humanizer

Write in a natural, human tone — no AI-speak, no filler, no corporate fluff.

Quality

80%

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

100%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 a model of a lean, well-structured instruction-only skill: concise, concrete, and well-organized with explicit boundary guidance, fully meeting each dimension's top anchor.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no padding or re-explanation of concepts Claude already knows; every rule earns its place with concrete examples, matching the 'lean, assumes competence, every token earns its place' anchor.	5 / 5
Actionability	As an instruction-only skill it gives concrete, copy-paste-ready guidance: exact phrases to drop ('I'd be happy to help'), specific word swaps ('Use' not 'utilise'), and worked examples ('Sales dropped 15% in March'); per scoring notes absence of code is not penalized when guidance is this actionable.	5 / 5
Workflow Clarity	This is a simple single-purpose skill under 50 lines with no destructive or batch operations, so the simple-skill exception applies; the single action (adjust writing style) is unambiguous and well-organized with a clear 'What this skill does NOT do' boundary section.	5 / 5
Progressive Disclosure	At under 50 lines with no need for external references, the guideline allows a 5 for well-organized sections; the body is cleanly split into Voice Rules, Structure Rules, Word Choice, and a boundary section with clear headers.	5 / 5
	Total	20 / 20 Passed

Description

61%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 clear and domain-specific with good natural trigger terms, but it omits an explicit 'Use when...' clause and lists anti-patterns rather than concrete actions, capping completeness and specificity at the mid-level anchors.

Suggestions

Add an explicit 'Use when...' clause (e.g. 'Use when the user asks to sound more human, less corporate, or to remove AI-speak') so completeness can exceed 3.

Reframe the anti-patterns as concrete actions (e.g. 'Rewrites responses to use contractions, short sentences, and plain words') to lift specificity above 3.

Add a couple more natural synonyms (e.g. 'conversational', 'chatty') to push trigger term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain ('natural, human tone') and three concrete anti-patterns ('no AI-speak, no filler, no corporate fluff'), but states no concrete actions the skill performs, matching the 'names domain and 1-2 concrete characterizations' anchor rather than the 4-anchor's list of specific actions.	3 / 5
Completeness	It clearly states the 'what' (write in a natural, human tone) but provides no 'Use when...' or equivalent trigger guidance, so per the judging guideline a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms users say ('human', 'tone', 'AI-speak', 'filler', 'corporate') with good coverage; a few synonyms (e.g. 'natural', 'conversational') are present but minor natural phrasings are missing, fitting the 4-anchor rather than the comprehensive 5-anchor.	4 / 5
Distinctiveness Conflict Risk	The 'natural human tone / no AI-speak' framing carves a distinct writing-style niche with minimal overlap risk; only slight overlap with general writing skills, matching the 4-anchor's 'mostly distinct, minor overlap' rather than the fully-distinct 5-anchor.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: siddsachar/row-bot
Path: bundled_skills/humanizer/SKILL.md
Commit: b4dcda4

Reviewed: 3 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.