Name: content-humanizer
Rating: 64 (1 reviews)
Author: alirezarezvani

content-humanizer

Makes AI-generated content sound genuinely human — not just cleaned up, but alive. Use when content feels robotic, uses too many AI clichés, lacks personality, or reads like it was written by committee. Triggers: 'this sounds like AI', 'make it more human', 'add personality', 'it feels generic', 'sounds robotic', 'fix AI writing', 'inject our voice'. NOT for initial content creation (use content-production). NOT for SEO optimization (use content-production Mode 3).

Quality

76%

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 ./.gemini/skills/content-humanizer/SKILL.md

The canonical home for this skill is content-humanizer in alirezarezvani/claude-skills

Quality

Content

63%Weight 40%Scale 1-5

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

The content is highly actionable with concrete phrase-replacement tables, rhythm guidance, and worked before/after examples, supported by a clearly sequenced three-mode workflow with score-band checkpoints. Its weaknesses are verbosity from explaining AI behavior Claude already knows and broken/dangling references to bundle files that are not present.

Suggestions

Ship the referenced bundle files (references/ai-tells-checklist.md, references/voice-techniques.md, scripts/humanizer_scorer.py) or remove the inline references so navigation is not broken.

Trim editorial padding and explanations of why AI writes the way it does (e.g., 'It hedges because it doesn't know if it's right', 'Remarkably consistent. Remarkably boring.') to improve token efficiency.

Move the duplicated AI-tell category list out of the body and into references/ai-tells-checklist.md so the core SKILL.md stays a lean overview, and add an explicit error-recovery branch for when the re-run score does not move.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but includes unnecessary explanation of AI behavior Claude already knows ('It hedges because it doesn't know if it's right', 'AI is remarkably consistent. Remarkably boring.') and editorial padding ('Every time.', 'Readers actually like these.') that could be tightened.	3 / 5
Actionability	It provides concrete, copy-paste-ready guidance — a phrase-replacement table, specific rhythm patterns, and a real before/after — but the one executable command ('python3 scripts/humanizer_scorer.py draft.md --json') points to a script that is not present in the bundle, a minor gap that keeps it below fully executable.	4 / 5
Workflow Clarity	The three-mode sequence (Detect → Humanize → Voice Injection) is clearly ordered with explicit score-band checkpoints ('80+ light polish', '60-79 Mode 2', 'below 60 full rewrite') and a re-run feedback loop ('the score must move'), but the feedback loop lacks an explicit error-recovery branch, a minor validation gap.	4 / 5
Progressive Disclosure	References are clearly signaled ('See references/ai-tells-checklist.md', 'See references/voice-techniques.md') and the sectioning is good, but the referenced files and the scripts/ directory do not exist in the bundle, and the AI-tell categories are duplicated in the body rather than offloaded to the (missing) checklist, so navigation is partly broken.	3 / 5
	Total	14 / 20 Passed

Description

90%Weight 40%Scale 1-5

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 strong: it clearly states what the skill does, when to use it with concrete trigger quotes, and explicitly distinguishes it from adjacent skills via negative boundaries. Its only weak spot is specificity, as it describes a single transformation rather than enumerating multiple distinct actions.

Dimension	Reasoning	Score
Specificity	It names the domain ('AI-generated content') and one concrete transformation ('sound genuinely human — not just cleaned up, but alive'), but does not list several distinct concrete actions, so it matches 'names domain and 1-2 concrete actions' rather than the multi-action 4/5 anchors.	3 / 5
Completeness	It explicitly answers both what ('Makes AI-generated content sound genuinely human') and when ('Use when content feels robotic... Triggers: ...') with concrete trigger phrases, matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	It gives comprehensive natural-language triggers users would actually say ('this sounds like AI', 'make it more human', 'add personality', 'sounds robotic', 'fix AI writing') plus four 'Use when' conditions, covering synonyms and variations thoroughly.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (humanizing, not creating) and explicitly disambiguates from sibling skills ('NOT for initial content creation (use content-production). NOT for SEO optimization'), giving distinct triggers and minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/content-humanizer/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours 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.