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

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

92%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 skill body is well-organized and highly actionable: a clear three-mode workflow, a validation feedback loop via the scorer, and clean offloading of detail to real reference files. The only minor weakness is occasional rhetorical color that costs tokens without adding instruction.

Suggestions

Tighten rhetorical asides like 'Remarkably boring.', 'Every time.', and 'Instantly human.' — they earn their place as voice demonstrations but a few could be cut to reduce token load.

The 7 core AI-tell categories are inlined in SKILL.md while references/ai-tells-checklist.md holds the comprehensive list; consider trimming the inline snapshot to the top 3-4 tells and deferring the rest to the checklist to reduce duplication.

Add a one-line explicit retry/escalation note when the post-humanize score does not move (e.g., fall back to full rewrite), making the feedback loop's failure path as explicit as its success path.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and skips generic primer material, but carries rhetorical flourishes ('Remarkably boring', 'Every time', 'Instantly human') and illustrative asides that, while on-theme, are trimmable tokens.	4 / 5
Actionability	It provides a copy-paste scoring command with score-band interpretation, a concrete AI-phrase-to-human-alternative table, and worked before/after examples — fully executable and specific guidance covering the common cases.	5 / 5
Workflow Clarity	Three modes are clearly sequenced (Detect → Humanize → Voice Injection) with an explicit validation feedback loop (run the scorer, 'the score must move', re-run after humanizing) and severity/pause checkpoints via the Proactive Triggers.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with well-signaled, one-level-deep references to real files (references/ai-tells-checklist.md and references/voice-techniques.md) plus a real scorer script, with duplication of the tell list explicitly acknowledged as a snapshot.	5 / 5
	Total	19 / 20 Passed

Description

95%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.

This is a strong, well-structured description: it states the purpose, gives explicit use-when triggers with natural phrasing, and draws clear boundaries against adjacent skills. The only minor gap is that capabilities are expressed as outcomes rather than a fully enumerated action list.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('sound genuinely human', removing 'AI clichés', adding 'personality', injecting 'our voice'), though it is framed more as outcomes than an exhaustive enumerated action list.	4 / 5
Completeness	It clearly answers 'what' (make AI content sound human) and 'when' (a 'Use when...' clause plus concrete trigger phrases), satisfying both halves explicitly.	5 / 5
Trigger Term Quality	An explicit 'Triggers:' list provides natural user phrases ('this sounds like AI', 'make it more human', 'sounds robotic', 'fix AI writing', 'inject our voice') plus synonyms, covering what users would actually say.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (humanizing existing AI content) and adds explicit 'NOT for' boundaries pointing to content-production and its SEO mode, minimizing overlap with sibling skills.	5 / 5
	Total	19 / 20 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: alirezarezvani/claude-skills
Path: marketing-skill/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.