# hughyau/qiushi-skill architecture

> Architecture diagram of the GitHub repository hughyau/qiushi-skill, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-29). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/hughyau/qiushi-skill
- Repository: https://github.com/hughyau/qiushi-skill

## Overview

Qiushi Skill is a collection of practical methodology skills for AI agents, with a session-start kernel that routes tasks to the appropriate methods and a separate CLI for installing those assets into supported hosts. The documented reasoning workflow starts from evidence, selects relevant methods, and can combine them through workflows; a manual command directory provides alternate entry points. The graph preserves the nine distinct methods and major integration paths. CLI wiring is based on sampled source; method-level relationships reflect the README, since skill instructions were not sampled.

Main entry points: [`skills/arming-thought/SKILL.md`](https://github.com/hughyau/qiushi-skill/blob/main/skills/arming-thought/SKILL.md) (Arming Kernel), [`commands`](https://github.com/hughyau/qiushi-skill/tree/main/commands) (Slash Commands), [`skills/workflows/SKILL.md`](https://github.com/hughyau/qiushi-skill/blob/main/skills/workflows/SKILL.md) (Workflow Compositions), [`bin/qiushi-skill.mjs`](https://github.com/hughyau/qiushi-skill/blob/main/bin/qiushi-skill.mjs) (CLI Entry)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_methods["Methodology Skills"]
  node_contradiction["Contradiction Analysis<br/>[SKILL.md]"]
  node_practice["Practice Cognition<br/>[SKILL.md]"]
  node_investigation["Investigation First<br/>[SKILL.md]"]
  node_massline["Mass Line<br/>[SKILL.md]"]
  node_criticism["Self-Criticism<br/>[SKILL.md]"]
  node_protracted["Protracted Strategy<br/>[SKILL.md]"]
  node_concentrate["Concentrate Forces<br/>[SKILL.md]"]
  node_spark["Spark Prairie Fire<br/>[SKILL.md]"]
  node_planning["Overall Planning<br/>[SKILL.md]"]
end

subgraph group_entry["Agent Entry Points"]
  node_arming["Arming Kernel<br/>[SKILL.md]"]
  node_commands["Slash Commands"]
  node_hooks["Session Hooks"]
  node_agents["Subagents"]
  node_workflows["Workflow Compositions<br/>[SKILL.md]"]
end

subgraph group_distribution["Installation CLI"]
  node_cli["CLI Entry<br/>[qiushi-skill.mjs]"]
  node_platforms["Platform Detection"]
  node_installer["Asset Installer<br/>[install.mjs]"]
end

node_user(("User"))
node_assistant(("AI Agent"))
node_host["Agent Hosts"]

node_user -->|"requests work"| node_assistant
node_assistant -->|"applies kernel"| node_arming
node_hooks -->|"injects at session start"| node_arming
node_arming -->|"routes when relevant"| node_contradiction
node_arming -->|"routes when relevant"| node_practice
node_arming -->|"routes when relevant"| node_investigation
node_arming -->|"routes when relevant"| node_massline
node_arming -->|"routes when relevant"| node_criticism
node_arming -->|"routes when relevant"| node_protracted
node_arming -->|"routes when relevant"| node_concentrate
node_arming -->|"routes when relevant"| node_spark
node_arming -->|"routes when relevant"| node_planning
node_assistant -->|"invokes manually"| node_commands
node_commands -->|"loads matching guidance"| node_contradiction
node_commands -->|"loads matching guidance"| node_practice
node_commands -->|"loads matching guidance"| node_investigation
node_commands -->|"loads matching guidance"| node_massline
node_commands -->|"loads matching guidance"| node_criticism
node_commands -->|"loads matching guidance"| node_protracted
node_commands -->|"loads matching guidance"| node_concentrate
node_commands -->|"loads matching guidance"| node_spark
node_commands -->|"loads matching guidance"| node_planning
node_workflows -->|"coordinates method use"| node_contradiction
node_workflows -->|"coordinates method use"| node_practice
node_workflows -->|"coordinates method use"| node_investigation
node_workflows -->|"coordinates method use"| node_massline
node_workflows -->|"coordinates method use"| node_criticism
node_workflows -->|"coordinates method use"| node_protracted
node_workflows -->|"coordinates method use"| node_concentrate
node_workflows -->|"coordinates method use"| node_spark
node_workflows -->|"coordinates method use"| node_planning
node_assistant -.->|"delegates investigation or review"| node_agents
node_user -->|"runs install or uninstall"| node_cli
node_cli -->|"detects and resolves targets"| node_platforms
node_cli -->|"installs or removes assets"| node_installer
node_installer -->|"copies assets to host directories"| node_host
node_host -.->|"runs session integration"| node_hooks

click node_arming "https://github.com/hughyau/qiushi-skill/blob/main/skills/arming-thought/SKILL.md"
click node_commands "https://github.com/hughyau/qiushi-skill/tree/main/commands"
click node_hooks "https://github.com/hughyau/qiushi-skill/tree/main/hooks"
click node_agents "https://github.com/hughyau/qiushi-skill/tree/main/agents"
click node_workflows "https://github.com/hughyau/qiushi-skill/blob/main/skills/workflows/SKILL.md"
click node_contradiction "https://github.com/hughyau/qiushi-skill/blob/main/skills/contradiction-analysis/SKILL.md"
click node_practice "https://github.com/hughyau/qiushi-skill/blob/main/skills/practice-cognition/SKILL.md"
click node_investigation "https://github.com/hughyau/qiushi-skill/blob/main/skills/investigation-first/SKILL.md"
click node_massline "https://github.com/hughyau/qiushi-skill/blob/main/skills/mass-line/SKILL.md"
click node_criticism "https://github.com/hughyau/qiushi-skill/blob/main/skills/criticism-self-criticism/SKILL.md"
click node_protracted "https://github.com/hughyau/qiushi-skill/blob/main/skills/protracted-strategy/SKILL.md"
click node_concentrate "https://github.com/hughyau/qiushi-skill/blob/main/skills/concentrate-forces/SKILL.md"
click node_spark "https://github.com/hughyau/qiushi-skill/blob/main/skills/spark-prairie-fire/SKILL.md"
click node_planning "https://github.com/hughyau/qiushi-skill/blob/main/skills/overall-planning/SKILL.md"
click node_cli "https://github.com/hughyau/qiushi-skill/blob/main/bin/qiushi-skill.mjs"
click node_platforms "https://github.com/hughyau/qiushi-skill/blob/main/bin/lib/detect-platform.mjs"
click node_installer "https://github.com/hughyau/qiushi-skill/blob/main/bin/lib/install.mjs"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_contradiction,node_practice,node_investigation,node_massline,node_criticism,node_protracted,node_concentrate,node_spark,node_planning,node_user toneBlue
class node_arming,node_commands,node_hooks,node_agents,node_workflows toneAmber
class node_cli,node_platforms,node_installer toneMint
class node_assistant,node_host toneIndigo
```

## Components

### Methodology Skills

- [Contradiction Analysis](https://github.com/hughyau/qiushi-skill/blob/main/skills/contradiction-analysis/SKILL.md): `skills/contradiction-analysis/SKILL.md`
- [Practice Cognition](https://github.com/hughyau/qiushi-skill/blob/main/skills/practice-cognition/SKILL.md): `skills/practice-cognition/SKILL.md`
- [Investigation First](https://github.com/hughyau/qiushi-skill/blob/main/skills/investigation-first/SKILL.md): `skills/investigation-first/SKILL.md`
- [Mass Line](https://github.com/hughyau/qiushi-skill/blob/main/skills/mass-line/SKILL.md): `skills/mass-line/SKILL.md`
- [Self-Criticism](https://github.com/hughyau/qiushi-skill/blob/main/skills/criticism-self-criticism/SKILL.md): `skills/criticism-self-criticism/SKILL.md`
- [Protracted Strategy](https://github.com/hughyau/qiushi-skill/blob/main/skills/protracted-strategy/SKILL.md): `skills/protracted-strategy/SKILL.md`
- [Concentrate Forces](https://github.com/hughyau/qiushi-skill/blob/main/skills/concentrate-forces/SKILL.md): `skills/concentrate-forces/SKILL.md`
- [Spark Prairie Fire](https://github.com/hughyau/qiushi-skill/blob/main/skills/spark-prairie-fire/SKILL.md): `skills/spark-prairie-fire/SKILL.md`
- [Overall Planning](https://github.com/hughyau/qiushi-skill/blob/main/skills/overall-planning/SKILL.md): `skills/overall-planning/SKILL.md`

### Agent Entry Points

- [Arming Kernel](https://github.com/hughyau/qiushi-skill/blob/main/skills/arming-thought/SKILL.md): `skills/arming-thought/SKILL.md`
- [Slash Commands](https://github.com/hughyau/qiushi-skill/tree/main/commands): `commands`
- [Session Hooks](https://github.com/hughyau/qiushi-skill/tree/main/hooks): `hooks`
- [Subagents](https://github.com/hughyau/qiushi-skill/tree/main/agents): `agents`
- [Workflow Compositions](https://github.com/hughyau/qiushi-skill/blob/main/skills/workflows/SKILL.md): `skills/workflows/SKILL.md`

### Installation CLI

- [CLI Entry](https://github.com/hughyau/qiushi-skill/blob/main/bin/qiushi-skill.mjs): `bin/qiushi-skill.mjs`
- [Platform Detection](https://github.com/hughyau/qiushi-skill/blob/main/bin/lib/detect-platform.mjs): `bin/lib/detect-platform.mjs`
- [Asset Installer](https://github.com/hughyau/qiushi-skill/blob/main/bin/lib/install.mjs): `bin/lib/install.mjs`

### Other components

- **User**
- **AI Agent**
- **Agent Hosts**

## Connections

- User → AI Agent: requests work
- AI Agent → Arming Kernel: applies kernel
- Session Hooks → Arming Kernel: injects at session start
- Arming Kernel → Contradiction Analysis: routes when relevant
- Arming Kernel → Practice Cognition: routes when relevant
- Arming Kernel → Investigation First: routes when relevant
- Arming Kernel → Mass Line: routes when relevant
- Arming Kernel → Self-Criticism: routes when relevant
- Arming Kernel → Protracted Strategy: routes when relevant
- Arming Kernel → Concentrate Forces: routes when relevant
- Arming Kernel → Spark Prairie Fire: routes when relevant
- Arming Kernel → Overall Planning: routes when relevant
- AI Agent → Slash Commands: invokes manually
- Slash Commands → Contradiction Analysis: loads matching guidance
- Slash Commands → Practice Cognition: loads matching guidance
- Slash Commands → Investigation First: loads matching guidance
- Slash Commands → Mass Line: loads matching guidance
- Slash Commands → Self-Criticism: loads matching guidance
- Slash Commands → Protracted Strategy: loads matching guidance
- Slash Commands → Concentrate Forces: loads matching guidance
- Slash Commands → Spark Prairie Fire: loads matching guidance
- Slash Commands → Overall Planning: loads matching guidance
- Workflow Compositions → Contradiction Analysis: coordinates method use
- Workflow Compositions → Practice Cognition: coordinates method use
- Workflow Compositions → Investigation First: coordinates method use
- Workflow Compositions → Mass Line: coordinates method use
- Workflow Compositions → Self-Criticism: coordinates method use
- Workflow Compositions → Protracted Strategy: coordinates method use
- Workflow Compositions → Concentrate Forces: coordinates method use
- Workflow Compositions → Spark Prairie Fire: coordinates method use
- Workflow Compositions → Overall Planning: coordinates method use
- AI Agent → Subagents: delegates investigation or review
- User → CLI Entry: runs install or uninstall
- CLI Entry → Platform Detection: detects and resolves targets
- CLI Entry → Asset Installer: installs or removes assets
- Asset Installer → Agent Hosts: copies assets to host directories
- Agent Hosts → Session Hooks: runs session integration