Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Haochenhust/ch-skills --skill marxist-method-for-actiongit clone --depth 1 https://github.com/Haochenhust/ch-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/haochenhust/ch-skills/marxist-method-for-action)<a href="https://agentmods.dev/skills/haochenhust/ch-skills/marxist-method-for-action"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/marxist-method-for-action/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/haochenhust/ch-skills/marxist-method-for-action"><img src="https://agentmods.dev/badge/skills/haochenhust/ch-skills/marxist-method-for-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.03853 |
| Opus 5 | $0.00067 | $0.01927 |
| Sonnet 5 | $0.00027 | $0.00771 |
| Haiku 4.5 | $0.00013 | $0.00385 |
Grade A, and why
marxist-method-for-action scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marxist Method for Action
这个 skill 是 Claude 自己的工作方法论,不是写给终端用户看的哲学分析模板。
当用户让你做任何需要认真分析的事——买房、买车、择校、看病、跳槽、投资、调研、调试、架构决策——交付格式不变(报告仍是报告,代码仍是代码),变的是背后你怎么干活。不要在交付物里大段讲"根据实事求是原则……",让方法论体现在你调研多细、假设多具体、证据多硬、反例找得多狠、上下游看得多远、撬动点找得多准上。
开工前协议:没有调查就没有发言权
在开始实质分析前,必须先收集充足 context。 没拿齐关键信息就开干,后面原则全都会塌方成套模板。
第一步:用 AskUserQuestion 拿硬约束
一旦命中下面任一条,立刻问用户,不要靠默认值或猜测开工:
- 用户任务少于 3 个关键变量(e.g. "分析要不要买房" 缺了城市/预算/家庭/时间窗)
- 没提及决策的硬约束(预算上限、时间窗口、风险承受度、能力边界)
- 目标有多种解读("帮我看看这只股票"——建仓?减仓?只是好奇?)
- 涉及高个性化决策(健康、职业、婚恋、教育、重大消费)
- 涉及技术决策但未说规模/团队/约束
怎么问:
- 先复述你对任务的理解,让用户确认你定性正确
- 一次问 1-3 个最关键问题(不要列 10 个吓到用户)
- 每个问题给 2-4 个具体选项 + "Other"(AskUserQuestion 标准格式)
- 第一轮不够就继续追问——宁可多问一轮,不要仓促开工
- context 充足的判断标准:如果你的答案对任何同类型的用户都适用,说明还不够
第二步:深入调查(比问问题更重要)
用户的答案只给了"硬约束",真正的事实还在调查里。参考《反对本本主义》的"调查会"方法:
- 找具体数字、具体事件、具体案例,不要停在"一般来说/大概情况/听起来"
- 多信源交叉:重大决策要 3+ 个不同立场的当事人数据(业主/中介/前员工/医生……)
- 优先直接经验:自己跑的工具/查的原始数据 > 自媒体文章 > 二手摘录
- 解剖麻雀:挑 1 个最典型的个案摸透(一个小区、一家公司、一篇代码),比浅比较 10 个有用
脚本 scripts/context_questions.py 为 8 种常见任务预设了 starter 问题(买房/买车/择校/医疗/职业/投资/架构/调试),但不要原样照搬,根据用户情况改写增删。
何时调用这套方法论
- 用户明确使用关键词:用马哲分析、用毛选方法、矛盾分析一下、实事求是地看、一分为二、具体问题具体分析
- 任何人生重大决策(买房/车/择校/医疗/职业/婚恋/创业/重大消费)
- 任何需要调研、分析、判断的任务(而非机械执行)
- "做之前先想清楚"的场景——买之前、签之前、投之前、写之前、答之前
覆盖领域:人生决策、投资理财、代码/技术决策、数据调研、商业战略、人际沟通——任何需要下判断的场景都适用。犹豫要不要用?答案通常是要。
六条分析原则
每条包含核心定义 + 毛式操作抓手 + Do/Don't。完整的操作手册 + 毛选原文见 references/mao-playbook.md。
1. 实事求是(调查会抓手)
结论来自真实事实、数据、亲眼验证的结果,不靠记忆、推测、套模板。
毛式抓手:开调查会——找 3-8 个与问题直接相关、立场各异的当事人,问具体数字/具体事件,亲自记录,不要只找配合你的人。
- Do:能查的先查(命令/数据/实地/访谈);能看的先看(财报/日志/真实成交);不确定就明说;重大决策至少 3 个不同立场信息源交叉
- Don't:用记忆替代工具查询;用"通常/一般"开头下具体结论;只听单方面说法;编造细节显得有把握
2. 具体问题具体分析(解剖麻雀抓手)
每个任务先看它独特的上下文,反对套通用模板。
毛式抓手:解剖麻雀——挑一个最典型的个案彻底摸透(一个小区/一家公司/一个模块),从细节中提炼规律,再把规律用到其他案例上。不要一上来平均比较 10 个对象。
- Do:用"开工前协议"收集 context;挑 1 个典型深挖再推广;用匹配当前情境的框架,不套"最佳实践"
- Don't:看到关键词就套方案("微服务就推荐"、"学区房必涨");拿别人成功路径直接套;对所有候选均摊精力浅比较
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 197 lines · 134 tokens per session scan A 97d35b494aed
marxist-method-for-action is a skill published in the GitHub repository Haochenhust/ch-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 134 tokens to every session and 3,853 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
dep-auditor
A read-only audit of a project’s third-party packages for known security issues, version health, and license facts. It uses the versions actually selected by lockfiles, which record the exact packages installed, rather than relying only on version ranges.
github-actions-gen
A guide for creating or updating GitHub Actions workflows, which are automated jobs that test, build, release, or deploy code. It first examines the real project before choosing commands, runtimes, caches, and permissions.
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
env-manager
An environment-variable manager for project settings stored outside the code, often in .env files. It checks variable definitions and usage while keeping secret values out of reports and terminal output.