humanizer-zh

Revise Chinese text to sound specific, fluent, restrained, and human while preserving facts and author intent.

Quality

70%

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 ./resources/bundled-skills/humanizer-zh/SKILL.md

Quality

Content

86%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.

A tight, well-structured instruction-only skill: every section is operational, the workflow is clearly sequenced with completion gates, and the compact single-file structure fits the simple-skill ideal. The only meaningful gap is the absence of worked before/after examples and an explicit re-validation loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a routing table, five terse workflow steps, gates, and boundaries with zero concept explanations or padding. Every line carries operational guidance, matching the anchor for lean and efficient content.	5 / 5
Actionability	Steps are concrete and executable in intent ("Mark generic abstractions, repetitive transitions, inflated claims, and uniform sentence patterns"; "Vary sentence length and connective density") plus a tool routing table. It falls short of 5 only because no worked before/after Chinese examples are provided to anchor what a good revision looks like.	4 / 5
Workflow Clarity	The five-step workflow is clearly sequenced and the "Completion gates" section supplies checkpoints (preserve names/numbers/citations, no added anecdotes, still answers the original purpose). It is not a 5 because there is no explicit validate-then-fix feedback loop after the gates are checked.	4 / 5
Progressive Disclosure	The skill is under 50 lines, has no bundle files and no need for external references, and is organized into well-labeled sections (Purpose, Tool routing, Workflow, Completion gates, Boundaries, Delivery), which scores 5 under the simple-skill guideline.	5 / 5
	Total	18 / 20 Passed

Description

53%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 states a clear, concrete capability but omits any "when to use" trigger guidance, which caps its completeness and limits natural trigger-term coverage. It is concise and reasonably distinct within the Chinese-writing niche.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to revise, rewrite, or polish Chinese text, or to make Chinese writing sound less machine-generated or more natural."

Include natural synonym phrasings users actually say — such as "rewrite", "polish (润色)", "de-AI-ify", or "make it sound natural" — to broaden trigger-term coverage.

Optionally list a couple of concrete capabilities (e.g. replacing generic abstractions with concrete subjects, varying sentence cadence) to lift specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	"Revise Chinese text to sound specific, fluent, restrained, and human" names the domain and one concrete action with several outcome qualities, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because it does not list several distinct specific actions, and not a 2 because it goes beyond bare domain naming.	3 / 5
Completeness	The "what" is clear (revise Chinese text while preserving facts and author intent) but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	Relevant keywords like "Chinese text", "revise", and "human" are present, but common user phrasings such as "rewrite", "polish" (润色), or "make it sound natural" are missing. This fits the anchor for some relevant keywords lacking common variations or synonyms.	3 / 5
Distinctiveness Conflict Risk	The Chinese-language revision niche with its distinctive "specific, fluent, restrained, and human" framing is mostly distinct, with only minor overlap risk against general editing or translation skills. It is not a 5 because no explicit trigger phrases carve out the niche unambiguously.	4 / 5
	Total	13 / 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: KunAgent/Kun
Path: resources/bundled-skills/humanizer-zh/SKILL.md
Commit: ebce7f6

Reviewed: 5 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.