# Humanize Docs

> Edits documentation in place for a human reader. TRIGGER WHEN: the user asks to humanize existing docs, improve scannability, or rewrite dense technical writing for progressive disclosure. DO NOT TRIGGER WHEN: humanizing prose/articles (use /text-humanizer:humanize-text) or creating new docs (use /codebase-mapper:docs-create).

- Skill: `acaprino/humanize-docs` (Agent Skill)
- Install (CLI): `npx skillmds@latest add acaprino/humanize-docs`
- Raw SKILL.md: https://api.skillmd.com/api/skills/acaprino/humanize-docs/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: acaprino (https://skillmd.com/u/acaprino)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/acaprino/humanize-docs

---


> `<plugin-root>` names the directory that holds this plugin's `.codex-plugin/plugin.json`. Resolve it once from where this file was loaded, then substitute it into every path below that starts with it.
> Arguments: `<path-to-docs>`. Wherever `<arguments>` appears below, substitute the text the user typed after the skill name.

<!-- Generated by the Daodan compiler for codex. Edit the kernel, never this file. -->

# Humanize Documentation

## CRITICAL RULES

1. **Path required.** The user must provide a path to documentation files or directory.
2. **Never invent content.** Only restructure and rephrase existing content.
3. **Confirm scope.** Show what will be rewritten before starting.
4. **Never enter plan mode.** Execute immediately.

## Step 1: Validate Target

Parse `<arguments>` for the documentation path.

If no path provided, ask:
```
Which documentation should I humanize? Provide a path to a file or directory.
```

Verify the path exists and contains documentation files (.md, .rst, .mdx, .txt).

## Step 2: Assess and Confirm Scope

Read the target documentation. Present a brief assessment:

```
Documentation to humanize: [path]

Files found: [count]
Total lines: ~[count]

Issues detected:
- [X] instances of passive voice / AI boilerplate
- [X] dense paragraphs (> 4 sentences)
- [X] monolithic diagrams
- [X] missing progressive disclosure
- [X] mixed reference / tutorial content

1. Proceed with humanization
2. Narrow scope -- I'll specify which files
3. Cancel
```

Use AskUserQuestion. Do NOT proceed until the user confirms.

## Step 3: Rewrite

Spawn the `doc-humanizer` agent:

```
Task:
  subagent_type: "codebase-mapper:doc-humanizer"
  description: "Humanize documentation at [path]"
  prompt: |
    Rewrite the following documentation to be human-readable.

    ## Target
    [path and file list]

    ## Instructions
    Read all target files and rewrite them following the codebase-mapper
    writing guidelines. Humanize toward the target register (if the user
    specified one) or infer it via
    <plugin-root>/skills/codebase-mapper/references/audience-adaptation.md.
    Fix anti-patterns (passive voice, AI boilerplate,
    dense text, missing structure) while preserving all factual content.

    Rewrite files in-place using the Edit tool.
    Provide a change summary when done.
```

## Step 4: AI Trace Removal Pass

After the `doc-humanizer` restructures the content, run a second pass with the `text-humanizer` agent to catch remaining AI writing patterns in the prose.

```
Task:
  subagent_type: "text-humanizer:text-humanizer"
  description: "Remove AI writing traces from humanized documentation"
  prompt: |
    Final polish pass on restructured documentation. Remove any remaining AI
    writing patterns (AI vocabulary, filler phrases, inflated significance,
    generic conclusions) while preserving the improved structure, code blocks,
    diagrams, and ALL tables (do not convert tables to prose).

    Do NOT add the self-evaluation pass -- just return the cleaned text.

    Files to process:
    [list of rewritten files]
```

## Step 5: Summary

Present before/after summary:

```
Humanization complete:

Files rewritten: [count]
Anti-patterns fixed:
- Passive voice: [count] instances
- AI boilerplate removed: [count] instances
- Paragraphs restructured: [count]
- Diagrams split: [count]
- Progressive disclosure added: [count] files
- AI writing traces removed: second pass applied

All factual content preserved. Review the changes with git diff.
```

## Quick Examples

```bash
/humanize-docs docs/                    # Humanize all docs in docs/
/humanize-docs README.md                # Humanize a single file
/humanize-docs docs/api/reference.md    # Humanize specific API docs
```