humanizer

Remove AI writing patterns to make documentation sound natural, specific, and human. Covers content patterns, language patterns, style patterns, and communication patterns.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/humanizer/SKILL.md

Quality

Content

85%

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

The body is concise and well-structured with a clear sequenced workflow that includes a self-check pass and excellent progressive disclosure via verified reference files. The only weak spot is actionability, held at level 2 by the absence of worked examples and the deferral of concrete pattern lists to the references.

Suggestions

Add one or two short before/after rewrite examples in the body so the core transformation is immediately actionable without loading a reference.

Optionally inline the single most common tell per category so the skill is useful before any reference is opened.

Dimension	Reasoning	Score
Conciseness	The body is lean: a short intro, a four-step process, a brief 'Adding voice' section, and a references table, with no padding or explanation of concepts Claude already knows, matching the level-3 'every token earns its place' anchor.	3 / 3
Actionability	The procedural guidance is concrete (identify patterns via references, rewrite, run a final anti-AI pass naming remaining tells) and code absence is fine for an instruction skill, but the body lacks worked before/after examples and defers the actual pattern lists to reference files, fitting the level-2 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	The four steps are clearly sequenced and conclude with an explicit verification pass ('ask what makes this obviously AI generated, name the remaining tells, and fix them'), a review-and-fix loop that satisfies the level-3 'clear sequence with explicit validation steps' anchor; the operation is non-destructive so the missing-feedback-loop cap does not apply.	3 / 3
Progressive Disclosure	The body is a concise overview with a well-signaled one-level-deep references table, each entry pointing to a real file (all four reference files exist) with a clear description of what it covers, matching the level-3 anchor for clear, easy navigation with appropriately split content.	3 / 3
	Total	11 / 12 Passed

Description

50%

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

The description is clear and reasonably specific about the skill's purpose, but consistently lands at level 2 because it lacks an explicit "Use when..." trigger clause and fuller coverage of natural trigger terms. Adding trigger guidance and common user phrasings would lift the weaker dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when text sounds AI-generated, robotic, or generic, or when the user asks to humanize or naturalize writing.'

Include the natural phrasings users actually say ("sounds too AI", "make it less robotic", "humanize", "de-AI") to improve trigger-term coverage and distinctiveness.

List a couple more concrete actions beyond 'remove' (e.g. 'rewrite hollow passages, add specific details, vary sentence rhythm') to strengthen specificity.

Dimension	Reasoning	Score
Specificity	The description names a concrete action ("Remove AI writing patterns") and the domain, but offers only one primary action plus a list of covered categories rather than multiple distinct concrete actions, matching the level-2 anchor rather than the level-3 multi-action example.	2 / 3
Completeness	It clearly states what the skill does but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant natural keywords ("AI writing patterns", "documentation", "natural", "human") but misses common variations users actually say (e.g., "sounds too AI", "make it less robotic", "humanize"), fitting the level-2 anchor of partial coverage.	2 / 3
Distinctiveness Conflict Risk	The "remove AI writing patterns" niche is fairly specific, but without explicit triggers it could still overlap with general writing- or editing-improvement skills, matching the level-2 "could still overlap" anchor rather than a clearly distinct, conflict-free niche.	2 / 3
	Total	8 / 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: kubb-labs/kubb
Path: .agents/skills/humanizer/SKILL.md
Commit: 8349acf

Reviewed: 2 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.