AB chinese-humanizer
Rewrite Chinese AI-generated or AI-polished drafts into natural, credible, genre-appropriate text. Use when the user asks to 去 AI 味, 去机器味, humanize Chinese writing, remove 公文腔/营销腔/翻译腔/套话, make a draft 像真人写, 保留意思但别那么模板, polish an AI 草稿, or adapt Chinese text to a genre such as 官网文案, 产品介绍, 投融资材料, 商务邮件, 公众号, 知乎, 小红书, 口播稿, 新闻评论, 技术博客, 产品文档, 咨询报告, 行业分析, 学术摘要, 申请文书, 个人陈述, 求职信, 反思总结. Improves editorial quality and authenticity. Do NOT use for pure translation, pure summarization, or factual research alone. This skill must never promise to bypass AI detectors, fabricate facts/sources/experiences, or optimize for detector scores.
Rewrite Chinese AI-generated or AI-polished drafts into natural, credible, genre-appropriate text.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 628 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Consistency. The Hermes dialect needs category and tags
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 27 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 1401 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 628: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 27 items
- +4Reference files are cited in the instructions (7 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.