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

Passed

No findings from the security scan

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 body is a well-structured, highly actionable three-mode workflow with a genuine validation loop and clean progressive disclosure into two real reference files and a working scorer script. Its only cost is mild redundancy in the mode overview section and occasional stylistic padding.

Dimension	Reasoning	Score
Conciseness	Most sections earn their tokens — replacement tables, score thresholds, and a full before/after example are all load-bearing — but the 'How This Skill Works' section summarizes all three modes that are then described in full, and a few rhetorical flourishes ("This is not a cleaning service") could be trimmed, fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Fully executable guidance: a real command (`python3 scripts/humanizer_scorer.py draft.md --json`, script verified present), numeric decision thresholds (80+/60-79/below 60), a concrete AI-phrase-to-human-alternative replacement table, and a worked before/after example with the changes enumerated. Placeholders like "[Named company]" are explicitly justified ("the structure is what matters").	5 / 5
Workflow Clarity	The three modes (Detect → Humanize → Voice Injection) are clearly sequenced with guidance on running them in one pass vs. splitting, and the scorer provides an explicit validation feedback loop ("Re-run after humanizing; the score must move") plus a Proactive Triggers section covering failure modes such as tell density too high for a patch job.	5 / 5
Progressive Disclosure	Two well-signaled, one-level-deep references — [references/ai-tells-checklist.md] and [references/voice-techniques.md] — both verified as real, relevant files, each tied to a specific mode, with the bulk detail (full tell vocabulary, voice-technique playbook) appropriately split out while the body keeps only a snapshot it explicitly labels as such.	5 / 5
	Total	19 / 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.

A strong description with explicit what/when framing, natural literal trigger phrases, and clear negative boundaries that disambiguate it from sibling skills like content-production. The only gap is that it describes the outcome rather than enumerating the concrete actions the skill performs (detect, humanize, inject voice).

Dimension	Reasoning	Score
Specificity	The description states one clear transformation — "Makes AI-generated content sound genuinely human" — and names the domain (AI clichés, robotic writing, personality), but does not enumerate the underlying concrete actions (pattern detection, pattern removal, voice injection), matching the 'names domain and 1-2 concrete actions' anchor rather than the 'lists several specific actions' anchor.	3 / 5
Completeness	It explicitly answers both: what ("Makes AI-generated content sound genuinely human — not just cleaned up, but alive") and when ("Use when content feels robotic, uses too many AI clichés, lacks personality, or reads like it was written by committee") with concrete trigger phrases, plus negative scope guidance.	5 / 5
Trigger Term Quality	The quoted triggers — "this sounds like AI", "make it more human", "add personality", "it feels generic", "sounds robotic", "fix AI writing", "inject our voice" — are literal phrases a user would naturally say, with comprehensive synonym coverage of how users describe robotic-sounding content.	5 / 5
Distinctiveness Conflict Risk	A clear niche (rewriting existing AI-flavored content) with explicit boundaries — "NOT for initial content creation (use content-production). NOT for SEO optimization (use content-production Mode 3)" — giving minimal conflict risk with related skills.	5 / 5
	Total	18 / 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: 16 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.