#265265th of 324 in Skills, plugins and prompts
qiushi-skill
Agent skill set applying Mao-era methodology to AI problem-solving
- Stars
- 3.8k
- License
- MIT
- Last commit
- Oct 2026
- Language
- JavaScript
172 on 3 Apr 20263,846 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A set of nine methodology skills plus a core "seek truth from facts" kernel for coding agents, drawn from Mao Zedong's writings (contradiction analysis, investigation first, protracted strategy and others). A hook injects a roughly 50-line kernel at session start, and the other skills load only when relevant. Installs with `npx qiushi-skill` into Claude Code, Cursor, Codex, OpenCode and other hosts, or through the Claude Code marketplace.
Who it is for: Users of Claude Code, Cursor or Codex who want structured reasoning skills
Strengths
- One npx command installs to Claude Code, Cursor, Codex, OpenCode, OpenClaw, Hermes and nanobot
- Only a ~50-line kernel stays resident; method skills load on demand
- Includes slash commands, two subagents (investigator, self-critic) and a validate script
- Each skill has an original-texts.md with source quotations
Weaknesses
- Main README is in Chinese; the English version is a separate file
- No benchmarks or measured effect on agent output quality in the README
- Content is built on a specific political text corpus, which may not suit every team
- No tagged releases
What it needs
- no GPU
- Needs Node.js (optional, for npx installer)
Quick answers
Is qiushi-skill open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |