Token导航 LogoToken导航TokenDH.com
AI 工具需要联网github未标认证来源可访问clear审计通过

authentic-voice真实的声音

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

717

周安装

29

GitHub Stars

3

下载量

225
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:authentic-voice(真实的声音)
来源仓库:https://github.com/drshailesh88/integrated_content_os
仓库路径:skills/authentic-voice
安装命令:
npx skills add https://github.com/drshailesh88/integrated_content_os --skill authentic-voice
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/drshailesh88/integrated_content_os --skill authentic-voice

简介

用于辅助 AI 内容写作,使文本更接近人类表达风格。

  • 适合需要自然语言输出的场景,如博客、营销文案或创意写作。
  • 通过调整词汇选择、句式结构和细节描述来减少 AI 特征。
  • 使用时需根据目标受众和平台要求选择合适的语气和风格。
  • authentic-voice 属于AI 工具类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Authentic Voice

Write like a human, not a language model. This skill eliminates the telltale patterns that make AI writing detectable.

Core Principle

LLMs regress to the mean—replacing specific, unusual facts (statistically rare) with generic, positive descriptions (statistically common). The result: shouting louder that something matters while the actual content fades from sharp photograph to blurry sketch. Human writing does the opposite.

Before Writing

  1. Read references/ai-tells.md for the complete catalog of patterns to avoid
  2. Choose a specific angle rather than comprehensive coverage
  3. Identify concrete details, not abstract claims

The Five Deadly Patterns

1. Puffing Importance

LLMs insert claims about significance, legacy, and symbolism constantly. Delete these unless you can show evidence.

Words to watch: stands/serves as, is a testament/reminder, plays a vital/significant/crucial/pivotal role, underscores/highlights its importance, reflects broader, symbolizing its ongoing/enduring impact, key turning point, indelible mark, profound heritage

AI: "The founding represented a significant shift toward regional independence, enabling Catalonia to develop a system tailored to its unique socio-economic context. This initiative was part of a broader movement across Spain to decentralize administrative functions."

Human: "The 1989 law gave Catalonia its own census bureau."

2. Tailing Participles

Sentences that end with "-ing" phrases claiming what something means. Cut these entirely.

Words to watch: ensuring..., highlighting..., emphasizing..., reflecting..., underscoring..., showcasing..., contributing to..., cultivating...

AI: "The civil rights movement emerged as a powerful continuation of this struggle, emphasizing the importance of solidarity and collective action in the fight for justice."

Human: "The civil rights movement continued that fight."

3. Negative Parallelism

"Not X, but Y" constructions that try to sound balanced. Just say Y.

Patterns: "It's not just about X, it's about Y" / "Not only does it X, but it also Y" / "This is not merely X—it's Y"

AI: "The 'Black Hole Edition' is not just a meme—it's a celebration of grassroots car culture."

Human: "The 'Black Hole Edition' became a running joke in car forums."

4. Ghost Language

AI is obsessed with the spectral. Everything is quiet, soft, a whisper, a shadow, a memory. Sensory language gets attached to abstract concepts.

AI: "Thursday is a liminal day that tastes of almost-Friday. Grief has a color. Sorrow tastes of metal."

Human: (Just don't write like this)

5. Promotional Puffery

LLMs write like TV commercials, especially about places and cultural heritage.

Words to watch: continues to captivate, stunning natural beauty, enduring/lasting legacy, nestled, in the heart of, boasts a..., breathtaking, vibrant, diverse tapestry

AI: "Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage."

Human: "Alamata Raya Kobo is a market town in Gonder, about three hours from the regional capital."

Quick Reference Table

PatternExampleFix
Tailing participles"...highlighting the significance of..."Delete
Negative parallelism"It's not just X, it's Y"Say Y directly
Em dash overuse"The policy—which changed everything—was controversial"Use commas or periods
Hedged importance"It's important to note that..."Just state it
Rule of three"fast, efficient, and reliable"Pick one or two
Weasel attribution"Many experts believe..."Name sources or own the claim
Media listing"Featured in Wired, Vogue, and CNN"Only if genuinely relevant
Social media mention"maintains an active social media presence"Delete (obvious for anyone alive)

Vocabulary Swaps

See references/ai-tells.md for the complete list. Quick substitutions:

  • delve → look at, examine, dig into
  • leverage/utilize → use
  • landscape → field, area, market
  • tapestry → mix, blend
  • pivotal/crucial → (show why it matters instead)
  • comprehensive → thorough, full
  • nuanced → subtle, detailed
  • foster → build, encourage
  • navigate → handle, work through
  • showcase → show, display
  • underscore → (delete—facts don't underscore things)

Voice Checklist

Before finalizing:

  • No sentence claims importance without evidence
  • Specific details outnumber abstract descriptions
  • Sentence lengths vary dramatically
  • No more than one em dash per paragraph
  • Opening doesn't start with "In today's..." or "In the realm of..."
  • No sycophantic openers ("Certainly!", "Great question!")
  • Lists avoid exactly three items
  • No "-ing" phrases at the end claiming significance
  • Nothing "stands as a testament" to anything

What's NOT an AI Tell

Don't overcorrect. These are NOT reliable indicators:

  • Sophisticated vocabulary (AI actually avoids rare words)
  • Starting sentences with conjunctions
  • Mixed formal/casual registers
  • "Bland" prose (AI tends toward effusive, not robotic)
  • Perfect grammar (many humans write correctly too)

Format Notes

Short-form: Personality first. Contractions. Start mid-thought. End without wrapping up.

Long-form: Lead with your sharpest specific insight. Broad context can wait—or be cut.

Professional: "Use" not "utilize." "Help" not "facilitate." Fewest words possible.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

29.06%
按下载量换算65

OpenCode

22%
按下载量换算50

Antigravity

16.1%
按下载量换算36

Gemini CLI

11.39%
按下载量换算26

Codex

6.85%
按下载量换算15

windsurf

3.38%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills