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.

1.09x

Quality

71%

Does it follow best practices?

Impact

100%

1.09x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./prompts/humanizer/SKILL.md

Quality

Content

65%

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

A highly actionable reference skill: concrete before/after pairs for 24 AI-writing patterns make it immediately usable. Its weaknesses are length/discursiveness in the personality section and a monolithic structure that could offload pattern detail into a reference file.

Suggestions

Move the 24 detailed pattern entries (or the bulk of them) into a reference file (e.g. references/patterns.md) and keep SKILL.md as a concise overview pointing to it, improving progressive disclosure and conciseness.

Trim or condense the 'PERSONALITY AND SOUL' section, which is discursive relative to the rest of the pattern reference.

Add an explicit verification feedback loop in the Process section, e.g. 'After rewriting, re-read aloud; if any pattern remains, revise and re-check.'

Dimension	Reasoning	Score
Conciseness	The dense pattern catalog adds specialized reference material Claude does not have memorized at this fidelity, but the ~420-line body and the discursive 'PERSONALITY AND SOUL' section could be tightened; it is mostly efficient rather than maximally lean.	2 / 3
Actionability	Every one of the 24 patterns pairs a concrete 'Before'/'After' example showing exactly what to remove and the natural replacement, plus a full worked example with a change log — copy-pattern-ready, fully executable guidance.	3 / 3
Workflow Clarity	A clear 5-step 'Process' and 'Output Format' section exist with an implicit verification checklist ('Sounds natural when read aloud'), but there is no explicit validate-then-fix feedback loop and the steps are somewhat generic.	2 / 3
Progressive Disclosure	No bundle files exist and the body is a single well-organized monolithic file with clear section headers, but at ~420 lines the 24 detailed pattern entries are all inline with no one-level-deep references to split the material.	2 / 3
	Total	9 / 12 Passed

Description

77%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that covers both capability and trigger with concrete, enumerated pattern types in third-person voice. The main weakness is that the 'when' trigger is somewhat generic ('editing or reviewing text') rather than surfacing the natural phrasings users actually say when they want AI text de-slopified.

Suggestions

Add concrete natural trigger terms users would actually say, e.g. 'Use when the user says text sounds AI-generated, robotic, or like ChatGPT, or asks to humanize, de-AI, or make writing sound more natural.'

Tighten the Wikipedia provenance clause ('Based on Wikipedia's comprehensive...') which adds length without improving trigger matching or specificity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Remove signs of AI-generated writing', 'Detects and fixes patterns') and enumerates nine specific pattern types (inflated symbolism, promotional language, -ing analyses, etc.), matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Clearly answers what ('Remove signs of AI-generated writing'; 'Detects and fixes patterns including...') and when ('Use when editing or reviewing text to make it sound more natural and human-written') with an explicit trigger clause.	3 / 3
Trigger Term Quality	'Use when editing or reviewing text to make it sound more natural and human-written' gives relevant keywords, but misses common natural variations a user would say ('make this sound less AI', 'humanize this', 'this reads like ChatGPT'), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The AI-writing-pattern niche with named patterns is fairly distinct, but the trigger 'editing or reviewing text' is broad and could overlap with general editing/proofreading skills, leaving some conflict risk.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jdrhyne/agent-skills
Commit: a4d31ad

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

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.