BF humanizer-zh
去除文本中的 AI 生成痕迹。当用户说"润色"、"改写"、"去 AI 味"、"更像人写的"、 "不要太机械"、"自然一点"、"有人味"时使用。也用于：编辑邮件/文案/文章/报告、 审阅 AI 生成内容、优化写作风格、让文字不那么像机器生成的。基于维基百科"AI 写作特征"指南， 检测并修复：夸大象征、宣传语言、模糊归因、三段式、AI 词汇、否定式排比、破折号滥用。
As a process F 31/100 · Will not run — References files that are not bundled: references/full-patterns.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
For the model run — optional
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/full-patterns.md
Process rating: all ten parameters 31/100
Will not run. References files that are not bundled: references/full-patterns.md
- 0Tools and files. 1 referenced file(s) missing: references/full-patterns.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (humanizer-zh) differs from the folder (elatia-humanizer-zh)
- 100Steps. 57 steps
- 100Execution cost. Instruction body is 1252 tokens
- 100Running it twice. No mutating operations
- low 11 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 183: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.
External checks
ClawHub: clean
This is a disclosed Chinese writing-editing skill with no executable code, network behavior, credential access, persistence, or hidden destructive actions.
LLM: benign (high) · VirusTotal: · 29 May 2026