
humanize-it
对指定文档进行去 AI 味的改写。自动选择最合适的人性化策略(humanizer-zh / humanize-chinese / technical-writing), 迭代改写直到效果达标或迭代 42 次为止。适用于中文文本的去 AI 化处理,包括通用文章、技术文档、学术论文等。 Use when user says: "humanize this", "去AI味", "降AIGC", "人性化改写", "改成人话", "去除AI痕迹", "humanize document", "make text human-like", "去机器味", "降低AI率", "过AIGC检测"
- Installs
- 534
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/smallnest/goal-workflow --skill humanize-it- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads humanize-it automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Humanize-It: 迭代式去 AI 味改写
对指定文档进行去 AI 味的改写。根据文本类型和内容,从三个子 skill 中自动选择最合适的一个开始改写。如果改写效果不满意,换用另一个 skill 继续迭代,直到效果达标或达到 42 次迭代上限。
子 Skill 能力矩阵
| Skill | 适用场景 | 核心能力 | 改写风格 |
|---|---|---|---|
| humanizer-zh | 通用文本、文章、博客、文案 | 识别 24+ AI 写作模式,注入个性与灵魂,节奏变化 | 自然、有温度、带观点 |
| humanize-chinese | 通用 + 学术 + 长文本 | 20+ 规则检测 + 统计特征 + LR 融合评分,CLI 工具链 | 多种风格可选(知乎/小红书/学术/文学等) |
| technical-writing | 技术文档、架构说明、设计稿、评审文档 | 去除技术黑话,证据先行,消除主持腔 | 平实、严谨、可论证 |
工作流程
第一步:读取文档并分析
- 读取用户指定的文档内容
- 判断文档类型:
- 技术文档(技术方案、架构说明、设计文档、评审稿)→ 优先使用
technical-writing - 学术论文(论文、研究文章)→ 优先使用
humanize-chinese(学术模式) - 通用文本(博客、文案、文章)→ 优先使用
humanizer-zh - 长文本(≥1500 字)→ 优先使用
humanize-chinese(长文本模式)
- 技术文档(技术方案、架构说明、设计文档、评审稿)→ 优先使用
第二步:改写策略选择
根据文档类型选择第一个改写 skill:
文档类型判断:
├── 技术文档 → technical-writing → humanizer-zh → humanize-chinese
├── 学术论文 → humanize-chinese(academic) → humanizer-zh → technical-writing
├── 通用文本 → humanizer-zh → humanize-chinese → technical-writing
└── 长文本(≥1500字) → humanize-chinese(longform) → humanizer-zh → technical-writing
第三步:迭代改写循环
iteration = 0
MAX_ITERATIONS = 42
while iteration < MAX_ITERATIONS:
iteration += 1
# 使用当前 skill 进行改写
result = humanize(current_text, current_skill)
# 评估改写效果
score = evaluate(result)
if score >= PASS_THRESHOLD:
# 改写效果达标,输出最终结果
output(result)
break
# 效果不达标,切换到下一个 skill
current_skill = next_skill(skill_order)
current_text = result # 在上次改写基础上继续优化
if all_skills_exhausted():
# 所有 skill 都用过一轮,从头开始新一轮组合
current_skill = first_skill(skill_order)
第四步:质量评估
每次改写后,按以下维度评估效果(百分制):
| 维度 | 权重 | 评估标准 |
|---|---|---|
| AI 痕迹去除 | 30% | 三段式、套话、机械连接词是否消除 |
| 自然度 | 25% | 读起来是否像人写的,节奏是否自然 |
| 信息完整 | 20% | 核心信息是否保留,没有丢失关键内容 |
| 风格一致 | 15% | 语气是否前后统一,符合文档类型 |
| 可读性 | 10% | 句子是否通顺,逻辑是否清晰 |
评分标准:
- ≥ 80 分:通过,输出结果
- 60-79 分:尚可,再迭代一轮看能否提升
- < 60 分:不达标,必须继续改写
第五步:输出结果
输出最终改写结果,附带:
- 改写后的完整文本(写入原文件或指定输出文件)
- 改写摘要(使用了哪些 skill,迭代了几次,最终评分)
- 主要改动点列表
具体执行指令
调用 humanizer-zh 时
使用 Skill 工具调用 humanizer-zh,将文档内容传入,让其按 24 种 AI 写作模式进行检测和改写。重点关注:
- 删除填充短语
- 打破公式结构
- 变化节奏
- 信任读者
- 删除金句
- 注入个性与灵魂
改写后按其 50 分制质量评分进行初步评估(≥ 40 分为达标)。
调用 humanize-chinese 时
使用 Skill 工具调用 humanize-chinese,根据文档类型选择对应模式:
- 通用文本:使用 detect + rewrite 流程
- 学术论文:使用 academic 模式
- 长文本:使用
--scene novel或--scene auto
如果 CLI 工具可用,优先使用 CLI 进行量化检测和改写;否则按其 LLM 使用指南手动执行。
改写后按其 0-100 分评分体系评估(≤ 35 分为 LOW 区间,达标)。
调用 technical-writing 时
使用 Skill 工具调用 technical-writing,主要用于技术文档的改写。重点关注:
- 去除 buzzword 黑名单中的词汇
- 消除主持腔和评价腔
- 按「条件 → 对象 → 判断」重写句子
- 证据先行,减少无支撑的强判断
- 去除过场句
迭代策略细节
何时切换 Skill
- 同一个 skill 连续改写 3 次评分无提升 → 切换到下一个 skill
- 评分下降 → 回退到上一个版本,切换 skill
- 所有 skill 都用完一轮但未达标 → 从第一个 skill 重新开始,但使用上一轮的改写结果作为输入
- 达到 42 次迭代 → 输出当前最佳结果
组合策略
不同 skill 的改写侧重不同,组合使用可以互补:
- humanizer-zh → humanize-chinese:先注入个性灵魂,再做量化去 AI 模式
- humanize-chinese → humanizer-zh:先做系统化去 AI,再注入温度
- technical-writing → humanizer-zh:先保证技术严谨性,再增加自然度
- humanizer-zh → technical-writing:先去除通用 AI 痕迹,再调整技术语气
用户交互
如果用户提供了明确的偏好(如"保持学术风格"、"要更口语化"、"技术文档不要太随意"),在改写时遵循用户偏好,并优先选择对应的 skill。
如果用户未指定文档类型,可以通过 AskUserQuestion 询问:
- 文档类型(通用 / 技术 / 学术)
- 期望的改写风格(自然随意 / 平实严谨 / 学术规范)
- 是否需要写入原文件还是输出到新文件
FAQ
What does the humanize-it skill do?
对指定文档进行去 AI 味的改写。自动选择最合适的人性化策略(humanizer-zh / humanize-chinese / technical-writing), 迭代改写直到效果达标或迭代 42 次为止。适用于中文文本的去 AI 化处理,包括通用文章、技术文档、学术论文等。 Use when user says: "humanize this", "去AI味", "降AIGC", "人性化改写", "改成人话", "去除AI痕迹", "humanize document", "make text human-like", "去机器味", "降低AI率", "过AIGC检测"
How do I install humanize-it?
Run npx skills add https://github.com/smallnest/goal-workflow --skill humanize-it in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/humanize-it/ (personal) or .claude/skills/humanize-it/ (project).
Which AI agents can use humanize-it?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is humanize-it safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains humanize-it?
It is published by smallnest in smallnest/goal-workflow. It has 534 recorded installs.
More from smallnest/goal-workflow
smell
smallnest/goal-workflow
Detect software architecture bad smells, algorithmic complexity hotspots, and anti-patterns in a codebase. Produces a detailed markdown report identifying violations of architectural principles, design patterns, code quality, and performance complexity. Triggers on: smell, code smell, architecture smell, find anti-patterns, detect bad smells, complexity analysis, 代码坏味道, 架构坏味道, 反模式, 找出坏味道, 复杂度分析.
prd
smallnest/goal-workflow
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. After PRD is confirmed, use /prd-to-spec (optional) for technical design, then /to-issues to create implementable tickets. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out, 写PRD, 需求文档, 需求分析, 规格说明.
insight-diagram
smallnest/goal-workflow
为任意项目生成 UML 图、架构图和流程图。分析代码库后让用户选择要生成的图表类型,使用 architecture-diagram skill 渲染为 HTML+SVG,保存到 docs/ 目录。适用于任何软件项目的文档可视化。
refactor
smallnest/goal-workflow
Expert code refactoring based on Martin Fowler's catalog — improve maintainability without changing behavior. Covers code smells, composing methods, moving features, organizing data, simplifying conditionals, method calls, and generalization. Triggers on: refactor, 重构, clean up, improve code, code smell, extract method, rename, simplify.
modern-go
smallnest/goal-workflow
Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code", "gofix", or wants to upgrade Go idioms.
review-it
smallnest/goal-workflow
Code review closeout for Claude Code, Codex, OpenCode, DeepSeek TUI, and Antigravity CLI: local dirty changes, branch vs main, parallel tests.
Popular docs & writing skills
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
lark-markdown
open.feishu.cn
飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。
writing-beats
mattpocock/skills
Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.
writing-shape
mattpocock/skills
Writing, exploit: shape raw material into an article, paragraph by paragraph.
writing-fragments
mattpocock/skills
Writing, explore: mine raw fragments, no structure yet.
writing-for-agents
mattpocock/skills
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.