋味。
  2. 认识过程分两个飞跃:第一次飞跃是从感性认识(表面的、片面的、现象级的)到理性认识(本质的、全面的、规律级的)。这不是自动发生的,需要"去粗取精"的主动加工。
  3. 第二次飞跃是从理性认识回到实践——这是"更重要"的一次。理论不被实践验证就是空谈。"实践是检验真理的唯一标准"。
  4. 整体是螺旋上升而非线性进步:实践->认识->再实践->再认识,每次循环都比上一次更接近真相。
  5. 两个常见错误:(1) 停在感性阶段——做了但不总结,永远凭感觉做事(经验主义);(2) 停在理性阶段——研究了很多但不行动,纸上谈兵(教条主义)。
  6. "读书是学习,使用也是学习,而且是更重要的学习"——不是先学好了再干,而是干起来再学习。

A1 — 书中应用 (Past Application)

应用1:实践论的写作动机 — 反对两种错误
  • 问题:1937年党内存在两种错误倾向——教条主义者照搬苏联经验不看中国实际,经验主义者只凭局部经验拒绝理论提升。
  • 方法使用:毛泽东写实践论不是为了纯哲学,而是为了纠正这两种实践中的认识论错误。他用"延安来考察的外来者"为例:先看到地形街道(感性)-> 收集材料后"想一想" -> 得出理性判断 -> 回到实践中验证。
  • 结论:正确的认识路径是"实践-认识-再实践-再认识"的无限循环,不是一次性完成的。
  • 结果:实践论与实践论并列为毛泽东哲学思想的两大基石,为后续一切方法论提供认识论基础。
应用2:从战争学习战争 — 指挥员的成长路径
  • 问题:红军极度缺乏有经验的军事指挥员,不可能先送军校学习再上战场。
  • 方法使用:毛泽东提出"从战争学习战争"——先干起来,在实战中积累感性认识,然后总结提炼为战术原则(理性认识),再在下一场战斗中验证和修正。
  • 结论:"常常不是先学好了再干,而是干起来再学习,干就是学习。"
  • 结果:红军从游击战中总结出一整套独特战术体系(十六字诀、集中兵力等),这些都不是从书本学来的,而是从实践中提炼出来的。

A2 — 触发场景 (Future Trigger)

  1. 分析瘫痪/过度准备:团队花了大量时间做调研、写方案、做计划,但迟迟不行动。用户会说:"我还需要更多数据才能决定""再研究研究""先做个完整的市场分析"。
  2. 盲目执行/不总结:团队一直在做但从不复盘,重复犯同样的错误,经验不沉淀。用户会说:"做了很多但好像没有进步""每次都是同样的问题""忙但不知道在忙什么"。
  3. 进入新领域:要进入一个没有经验的行业或做一种没做过的事情。用户会说:"我对这个行业不了解,不敢开始""没有经验能做吗"。
  4. 理论与实践脱节:学了很多方法论但落地效果不好,或实践很有效但无法系统化。用户会说:"理论都懂但不知道怎么用""做得很好但说不清为什么好"。
  5. 迭代停滞:产品/业务做了很多版本但每一版都没有本质提升。用户会说:"一直在迭代但没有突破""每次改的都是表面"。

语言信号:用户提到"先学好再干""边做边学""复盘""迭代""MVP""验证假设""知行合一"等词汇时,应激活此skill。

与相邻skill区分:

  • vs 实事求是信息加工法:本skill = 认知循环的整体框架,后者 = 单次循环中"感性->理性"的具体加工技术
  • vs 调查研究法:本skill关注"行动-认知"的循环提升,后者关注"如何正确采集一手信息"
  • vs 矛盾特殊性原则:本skill解决"怎么获得正确的认识",后者解决"对不同认识对象该用什么方法"

E — 可执行步骤 (Execution)

步骤1:确定当前所处阶段
  • 判断用户/团队当前处于循环的哪个位置:(A) 缺乏感性认识(还没动手做)?(B) 有感性认识但未提炼(做了但不总结)?(C) 有理性认识但未验证(有理论但没实践过)?(D) 已经过一轮循环需要进入下一轮?
  • 完成标准:明确说出"当前处于___阶段,下一步应该___"。
步骤2:推动飞跃(执行关键动作)
  • 如果处于(A):设计最小可行实践(MVP/快速试验),获得第一批感性认识。不要追求完美,先"亲口尝一尝"。
  • 如果处于(B):安排复盘会,用"实事求是四步法"从经验中提炼规律。追问:做了什么?为什么有效/无效?底层规律是什么?
  • 如果处于(C):制定验证计划,把理论拿到实践中检验。设定明确的验证标准:如果___现象出现,说明理论正确;如果___出现,说明需要修正。
  • 判停点:如果感性认识严重不足(连基本事实都没搞清楚),不要急于提炼规律——先补足实践。
步骤3:螺旋进入下一轮
  • 完成一轮循环后,明确标注"本轮新认知"(相比上一轮知道了什么新的东西),然后设计下一轮的实践计划。
  • 检查是否出现了新的矛盾或新的认知盲区,如果有,进入下一轮循环。
  • 完成标准:写出"第N轮循环总结:我们之前以为___,实践证明___,新的认知是___,下一轮我们将验证___。"

B — 边界 (Boundary)

不要使用的场景
  1. 高风险一次性决策:有些决策只有一次机会(如重大投资、并购),不能"先试试再迭代",必须充分准备后一次性做好。
  2. 已有成熟方法论领域:在已经被充分验证的标准化操作中(如基础编程、财务做账),直接学习成熟方法比从零开始"实践出真知"效率高得多。
  3. 纯理论/学术研究:有些认知活动本身就是理性层面的工作(数学证明、逻辑推理),不需要每次都回到实践中验证。
失败模式(来自反例)
  • 教条主义(ce01):从理性出发但不回到实践——学了很多理论但从不验证,或面对与理论矛盾的事实仍然坚持理论。本质是只有第二次飞跃没有第一次。
  • 经验主义(ce02):永远停留在感性阶段——做了很多事但不总结不提炼,"我之前这样做成功了"但不分析为什么。本质是只有第一次飞跃没有第二次。
  • 盲动主义(ce10):连感性认识阶段都没有就冲——不分析主客观条件就行动,"只想大干,充满着幻想"。本质是连循环的起点都不具备就强行启动。
作者盲点
  • 毛泽东强调"实践是检验真理的标准",但在某些时期(如大跃进)不尊重实践反馈——当实践结果与理论矛盾时,选择了修改数据而非修正理论。教训:实践认识论的有效性取决于你真的愿意接受实践的否定性结论。

相关 skills

  • 矛盾分析法 (composes-with): 实践认识论提供认知循环的整体框架,矛盾分析法是这个循环中的核心分析工具——在实践中发现问题,用矛盾分析诊断问题,再回到实践中验证。
  • 实事求是信息加工法 (composes-with): 实事求是四步法(去粗取精、去伪存真、由此及彼、由表及里)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。
  • 在战争中学习战争 (composes-with): "在战争中学习战争"是实践认识论在"行动 vs 学习"矛盾中的具体操作原则——不是先学好了再干,而是干起来再学习。

© 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 shijian-renshilun of kangarooking/mao-selected-works-skill.

  • SKILL.md
  • test-prompts.json

Open the folder on GitHubat commit 5058fe4

Compare with similar skills

Shijian Renshilun next to the 4 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.

Shijian Renshilun compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Shijian Renshilun this skillkangarooking/mao-selected-works-skill115—~961Automated safety check: PassMIT
Jianmiezhan Jizhong Binglikangarooking/mao-selected-works-skill115—~1.1kAutomated safety check: PassMIT
Maodun Techuxingkangarooking/mao-selected-works-skill115—~811Automated safety check: PassMIT
Buduicheng Zhanluekangarooking/mao-selected-works-skill115—~892Automated safety check: PassMIT
Zhudongxing Linghuoxing Jihuaxingkangarooking/mao-selected-works-skill115—~981Automated safety check: PassMIT

Similar skills

  • 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
  • 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
  • Zhudongxing Linghuoxing Jihuaxing

    kangarooking/mao-selected-works-skill

    当用户的团队执行力出了问题——OKR完不成、计划总变、团队被动等指令——时激活此skill. An agent skill from kangarooking/mao-selected-works-skill.

    115 GitHub stars~981 tokensUpdated 5 mo ago
    Business, Finance & HRAuto-check passed

More from kangarooking/mao-selected-works-skill

All 13 skills in this repo
  • 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
  • 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
  • Shishiqiushi Sigao

    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.

    115 GitHub stars~899 tokensUpdated 5 mo ago
    Auto-check passed
  • Xingxingzhihuo Genjudi

    kangarooking/mao-selected-works-skill

    当用户处于早期弱小阶段、需要规划从0到1的扩张路径时激活此skill. An agent skill from kangarooking/mao-selected-works-skill.

    115 GitHub stars~1k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Shijian Renshilun

What does Shijian Renshilun do?

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. Shijian Renshilun is an agent skill from kangarooking/mao-selected-works-skill.

How do I install Shijian Renshilun in Claude Code?

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

How do I install Shijian Renshilun in Codex?

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

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

What does Shijian Renshilun need to run?

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

Does Shijian Renshilun 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 Shijian Renshilun 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 Shijian Renshilun use?

Shijian Renshilun 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 Shijian Renshilun use?

About 961 tokens (SKILL.md is roughly 3.8k 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 Shijian Renshilun?

Skills that share tags, products or a category with Shijian Renshilun: Jianmiezhan Jizhong Bingli (kangarooking/mao-selected-works-skill, 115 stars), Maodun Techuxing (kangarooking/mao-selected-works-skill, 115 stars), Buduicheng Zhanlue (kangarooking/mao-selected-works-skill, 115 stars) and Zhudongxing Linghuoxing Jihuaxing (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 Shijian Renshilun?

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.