humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
83
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly explains what the skill does and when to use it, with excellent specificity about the patterns it addresses. The main weakness is trigger term coverage - it could benefit from more colloquial phrases users might naturally say when wanting to de-AI their text.
Suggestions
Add common user phrases to trigger terms such as 'sounds like ChatGPT', 'robotic writing', 'humanize text', or 'make it less AI'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Detects and fixes patterns including inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.' | 3 / 3 |
Completeness | Clearly answers both what ('Remove signs of AI-generated writing', 'Detects and fixes patterns...') and when ('Use when editing or reviewing text to make it sound more natural and human-written'). | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'AI-generated writing', 'natural', 'human-written', but missing common user phrases like 'sounds like ChatGPT', 'robotic', 'make it less AI', 'humanize', or 'rewrite'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on AI writing detection and removal with distinct triggers; unlikely to conflict with general editing or writing skills due to the specific focus on AI patterns. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent concrete examples for each AI writing pattern. The before/after format makes it immediately usable. Main weakness is length - the comprehensive pattern catalog could benefit from being split into referenced files, and some explanatory text could be trimmed since Claude can infer context from the examples alone.
Suggestions
Split the 24 patterns into separate reference files (e.g., CONTENT_PATTERNS.md, LANGUAGE_PATTERNS.md, STYLE_PATTERNS.md) and keep SKILL.md as a concise overview with the process and links
Trim explanatory prose where the before/after examples already make the pattern clear - many 'Problem:' descriptions restate what's obvious from the examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but could be tightened. Some patterns have lengthy explanations where the before/after examples alone would suffice. The 'Personality and Soul' section adds value but is verbose in places. | 2 / 3 |
Actionability | Excellent actionability with concrete before/after examples for every pattern. Each pattern includes specific words to watch, clear problem statements, and executable transformations Claude can apply directly. | 3 / 3 |
Workflow Clarity | Clear 5-step process at the start, followed by organized pattern categories. The final 'Process' section provides explicit steps, and the output format is specified. For a text transformation task, this level of workflow guidance is appropriate. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers, but the skill is monolithic at ~400 lines. The 24 patterns could be split into separate reference files (content_patterns.md, language_patterns.md, style_patterns.md) with SKILL.md as an overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.