CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

81

1.09x
Quality

71%

Does it follow best practices?

Impact

100%

1.09x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./prompts/humanizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is impressively comprehensive and highly actionable, with excellent concrete before/after examples for each AI writing pattern. However, it is far too long for a SKILL.md file—it reads more like a complete reference manual than a skill overview. The lack of progressive disclosure (no bundle files, everything inline) and the verbosity of explaining 24 patterns in full detail make this a poor fit for the context window, despite the quality of the individual examples.

Suggestions

Split the 24 pattern descriptions into a separate PATTERNS.md reference file, keeping SKILL.md as a concise overview (~50-80 lines) with the process, key principles, and links to the detailed reference.

Condense the words-to-watch lists into a compact table or single-line entries rather than full prose explanations for each pattern—Claude can infer the reasoning from the before/after examples alone.

Remove the 'Personality and Soul' section's basic writing advice (vary rhythm, use first person, have opinions) which Claude already knows, or reduce it to a brief checklist.

Add a verification step to the workflow, such as 'Re-read the output aloud to check it doesn't sound sterile or overcorrected' to close the feedback loop.

DimensionReasoningScore

Conciseness

At ~400+ lines, this skill is extremely verbose. It exhaustively lists 24 patterns with before/after examples for each, many of which Claude already understands (what em dashes are, what filler phrases are, basic writing advice). The 'Personality and Soul' section explains general writing craft that Claude knows. Much of this could be condensed into a compact reference table.

1 / 3

Actionability

The skill is highly actionable with concrete before/after examples for every pattern, specific words-to-watch lists, and a clear process. The examples are specific and demonstrate exactly what to change and why, making it copy-paste usable.

3 / 3

Workflow Clarity

There is a basic 5-step process at the top and a 5-step process near the bottom, but there are no validation checkpoints or feedback loops. For a text transformation task, there's no guidance on how to verify the output doesn't overcorrect or lose meaning, and no iterative review step.

2 / 3

Progressive Disclosure

This is a monolithic wall of text with all 24 patterns inline. The content would benefit enormously from splitting the pattern catalog into a separate reference file, keeping SKILL.md as a concise overview with the process and key principles, then linking to the detailed pattern reference.

1 / 3

Total

7

/

12

Passed

Description

100%

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 an excellent skill description that clearly communicates its purpose, provides explicit trigger conditions, and lists specific capabilities in detail. The enumeration of specific AI writing patterns (em dash overuse, rule of three, negative parallelisms, etc.) gives Claude strong signals for when to select this skill. It uses proper third-person voice throughout and occupies a distinct niche that won't easily conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and patterns: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Very detailed enumeration of what the skill does.

3 / 3

Completeness

Clearly answers both 'what' (remove signs of AI-generated writing, detects and fixes specific patterns) and 'when' ('Use when editing or reviewing text to make it sound more natural and human-written'). Has an explicit 'Use when...' clause with clear trigger guidance.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms like 'AI-generated writing', 'sound more natural', 'human-written', 'editing', 'reviewing text', plus specific pattern names users familiar with AI writing issues would recognize. Good coverage of terms a user would naturally use when wanting to de-AI their text.

3 / 3

Distinctiveness Conflict Risk

Occupies a very clear niche — specifically about detecting and removing AI writing patterns. The reference to Wikipedia's guide and the enumerated list of specific AI writing patterns make this highly distinctive and unlikely to conflict with general editing or writing skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
jdrhyne/agent-skills
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.