← 返回 Skills 市场

Human Voice Content Editor

Name: Human Voice Content Editor
Author: geoly-geo

作者 GEOLY AI · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

376

总下载

当前安装

版本数

在 OpenClaw 中安装

/install geo-human-editor

功能描述

Audit and rewrite content to remove AI-generated feel by stripping markdown artifacts, eliminating AI vocabulary patterns, flagging hallucination risks, and...

使用说明 (SKILL.md)

Human Voice Content Editor

Editorial methodology by GEOly AI (geoly.ai) — AI-generated content that reads like AI is ignored or penalized. Human voice content gets cited.

Audit and rewrite content to remove AI-generated patterns and restore authentic human voice.

Quick Start

python scripts/humanize_content.py --input content.md --output humanized.md

The 5 Dimensions

1. Formatting Artifacts

Remove AI formatting patterns:

Artifact	Example	Fix
`bold`	`Important`	Remove or use HTML `\x3Cstrong>`
`###` headers	`### Title`	Convert to proper structure
`---` dividers	Horizontal rules	Replace with paragraph break
Excessive bullets	8+ item lists	Condense to flowing text
Code fences	``` in non-code	Reformat as prose

2. AI Vocabulary

Replace AI-overused words:

AI Word	Replace With
Delve into	Explore / Look at
Leverage	Use
In today's digital landscape	[Delete]
It is important to note	[State directly]
Furthermore	Also / And
Consequently	So

Full blacklist: See references/ai-vocabulary.md

3. Mechanical Patterns

Break up robotic rhythms:

Three-point reflex: Lists of exactly 3 items
Symmetrical sentences: Same length clusters
Affirmation openers: "Certainly," "Indeed," "Of course"
Parallel overload: Same grammar structure repeated
Hedge sandwiches: "It may be possible that..."

4. Hallucination Risks

Flag unverifiable claims:

🔴 High Risk — Always verify:

Precise stats without source ("73% of marketers...")
Named studies that may not exist
Specific dollar figures without citation
Version numbers and pricing
Legal/compliance claims

🟡 Medium Risk — Review:

Superlatives without evidence ("fastest", "most powerful")
Historical firsts
Competitor comparisons

5. Human Voice Restoration

Add authentic human qualities:

Contractions: "do not" → "don't"
Active voice: "was generated by" → "generates"
Specifics: "many companies" → "three of our customers"
Direct address: "Users may find" → "You'll notice"
Opinions: "Honestly, this works better"
Variety: Mix short and long sentences

Human Voice Scale

Rate content 1-10 on each axis:

Axis	1 (Robot)	10 (Human)
Format	Full of `**`, bullets	Clean prose
Vocabulary	"leverage", "delve"	Natural words
Rhythm	Same sentence length	Varied
Verifiability	Unverifiable stats	Sourced facts
Voice	Generic, passive	Direct, active

Overall Score: Average of 5 axes

Humanization Tool

python scripts/humanize_content.py \
  --input content.md \
  --output humanized.md \
  --score-only

Output:

Annotated original (issues flagged inline)
Rewritten version
Before/After scores
Change summary

Workflow

Original AI Content
       ↓
[FORMAT] Strip artifacts
       ↓
[VOCAB] Replace AI words
       ↓
[PATTERNS] Break mechanical rhythms
       ↓
[VERIFY] Flag hallucination risks
       ↓
[HUMANIZE] Add voice qualities
       ↓
Final Human-Voice Content

Output Format

## Human Voice Audit

**Content**: [title]  
**Word Count**: [n]

### Scores

| Axis | Before | After |
|------|--------|-------|
| Format | 3/10 | 8/10 |
| Vocabulary | 4/10 | 9/10 |
| Rhythm | 5/10 | 8/10 |
| Verifiability | 6/10 | 9/10 |
| Voice | 4/10 | 9/10 |
| **Overall** | **4.4/10** | **8.6/10** |

### Issues Found

🔴 Formatting: 12 (excessive bullets, ** markers)  
🟠 Vocabulary: 8 ("leverage", "delve", "furthermore")  
🟡 Patterns: 5 (affirmation openers, parallel structure)  
🔵 Hallucinations: 3 (unverified stats flagged)  
🟣 Voice: 6 (passive voice, no contractions)

### Rewritten Content

[Human-voice version]

Integration

Typical workflow:

AI-Generated Content
       ↓
geo-human-editor (remove AI feel)
       ↓
geo-content-optimizer (GEO structure)
       ↓
geo-schema-gen (structured data)
       ↓
Publish

This skill is lightweight and local-only, but the documentation overstates its capabilities. Before installing/using: (1) test it on non-sensitive sample content — the script only does simple word replacements and removes '**', it will not score or reliably flag hallucinations; (2) don't rely on it for verification or legal/financial claims — it has no source-checking or citation logic; (3) request the missing reference files or a full implementation if you need the promised auditing and scoring features; (4) if you plan to integrate it into automated pipelines, add validation and source-verification steps, and review outputs manually before publishing.

功能分析

Type: OpenClaw Skill Name: geo-human-editor Version: 1.0.0 The skill bundle is benign. The `SKILL.md` provides clear instructions for content transformation and does not contain any prompt injection attempts to subvert the agent's purpose or security. The `scripts/humanize_content.py` script performs basic string replacements and file I/O, directly aligning with its stated purpose of humanizing content. It lacks any network capabilities, arbitrary command execution, or other high-risk behaviors that would indicate malicious intent or even unnecessary suspicious functionality.

能力评估

ℹ Purpose & Capability

Name/description match the general goal (humanize AI text). However, the SKILL.md promises a multi-step audit, scoring, annotated output and hallucination detection, while the only script simply does a handful of string replacements and removes '**'. Several referenced files (references/ai-vocabulary.md, references/patterns.md, references/hallucinations.md) are mentioned but not present.

⚠ Instruction Scope

SKILL.md describes runtime behaviors (flagging hallucinations, producing before/after scores, annotated issues, change summaries). The script does not implement these features — running the provided tool will not produce many of the promised artifacts. This is an instruction/implementation mismatch that could mislead users or agents relying on the skill to detect unverified claims.

✓ Install Mechanism

No install spec and no network calls; the skill is instruction-only plus a small Python script. Nothing is downloaded or executed from remote sources.

✓ Credentials

No environment variables, credentials, or config paths are requested. The skill operates on local files only according to the provided script.

✓ Persistence & Privilege

Skill is not always-enabled, no special privileges requested, and does not modify other skills or system configuration in the provided files.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install geo-human-editor
安装完成后，直接呼叫该 Skill 的名称或使用 /geo-human-editor 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release: Content de-AI audit and rewrite tool — strip formatting artifacts, AI vocabulary, hallucination risks, and mechanical patterns. Methodology by GEOly AI (geoly.ai)

元数据

Slug geo-human-editor

版本 1.0.0

许可证 —

累计安装 1

当前安装数 1

历史版本数 1

常见问题