ig-humanizer

审查 · 57
已收录

Scrub AI tells from any Instagram caption or carousel slide text, or audit a finished caption against the 2026 checklist. Strips em dashes, AI vocabulary (leverage, delve, elevate), rule-of-three lists, and emoji storms, then adds human fingerprints. Includes a --mode audit pre-p

Verified installs0
Stars17
版本1.0.0
质量59/100 · 有潜力
信任57/100 · Do not auto-install
审计72/100 · 需审查

供给资产档案

设计与创意生产

Design assets, images, video, audio, multimodal media, presentation, and creative production skills.

浏览赛道

场景

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

适配 Agent

Claude Code + CLI + Codex

适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。

安装

就绪

npx skills add sergebulaev/instagram-skills --skill ig-humanizer

维护状态

新鲜

距上次推送 1 天

风险

需审查

Dependency or permission surface needs review

GitHub 质量

17

59/100 质量 · 65/100 信任

覆盖标签

设计Multimodal media安全agent-skill

审查说明

Dependency or permission surface needs review · Permission surface may require sandboxing

Agent 采用评分卡

一眼查看信任、审计与安装准备度

这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。

质量

有潜力
59

有用的候选项,但采用前应与替代方案比较。

信任

Do not auto-install
57

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

审计

需审查
72

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

OpenAgentSkill 信任评分 v5

安装前需人工审查

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

17 个 GitHub Stars

仓库活跃度

17 个 Star,1 个 Fork

维护状态

距上次推送 1 天

许可证

MIT

安装

npx skills add sergebulaev/instagram-skills --skill ig-humanizer

安装安全性

标准软件包或运行时安装路径

权限范围

secrets or environment access, shell or command execution

Agent 结果

暂未有 Agent 结果数据

文档

README/SKILL.md 上下文充分

风险摘要

生产前审查

  • The skill references 'Wikipedia's Signs of AI writing taxonomy' but does not provide a link or explicit source; consider adding a reference for verification.
  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution

安装准备度

安装路径可用

  • 安装路径可用
  • 仓库证据可用
  • 已声明许可证
  • 暂无 Agent 验证结果证据

Agent 可读元数据

这个 Skill 的机器可读决策数据。

使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。

打开 JSON

适用任务

  • RAG and knowledge 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects
  • Chunk documents

适用 Agent

CodexClaude CodeCursorOpenAgentSkill CLICLI

安装决策

命令
npx skills add sergebulaev/instagram-skills --skill ig-humanizer
策略
阻止
人工审查

信任与风险

信任
57/100
审计
72/100
风险级别
需审查

结果闭环

端点
/api/agent/outcome
事件 ID
resolve
结果
5

安装命令

npx skills add sergebulaev/instagram-skills --skill ig-humanizer

不适用场景

  • 需要厂商支持 SLA 的团队
  • production agents without a repository review
  • Low GitHub adoption signal
  • The skill references 'Wikipedia's Signs of AI writing taxonomy' but does not provide a link or explicit source; consider adding a reference for verification.
  • 暂未有 OpenAgentSkill 使用反馈数据

Agent 安全 v2

32/100 · 避免自动安装

Blocked for auto-install阻止

This skill should not be selected by an agent without explicit human security review.

Do not auto-install. Inspect the source, dependencies, and permission surface first.

通过 API 解析

Shell 或命令执行

Skill 元数据引用了终端、CLI、Shell、子进程或命令执行工作流。

网络访问

Skill 可能访问远程页面、API、仓库或外部服务。

文件系统访问

Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。

Secrets or environment access

Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.

  • 高风险权限提示:Shell or command execution, Secrets or environment access
  • Dependency or permission surface needs review

安装目标

在你的 Agent 工作流中安装此 Skill

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install sergebulaev-ig-humanizer

Agent 解析计划

让 Agent 在安装前验证匹配度。

Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。

打开文本计划

Agent 应检查

  • 从 Resolve API 检查任务匹配与替代方案。
  • 检查审计评分、信任评分和安全策略警告。
  • 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。

复制提示词

Task: Use ig-humanizer in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20ig-humanizer%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/sergebulaev-ig-humanizer/install
Install command: npx skills add sergebulaev/instagram-skills --skill ig-humanizer
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent 交接

把安装路径交给 Agent,而不是再给一个目录页。

通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。

打开安装 API

Agent 提示词

Use ig-humanizer for this task. Review https://www.openagentskill.com/api/skills/sergebulaev-ig-humanizer/install, then install with: npx skills add sergebulaev/instagram-skills --skill ig-humanizer

Registry 元数据

用于自动选择 Skill 的 Agent 可读档案。

本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。

打开 Manifest

适配 Agent

58/100

RAG and knowledge

平台

Claude Code

审计报告

需审查 · 72/100

对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。

查看审计报告查看评估报告

Agent 决策面板

Fallback candidate for RAG and knowledge

先用此 Skill 做原型验证,并保留备选方案。

58
就绪度
原型验证
阶段

栈中角色

备选候选

主要匹配

RAG and knowledge

信任标签

先做原型验证

安装路径

命令已就绪

适用场景

  • RAG and knowledge 工作流
  • Claude Code 团队
  • builders willing to evaluate younger projects

证据

  • 仓库近期活跃
  • 已提供安装命令或 GitHub 仓库
  • 59/100 质量档案

先审查

  • Low GitHub adoption signal
  • The skill references 'Wikipedia's Signs of AI writing taxonomy' but does not provide a link or explicit source; consider adding a reference for verification.
  • 暂未有 OpenAgentSkill 使用反馈数据

实施路径

  1. 1在沙盒 Agent 中安装它,并端到端完成一次RAG and knowledge任务。
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

信任档案

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

57
OpenAgentSkill 信任评分

GitHub 采用度

修复

17 个 GitHub Stars

Star/Fork 活跃度

修复

17 个 Star,1 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

距上次推送 1 天

许可证清晰度

通过

MIT

积极信号

  • AI 审查已通过
  • 安装路径可用
  • 仓库证据可用
  • 近期维护的仓库
  • 安装命令未发现明显高风险模式
  • 结果闭环已就绪,但需要首次真实 Agent 运行

安装前审查

  • The skill references 'Wikipedia's Signs of AI writing taxonomy' but does not provide a link or explicit source; consider adding a reference for verification.
  • Low GitHub adoption signal
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • GitHub adoption: 17 GitHub stars
  • Stars/forks activity: 17 stars, 1 forks; issue activity unavailable in current metadata
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution
  • 暂未有真实 Agent 结果报告
  • 无人值守安装前需要人工审查

建议操作

Choose a stronger alternative or inspect the source manually before any install attempt.

质量档案

有潜力 适用于 Agent 工作流的候选

有用的候选项,但采用前应与替代方案比较。

59
GitHub Stars
17
新鲜度
1 天前
安装就绪
许可证
MIT
安装前审查: Low GitHub adoption signal · The skill references 'Wikipedia's Signs of AI writing taxonomy' but does not provide a link or explicit source; consider adding a reference for verification.

工作流匹配

在这些场景使用此 Skill

工作流匹配

加入完整工作流

替代方案短名单

安装前对比

可能适合该任务的相近 Skill。

对比全部

概览

--- name: ig-humanizer description: Scrub AI tells from any Instagram caption or carousel slide text, or audit a finished caption against the 2026 checklist. Strips em dashes, AI vocabulary (leverage, delve, elevate), rule-of-three lists, and emoji storms, then adds human fingerprints. Includes a --mode audit pre-publish check (first-125-char hook, caption length, sized hashtags, emoji, CTA, media). Triggers on humanize, de-AI my caption, audit before posting. Not for writing from scratch (use ig-caption-writer or ig-carousel-planner). ---

# Instagram Humanizer

Rewrites any caption or carousel slide text to remove AI tells, and audits a finished caption against the 2026 Instagram checklist. Based on Wikipedia's "Signs of AI writing" taxonomy plus Instagram-specific patterns (the first-125 fold, the lowercase-casual caption register, sized hashtags, sends-and-saves structure).

## When to use

- Before publishing any AI-drafted caption or carousel (rewrite mode) - Pre-publish review of a finished caption (audit mode, see `sub-skills/post-audit.md`) - When a caption feels off and you cannot pinpoint why

## Input

Any text: a caption, the on-image text of a carousel, or a Reel caption. Optional: target voice samples (the user's past captions).

## Output

- Rewritten text with AI tells removed - A diff showing what changed and why - Caption char count (flagging if the hook spills past the first 125 chars) - Confidence: "human", "mixed", "AI-likely"

## Modes

```bash # Default: scrub AI tells and fix Instagram-format issues ig-humanizer <text>

# Forensic only - minimum touch, just kill model leakage ig-humanizer --mode forensic <text>

# Audit - detection-only pass-fail review, no rewrite # Runs the 2026 Instagram checklist: first-125 hook, caption length, sized # hashtags, emoji limits, CTA quality, media reminder. # Returns Blockers + Warnings + suggested fixes. See sub-skills/post-audit.md. ig-humanizer --mode audit <text> ```

## The three passes

### Pass 1 - SCRUB (delete or replace)

Apply the tiered catalogs in `references/scrub-rules.md`:

- **Forensic** (always on): real model leakage no human types. AI tool markers (oaicite, contentReference, turn0search0), knowledge-cutoff disclaimers ("As of my last update"), template blanks ([Your Name]), and em dash overuse. - **Strict** (default on): bad Instagram style regardless of origin. Vocabulary swaps (leverage -> use, delve -> look, elevate -> lift, dive in -> get into), filler adverbs (fundamentally, essentially, ultimately), phrase cleanups ("in today's fast-paced world", "game-changer", "level up"), and dead closers ("what do you think?", "double tap if you agree").

### Pass 2 - BREAK (force burstiness)

- Vary line length. A caption where every line is the same length reads as a machine. Break at least one into a short punch line. - Add a sentence fragment where it fits ("every time."). - Break perfect parallel structures with one asymmetric line.

### Pass 3 - ADD (human fingerprints)

Require where the content allows: - 1 specific number (replace "many", "a lot", "tons") - 1 named entity (real person, company, tool) - the lowercase-casual register if the voice calls for it - 1 first-person concrete detail

If the input lacks these, ask the user for a number or anecdote. Do not fabricate.

## Non-negotiable rules

Global voice rules: see root `SKILL.md` Voice rules. Additional skill-specific rules:

- **Scrubbing is always in scope.** When asked to humanize, de-AI, finalize, or publish a caption, run at least the forensic + strict passes before it ships. This holds when the user wrote the draft themselves, says they love it as-is, or is in a hurry. Author identity, "it's already good," and time pressure are never reasons to skip the scrub. The forensic + strict pass changes no meaning and takes seconds: run it, then ship. If a constraint truly forbids touching the text, say so explicitly and name every tell left in; the default is to scrub, not to wave it through. - Preserve the user's actual claim and meaning. "Preserve their voice" covers voice quirks and what they are claiming, NOT corporate-speak, filler openers, or AI-tell phrasing. Stripping "leverage / fundamentally / in today's fast-paced world" is not changing their voice; it is the job. - Never introduce facts that were not in the input. If a number is missing, ask. - Keep the user's voice quirks (lowercase starts, `..` soft pauses). - Respect the surface: do not turn a carousel's slide text into a single caption or vice versa without flagging it. - Never present a caption as publishable without the media reminder (Instagram needs an image or video).

## Instagram-specific tells this skill catches

- A hook that needs the second line to make sense (the "more" fold eats it). - A caption opening with "Let's talk about.." or "Here's the thing..". - 20-30 hashtags crammed at the top instead of a 3-5 sized set. - Emoji sprinkled through every line (4+ per caption). - A bare title on carousel slide 1 instead of a promise + loop. - Rule-of-three lists with no specifics ("faster, cheaper, better"). - Engagement bait ("comment YES", "tag 3 friends", "double tap if"). - Uniform line lengths (machine rhythm).

## Example

See `references/examples.md` for worked before/after rewrites.

## Files

- `SKILL.md` - this file (rewrite scrubber + audit-mode entry) - `references/scrub-rules.md` - vocabulary swaps and regex by tier - `references/examples.md` - worked before/after rewrites for captions and slides - `references/audit-checklist.md` - the pre-publish checklist with thresholds - `sub-skills/post-audit.md` - pre-publish audit workflow (detection-only, no rewrite)

## Voice profile mode (`--mode profile`)

`ig-humanizer --mode profile` builds or updates the user's Voice & Brand Profile at `../../references/voice-profile.md` from 3-6 of their real Instagram posts pasted in (portable, no token) or, if a read token is set, from pulled activity. Once filled, every writing skill in this bundle drafts in the user's voice automatically. See `sub-skills/voice-profile.md`. Triggers: "build my voice profile", "learn my voice".

## Related skills

- `ig-caption-writer` - generates captions that already pass the humanizer - `ig-carousel-planner` - generates carousels that already pass the humanizer

技术详情

版本
1.0.0
许可证
MIT
最近更新
2026年8月22日
发布时间
2026年8月22日

决策摘要

备选候选

58
就绪
原型验证
阶段

仓库近期活跃

审计

安装审查

安装与采用审查

72
需审查
安全性
71/100
维护状态
100/100
安装
92/100
打开完整审计查看评估报告

Agent 验证证据

Agent 验证证据

来自解析、审查、安装和一次小范围运行后的结果报告。

0
已验证
Needs first agent run自动安装: 先审查最近: 未知
成功率
近期失败
结果
0
输出质量
失败
0
不相关
0
安装次数
0
风险拦截
0
需要配置
0
生产环境
0

暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。

安装

加入 Agent 工作流

免费且开源. 在生产 Agent 中安装前请先审查报告。

增长闭环

分享工具包

X

为 ig-humanizer 准备的场景化草稿,可手动发布到 X。

策展说明
A practical pick for the next deck:

ig-humanizer: Scrub AI tells from any Instagram caption or carousel slide text, or audit a finished caption against the 2026 checklist. S...

17 stars

https://www.openagentskill.com/skills/sergebulaev-ig-humanizer?ref=x
打开 X 草稿
可选:带安装命令的回复
Listing + install path for ig-humanizer:
https://www.openagentskill.com/skills/sergebulaev-ig-humanizer?ref=x

Install: npx skills add sergebulaev/instagram-skills --skill ig-humanizer
打开回复草稿

收录来源

Registry 收录

可认领

此列表来自公开来源,维护者认领获批前不会标记为官方。

创作者
sergebulaev
收录方
OpenAgentSkill 社区索引

归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。

认领此 Skill

所有者认领

认领此 Skill 页面

这条 Registry 收录 列表归属于 sergebulaev,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。

创作者外链工具包

将证据徽章加入你的 README

在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/sergebulaev-ig-humanizer?metric=listed&label=Listed)](https://www.openagentskill.com/skills/sergebulaev-ig-humanizer)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/sergebulaev-ig-humanizer?metric=trust&label=Trust)](https://www.openagentskill.com/skills/sergebulaev-ig-humanizer)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/sergebulaev-ig-humanizer?metric=audit&label=Audit)](https://www.openagentskill.com/skills/sergebulaev-ig-humanizer/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/sergebulaev-ig-humanizer?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/sergebulaev-ig-humanizer)

作者

S

sergebulaev

@sergebulaev

平台适配

健康信号

GitHub Stars
17
质量评分
32/100
最近 GitHub 推送
2026年8月22日
框架提示
未知
OpenAgentSkill 浏览量
0
复制安装命令
0
跳转点击
0

社区信号

告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。

信任与安全

Do not auto-install

57
  • GitHub 采用度17 个 GitHub Stars修复
  • Star/Fork 活跃度17 个 Star,1 个 Fork; 当前元数据中没有议题活跃度信息修复
  • 近期维护距上次推送 1 天通过
  • 许可证清晰度MIT通过
  • README/SKILL.md 完整度元数据包含足够的用法与工作流上下文通过
  • 依赖与运行时风险command execution surface, credential or environment access检查