# iampattanayak/claude-humanizer architecture

> Architecture diagram of the GitHub repository iampattanayak/claude-humanizer, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-24). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/iampattanayak/claude-humanizer
- Repository: https://github.com/iampattanayak/claude-humanizer

## Overview

Claude Humanizer is a prompt-as-code skill for revising AI-generated text in Claude Code. The documented workflow takes a draft through an initial cleanup, a self-critique audit, and a final revision; the audit targets a 24-pattern matrix spanning wording, structure, and typography. The README documents invocation and workflow, but no source excerpts are available, so the graph represents only those documented relationships and not internal implementation details.

Main entry points: [`SKILL.md`](https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md) (Self-critique audit), [`README.md`](https://github.com/iampattanayak/claude-humanizer/blob/main/README.md) (Anti-pattern matrix)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_humanizer["Humanizer workflow"]
  node_skill["Skill protocol<br/>[SKILL.md]"]
  node_draft["Draft cleanup<br/>[SKILL.md]"]
  node_audit["Self-critique audit<br/>[SKILL.md]"]
  node_patterns["Anti-pattern matrix<br/>[README.md]"]
  node_final["Final revision<br/>[SKILL.md]"]
end

node_user(("User"))
node_claude_cli["Claude Code CLI"]

node_user -->|"submits draft"| node_claude_cli
node_claude_cli -->|"invokes"| node_skill
node_skill -->|"guides"| node_draft
node_draft -->|"continues to"| node_audit
node_audit -->|"checks against"| node_patterns
node_audit -->|"prompts revision"| node_final
node_final -->|"returns result"| node_claude_cli
node_claude_cli -->|"presents result"| node_user

click node_skill "https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md"
click node_draft "https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md"
click node_audit "https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md"
click node_patterns "https://github.com/iampattanayak/claude-humanizer/blob/main/README.md"
click node_final "https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md"

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_skill,node_draft,node_audit,node_patterns,node_final,node_user toneBlue
class node_claude_cli toneIndigo
```

## Components

### Humanizer workflow

- [Skill protocol](https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md): `SKILL.md`
- [Draft cleanup](https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md): `SKILL.md`
- [Self-critique audit](https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md): `SKILL.md`
- [Anti-pattern matrix](https://github.com/iampattanayak/claude-humanizer/blob/main/README.md): `README.md`
- [Final revision](https://github.com/iampattanayak/claude-humanizer/blob/main/SKILL.md): `SKILL.md`

### Other components

- **User**
- **Claude Code CLI**

## Connections

- User → Claude Code CLI: submits draft
- Claude Code CLI → Skill protocol: invokes
- Skill protocol → Draft cleanup: guides
- Draft cleanup → Self-critique audit: continues to
- Self-critique audit → Anti-pattern matrix: checks against
- Self-critique audit → Final revision: prompts revision
- Final revision → Claude Code CLI: returns result
- Claude Code CLI → User: presents result