# cangtianhuang/humanizer-academic-zh architecture

> Architecture diagram of the GitHub repository cangtianhuang/humanizer-academic-zh, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-06-18). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/cangtianhuang/humanizer-academic-zh
- Repository: https://github.com/cangtianhuang/humanizer-academic-zh

## Overview

1. **Repository type**
   - This is a **prompt artifact repository**, not an application codebase.
   - Its “architecture” is mostly about **packaging and distributing a single behavioral policy** for LLMs: a Chinese academic text humanizer.

2. **Core purpose**
   - The repository provides instructions that tell an LLM how to **reduce AI-like writing signals without changing meaning**.
   - The design goal is explicitly **short, precise, and token-efficient**, so the payload is minimal and intended for direct insertion into model context.

3. **Main functional subsystem**
   - The only meaningful subsystem is the **prompt ruleset**.
   - Those rules are designed around **surface-pattern rewriting**: preserve content, adjust wording/style to look more human and academically natural.

4. **Two packaging formats for the same behavior**
   - `SKILL.md` is the **Claude Code Skills** version, with YAML frontmatter so it can be installed as a skill.
   - `SYSTEM_PROMPT.md` is the **generic system-prompt version** for any LLM.
   - Both files are described as having **the same core content**, just different delivery mechanisms.

5. **Documentation and entry point**
   - `README.md` is the human-facing control plane of the repo.
   - It explains what the skill does, how to install it, and how to invoke it in either Claude Code Skills mode or raw system-prompt mode.
   - `LICENSE` is operationally separate and only governs reuse.

6. **Input → processing → output flow**
   - **Input:** a user pastes a Chinese academic paragraph or paper fragment.
   - **Processing:** the LLM applies the prompt rules to remove AI-like traces while maintaining meaning.
   - **Output:** a rewritten academic-style text segment.
   - No intermediate services, databases, or pipelines exist in the repository itself; the transformation happens entirely inside the consuming LLM.

7. **Distribution and activation boundary**
   - The repo supports two activation paths:
     - **Claude Code Skills installation** via `SKILL.md`
     - **Direct system prompt insertion** via `SYSTEM_PROMPT.md`
   - This creates a clean boundary between **authoring the prompt** and **executing it in a model client**.

8. **External tooling that matters**
   - The README references **`npx skills`** as an external distribution/installation tool.
   - It also references downstream consumers such as **Claude Code, Cursor, Codex, ChatGPT, DeepSeek**, etc.
   - These are not part of the repo’s runtime, but they are the real deployment targets for the prompt.

9. **What is intentionally absent**
   - There is no backend service, UI, API server, build system, or test suite.
   - There is also no dataset, model weights, or retrieval layer.
   - Architecturally, this is a **static prompt package** with documentation.

10. **How to diagram it**
   - Draw the repo as a **source-of-truth prompt bundle** with two output artifacts: `SKILL.md` and `SYSTEM_PROMPT.md`.
   - Show `README.md` as the installer/instruction layer.
   - Show the consumer side as an **LLM client/runtime** that receives the prompt and a user’s text, then emits polished academic Chinese.

Main entry points: [`README.md`](https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/README.md) (README), [`SKILL.md`](https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/SKILL.md) (SKILL.md), [`SYSTEM_PROMPT.md`](https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/SYSTEM_PROMPT.md) (SYSTEM_PROMPT), [`LICENSE`](https://github.com/cangtianhuang/humanizer-academic-zh/tree/main/LICENSE) (LICENSE)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_repo["Repository"]
  node_readme["README<br/>docs<br/>[README.md]"]
  node_skill["SKILL.md<br/>prompt skill<br/>[SKILL.md]"]
  node_system_prompt["SYSTEM_PROMPT<br/>[SYSTEM_PROMPT.md]"]
  node_license["LICENSE"]
  node_prompt_core{{"Core rules<br/>policy"}}
end

subgraph group_external["Consumers"]
  node_npx_skills["npx skills<br/>installer"]
  node_claude_code["Claude Code<br/>client"]
  node_llm_client["LLM client<br/>runtime"]
  node_user_text["User text<br/>input"]
  node_humanized_text["Rewritten text<br/>output"]
end

node_readme -->|"installs"| node_skill
node_readme -->|"inserts"| node_system_prompt
node_readme -.->|"references"| node_npx_skills
node_skill -->|"packages"| node_prompt_core
node_system_prompt -->|"packages"| node_prompt_core
node_prompt_core -->|"loads into"| node_claude_code
node_prompt_core -->|"loads into"| node_llm_client
node_user_text -->|"supplies"| node_claude_code
node_user_text -->|"supplies"| node_llm_client
node_claude_code -->|"rewrites"| node_humanized_text
node_llm_client -->|"rewrites"| node_humanized_text
node_license -.->|"governs"| node_skill
node_license -.->|"governs"| node_system_prompt

click node_readme "https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/README.md"
click node_skill "https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/SKILL.md"
click node_system_prompt "https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/SYSTEM_PROMPT.md"
click node_license "https://github.com/cangtianhuang/humanizer-academic-zh/tree/main/LICENSE"

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_readme,node_skill,node_system_prompt,node_license,node_prompt_core toneBlue
class node_npx_skills,node_claude_code,node_llm_client,node_user_text,node_humanized_text toneAmber
```

## Components

### Repository

Source-of-truth prompt bundle and documentation

- [README](https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/README.md): docs · Usage, install, and invocation guide · `README.md`
- [SKILL.md](https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/SKILL.md): prompt skill · Claude Code Skills packaging for the humanizer policy · `SKILL.md`
- [SYSTEM_PROMPT](https://github.com/cangtianhuang/humanizer-academic-zh/blob/main/SYSTEM_PROMPT.md): prompt · Generic system-prompt packaging for the same policy · `SYSTEM_PROMPT.md`
- [LICENSE](https://github.com/cangtianhuang/humanizer-academic-zh/tree/main/LICENSE): license · Reuse and distribution terms · `LICENSE`
- **Core rules**: policy · Token-efficient rewriting rules that preserve meaning while reducing AI-like signals

### Consumers

Outside tools and model runtimes that load the prompt

- **npx skills**: installer · External skill distribution and installation tool
- **Claude Code**: client · Skill-aware consumer that can load SKILL.md
- **LLM client**: runtime · Generic model host that accepts SYSTEM_PROMPT.md
- **User text**: input · Chinese academic paragraph or paper fragment to be rewritten
- **Rewritten text**: output · Polished Chinese academic output with preserved meaning

## Connections

- README → SKILL.md: installs · Explains Claude Code Skills setup
- README → SYSTEM_PROMPT: inserts · Explains direct system-prompt use
- README → npx skills: references · Mentions external installation tool
- SKILL.md → Core rules: packages · Skill-form version of the same rules
- SYSTEM_PROMPT → Core rules: packages · Generic prompt-form version of the same rules
- Core rules → Claude Code: loads into · Activated through Claude Code Skills
- Core rules → LLM client: loads into · Activated as a raw system prompt
- User text → Claude Code: supplies · User provides the source paragraph to the client
- User text → LLM client: supplies · User provides the source paragraph to the model host
- Claude Code → Rewritten text: rewrites · Produces humanized academic Chinese
- LLM client → Rewritten text: rewrites · Produces humanized academic Chinese
- LICENSE → SKILL.md: governs · Reuse terms apply to the packaged prompt files
- LICENSE → SYSTEM_PROMPT: governs · Reuse terms apply to the packaged prompt files