# newtype-01/newtype-skills architecture

> Architecture diagram of the GitHub repository newtype-01/newtype-skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-02-14). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/newtype-01/newtype-skills
- Repository: https://github.com/newtype-01/newtype-skills

## Overview

##### Project type & purpose (what you’re diagramming)
This repo is **not an executable software system** (no runtime services, no code, no build/deploy). It’s a **content-based prompt/skill library**: a collection of methodology-driven prompt “skills” (Markdown documents) meant to be **copied/pasted** or **loaded by AI tooling** (OpenCode / Claude Code / Custom GPT / Claude Project).

- **Artifacts**: the skills as documents (SKILL.md files)
- **Consumers**: humans and AI assistants
- **Integration points**: tools that can load skills from a directory (e.g., `~/.claude/skills`, `.opencode/skill`) and “/skill” commands
- **Flows**: how a user selects/installs/loads a skill and how it influences AI outputs

##### File structure analysis (map repo structure into components)
Top-level:
- `README.md`, `README.zh-cn.md`: entrypoints / documentation / usage instructions
- `skills/`: the core library namespace
- `skills/<skill-name>/SKILL.md`: each skill is a self-contained prompt methodology document

Concrete skill modules:
- `skills/super-analyst/SKILL.md`
- `skills/super-writer/SKILL.md`
- `skills/super-fact-checker/SKILL.md`
- `skills/super-editor/SKILL.md`
- `skills/super-interviewer/SKILL.md`

Architecturally this is a **modular catalog**: each folder is a module; `skills/` is a package index; README is the “registry UI” (human-facing).

##### README-derived architecture cues (how it’s used)
The README describes three primary consumption modes:
##### Direct Copy-Paste into a conversation with *any* AI assistant
2. **Tooling integration** (OpenCode / Claude Code) by cloning into a specific skills directory and loading via `/skill <name>`
##### Embedding into Custom GPT / Claude Project system prompts (i.e., saved configuration)

Key non-functional attributes to reflect:
- **Tool-agnostic**: works across ChatGPT/Claude/Gemini etc.
- **Language**: skills written primarily in Simplified Chinese but methodologies are universal
- **License**: MIT (important for distribution/reuse)

##### Repository (this project)
- `README.md` / `README.zh-cn.md` (documentation)
- `skills/` (skill catalog)
- `super-analyst/SKILL.md`
- `super-writer/SKILL.md`
- `super-fact-checker/SKILL.md`
- `super-editor/SKILL.md`
- `super-interviewer/SKILL.md`

##### Distribution / Installation targets
- GitHub (source of truth)
- Local filesystem clone (e.g., `~/.claude/skills/huangyihe-skills` or `.opencode/skill/huangyihe-skills`)

##### Skill loader environments
- OpenCode
- Claude Code
- (Optional) other AI tools that support skill loading / prompt presets

##### Execution / Runtime environment (conceptual)
- AI assistant / LLM (ChatGPT, Claude, Gemini…)
- Conversation context (where the skill prompt is injected)

##### Actors
- User (selects skill, loads it, asks tasks)
- (Optional) Contributor (adds/edits SKILL.md; PR flow)

##### Architectural patterns/design principles
- **Modular skill packaging**: one skill per folder, single entry file `SKILL.md`
- **Tool-agnostic prompt interface**: “prompt text” is the integration contract
- **Registry/index pattern**: README is the catalog; `skills/` is the namespace
- **Immutable-ish artifacts**: skills are versioned via Git; distribution via clone/fork

##### Relevant technologies/frameworks (even if “soft”)
Since there’s no runtime stack, your “tech” labels should reflect:
- **Markdown** (`.md`) as artifact format
- **Git/GitHub** as distribution/versioning mechanism
- **OpenCode / Claude Code skill loader** (integration mechanism)
- **AI assistant platforms** (execution targets)

3. **Component view (C4 Level 3)**: show each skill as a component with its purpose (Analyst/Writer/Fact-checker/Editor/Interviewer)

## Diagram (Mermaid)

```mermaid
flowchart TD

%% ============ Lane A: Source & Artifacts ============
subgraph LaneA["Lane A — Source & Artifacts (Markdown + Git)"]
  direction TB

  subgraph GitHubRepo["GitHub Repo (Source of Truth)"]
    direction TB

    Readme["README (Registry UI / Usage Guide)"]:::doc
    ReadmeZh["README.zh-cn (中文说明)"]:::doc

    subgraph SkillsNS["skills/ (Skill Catalog Namespace)"]
      direction TB

      subgraph SA_Mod["super-analyst (Module)"]
        direction TB
        SA_SKILL["SKILL.md (Analyst Methodology Prompt)"]:::skill
      end

      subgraph SW_Mod["super-writer (Module)"]
        direction TB
        SW_SKILL["SKILL.md (Writer Methodology Prompt)"]:::skill
      end

      subgraph SFC_Mod["super-fact-checker (Module)"]
        direction TB
        SFC_SKILL["SKILL.md (Fact-check Methodology Prompt)"]:::skill
      end

      subgraph SE_Mod["super-editor (Module)"]
        direction TB
        SE_SKILL["SKILL.md (Editor Methodology Prompt)"]:::skill
      end

      subgraph SI_Mod["super-interviewer (Module)"]
        direction TB
        SI_SKILL["SKILL.md (Interview Methodology Prompt)"]:::skill
      end
    end

    License["MIT License (Reuse/Distribution Allowed)"]:::note
  end
end

%% ============ Lane B: Distribution & Loading ============
subgraph LaneB["Lane B — Distribution & Loading"]
  direction TB

  Git["Git (clone/pull/fork)"]:::tool

  LocalDir["Local Skills Directory (Filesystem Install Target)"]:::fs
  ClaudeSkills["~/.claude/skills/... (example target)"]:::fs
  OpenCodeSkills[".opencode/skill/... (example target)"]:::fs

  subgraph SkillLoaderEnv["Skill Loader Environments"]
    direction TB
    ClaudeCode["Claude Code (Skill Loader)"]:::tool
    OpenCode["OpenCode (Skill Loader)"]:::tool
    OtherTools["Other Tools (Prompt Presets / Skill Loading)"]:::tool
  end

  SkillCmd["/skill <name> (Loader Command)"]:::interface
end

%% ============ Lane C: Execution ============
subgraph LaneC["Lane C — Execution (Conceptual Runtime)"]
  direction TB

  PromptStore["Custom GPT / Claude Project Prompt Store (Saved Config)"]:::store
  Context["Conversation Context (System Prompt / Prepend)"]:::runtime
  LLM["AI Assistant / LLM (ChatGPT / Claude / Gemini ...)"]:::cloud
  Output["AI Response (Guided by Skill Methodology)"]:::output
end

%% ============ Actors ============
User["User (Selects/Installs/Loads Skill)"]:::actor
Contributor["Contributor (Edits Skills + PR)"]:::actor

%% ============ Flows (Documentation / Guidance) ============
Readme -.->|"usage_instructions"| User
ReadmeZh -.->|"usage_instructions"| User
Readme -.->|"module_catalog"| SA_SKILL
Readme -.->|"module_catalog"| SW_SKILL
Readme -.->|"module_catalog"| SFC_SKILL
Readme -.->|"module_catalog"| SE_SKILL
Readme -.->|"module_catalog"| SI_SKILL

%% ============ Flow 1: Direct Copy-Paste ============
User -->|"opens_SKILL.md"| SA_SKILL
User -->|"opens_SKILL.md"| SW_SKILL
User -->|"opens_SKILL.md"| SFC_SKILL
User -->|"opens_SKILL.md"| SE_SKILL
User -->|"opens_SKILL.md"| SI_SKILL
User -->|"copy/paste_prompt"| Context

%% ============ Flow 2: Tool-based Loading via Filesystem ============
Contributor -->|"edit_SKILL.md"| SA_SKILL
Contributor -->|"edit_SKILL.md"| SW_SKILL
Contributor -->|"edit_SKILL.md"| SFC_SKILL
Contributor -->|"edit_SKILL.md"| SE_SKILL
Contributor -->|"edit_SKILL.md"| SI_SKILL

GitHubRepo -->|"versioned_content"| Git
Git -->|"git_clone/pull"| LocalDir
LocalDir -->|"install_to"| ClaudeSkills
LocalDir -->|"install_to"| OpenCodeSkills

User -->|"runs_loader"| ClaudeCode
User -->|"runs_loader"| OpenCode

ClaudeCode -->|"accepts"| SkillCmd
OpenCode -->|"accepts"| SkillCmd

SkillCmd -->|"selects_skill_name"| ClaudeCode
SkillCmd -->|"selects_skill_name"| OpenCode

ClaudeCode -.->|"reads_SKILL.md_from_fs"| ClaudeSkills
OpenCode -.->|"reads_SKILL.md_from_fs"| OpenCodeSkills

ClaudeSkills -.->|"contains_repo_clone"| LocalDir
OpenCodeSkills -.->|"contains_repo_clone"| LocalDir

ClaudeCode -->|"injects_prompt"| Context
OpenCode -->|"injects_prompt"| Context
OtherTools -->|"injects_prompt"| Context

%% ============ Flow 3: Saved Prompt Embedding ============
User -->|"copy/paste_prompt"| PromptStore
PromptStore -->|"applies_to_session"| Context

%% ============ Execution ============
Context -->|"guides_generation"| LLM
User -->|"task_request"| LLM
LLM -->|"response_guided_by_methodology"| Output

%% ============ Architectural Notes ============
Patterns["Design Principles:\n- Modular packaging (1 skill/folder, SKILL.md)\n- Tool-agnostic interface (plain text prompt)\n- Registry/index via README\n- Versioned artifacts via Git/GitHub"]:::note
Patterns -.->|"applies_to"| Readme
Patterns -.->|"applies_to"| SA_SKILL
Patterns -.->|"applies_to"| SW_SKILL
Patterns -.->|"applies_to"| SFC_SKILL
Patterns -.->|"applies_to"| SE_SKILL
Patterns -.->|"applies_to"| SI_SKILL

%% ============ Directory Click Targets (separate nodes to preserve all clicks) ============
SkillsCatalogDir["skills/ (Catalog Dir)"]:::note
SA_DIR["skills/super-analyst/ (Module Dir)"]:::note
SW_DIR["skills/super-writer/ (Module Dir)"]:::note
SFC_DIR["skills/super-fact-checker/ (Module Dir)"]:::note
SE_DIR["skills/super-editor/ (Module Dir)"]:::note
SI_DIR["skills/super-interviewer/ (Module Dir)"]:::note

Patterns -.-> SkillsCatalogDir
SA_SKILL -.-> SA_DIR
SW_SKILL -.-> SW_DIR
SFC_SKILL -.-> SFC_DIR
SE_SKILL -.-> SE_DIR
SI_SKILL -.-> SI_DIR

%% ============ Click Events (from component_mapping) ============
click Readme "https://github.com/newtype-01/newtype-skills/blob/main/README.md"
click ReadmeZh "https://github.com/newtype-01/newtype-skills/blob/main/README.zh-cn.md"
click SA_SKILL "https://github.com/newtype-01/newtype-skills/blob/main/skills/super-analyst/SKILL.md"
click SW_SKILL "https://github.com/newtype-01/newtype-skills/blob/main/skills/super-writer/SKILL.md"
click SFC_SKILL "https://github.com/newtype-01/newtype-skills/blob/main/skills/super-fact-checker/SKILL.md"
click SE_SKILL "https://github.com/newtype-01/newtype-skills/blob/main/skills/super-editor/SKILL.md"
click SI_SKILL "https://github.com/newtype-01/newtype-skills/blob/main/skills/super-interviewer/SKILL.md"

%% Directory-level click targets (modules + skills/)
click SkillsCatalogDir "https://github.com/newtype-01/newtype-skills/tree/main/skills/"
click SA_DIR "https://github.com/newtype-01/newtype-skills/tree/main/skills/super-analyst/"
click SW_DIR "https://github.com/newtype-01/newtype-skills/tree/main/skills/super-writer/"
click SFC_DIR "https://github.com/newtype-01/newtype-skills/tree/main/skills/super-fact-checker/"
click SE_DIR "https://github.com/newtype-01/newtype-skills/tree/main/skills/super-editor/"
click SI_DIR "https://github.com/newtype-01/newtype-skills/tree/main/skills/super-interviewer/"

%% Additional catalog click targets preserved
click Patterns "https://github.com/newtype-01/newtype-skills/tree/main/skills/"
click License "https://github.com/newtype-01/newtype-skills/tree/main/skills/"

%% ============ Styles ============
classDef doc fill:#d6ecff,stroke:#2b6cb0,stroke-width:1.5px,color:#0b2a4a
classDef skill fill:#bee3f8,stroke:#2c5282,stroke-width:1.5px,color:#0b2a4a
classDef tool fill:#c6f6d5,stroke:#276749,stroke-width:1.5px,color:#12351f
classDef fs fill:#ffe5b4,stroke:#b7791f,stroke-width:1.5px,color:#4a2c0a
classDef cloud fill:#e2e8f0,stroke:#4a5568,stroke-width:1.5px,color:#1a202c
classDef runtime fill:#f7fafc,stroke:#2d3748,stroke-width:1.5px,color:#1a202c
classDef output fill:#fbd38d,stroke:#975a16,stroke-width:1.5px,color:#3b2407
classDef actor fill:#111827,stroke:#111827,stroke-width:1.5px,color:#ffffff
classDef interface fill:#d9f99d,stroke:#3f6212,stroke-width:1.5px,color:#1f2d0b
classDef store fill:#fbcfe8,stroke:#9d174d,stroke-width:1.5px,color:#4a0f25
classDef note fill:#fff,stroke:#718096,stroke-width:1.5px,color:#2d3748,stroke-dasharray:4 3
```
