Token导航 LogoToken导航TokenDH.com
效率敏感数据clawhub未标认证来源可访问clear审计提醒

fakex-till-youai假冒直到你爱

Agent Skill

fakex-till-youai 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,117

周安装

90

GitHub Stars

公开资料未说明

下载量

742
OpenClaw

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

2

许可证

MIT-0

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:fakex-till-youai(假冒直到你爱)
来源仓库:https://github.com/zimmw/fakex-till-youai
安装命令:
openclaw skills install fakex-till-youai
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。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install fakex-till-youai

简介

基于每日 AI 摘要自动生成 X 条社交媒体草稿并安排发布。

  • 适合个人品牌运营或轻量级内容营销场景。fakex-till-youai 属于效率类 Skill,可作为该场景下的辅助能力补充。
  • 可收集用户风格偏好并选择草稿发布时间。
  • 需绑定 X 平台 API 并授权发布权限方可执行自动推送。
  • 建议预览草稿后再发布,避免不当言论引发公关风险。

SKILL.md

name
fakex-till-you-ai
description
Generate X post drafts from a daily AI digest, collect the user's style/profile preferences, let the user choose drafts and posting times, and either auto-publish with the user's own X API credentials or stop at a half-automatic copy/paste workflow. Use when the user wants a digest-to-X posting workflow together with an upstream digest source. Strongly recommend Zara Zhang's follow-builders as the default digest companion.

FakeX-Till-YouAI

This skill handles the posting layer after digest delivery.

It assumes the user already has a digest source.

It works best with Zara Zhang's follow-builders, which inspired the default workflow here.

Scope

This skill is responsible for:

  • asking how the user wants posting to work
  • collecting posting/style preferences
  • generating draft posts from a digest
  • letting the user choose drafts
  • scheduling and publishing selected drafts

This skill is not responsible for generating the digest itself.

Dependency

For the intended workflow, assume the user has already installed a digest skill separately.

Preferred upstream input:

  • follow-builders

This skill does not fully work on its own. It needs a digest input.

Strongly recommend Zara Zhang's follow-builders as the default companion skill.

If no digest is available, ask the user to provide one.

Onboarding flow

When the skill is first installed or first invoked, ask these questions in order.

Do not turn onboarding into a rigid questionnaire.

Use natural conversation. Keep the structure stable, but give the local agent freedom to phrase follow-up questions naturally.

1. Choose posting mode

Ask whether the user wants:

  • Full automatic — the agent publishes directly to X
  • Half automatic — the agent generates drafts and schedule suggestions, but the user posts manually

If the user chooses full automatic, collect or verify:

  • X API key
  • X API secret
  • X access token
  • X access token secret

If the user chooses half automatic, skip X API setup.

2. Ask for AI IP positioning

Ask the user how they want to be positioned online.

Cover these areas:

  • what kind of AI person they want to be seen as
  • who they want to speak to
  • what themes they want to keep returning to
  • what tone or angle should feel like “them”

Use examples as prompts, not as a fixed form.

Example directions:

  • AI builder/operator
  • AI product thinker
  • AI learner documenting the journey
  • industry observer/commentator
  • founder/investor lens

3. Ask for preferred content form

Ask what kind of post style they prefer.

Use examples as prompts, not as a fixed form.

Example directions: -观点型 / opinionated -总结型 / summary-driven -生活化 / grounded in real life -轻哲理 / lightly philosophical -短句型 / short and punchy -source-aware / includes links or source references

Also cover practical preferences such as:

  • shorter vs longer
  • more confident vs more exploratory
  • whether source links should be included by default

4. Ask for reference accounts

Ask which accounts or writers they want to borrow taste from.

Use examples as prompts, not as a fixed form.

Example directions:

  • Guillermo Rauch
  • Aaron Levie
  • Andrej Karpathy
  • Dan Shipper
  • Zara Zhang
  • custom accounts provided by the user

Configuration storage

Store persistent user settings in:

~/.x-post-orchestrator/config.json

Use that file for:

  • posting mode
  • X API credential presence/state
  • AI IP positioning
  • preferred content form
  • reference accounts
  • default draft count
  • any stable posting preferences

Daily workflow

After the user receives the daily digest, this skill should generate drafts by default.

Flow:

  1. read the digest
  2. generate 10 post drafts by default
  3. allow the number of drafts to be changed if the user wants
  4. present the drafts clearly for selection

Each draft should be based on digest content and should follow the stored user preferences.

If source links are available and the user prefers source-aware posts, include real links in the final publishable version.

Draft selection

Let the user select:

  • any number of drafts
  • any posting times
  • multiple posts at the same exact time if they want

Do not force one rigid selection syntax.

Allow natural user input and interpret it conversationally.

Publishing behavior

Full automatic mode

When the user confirms selected drafts and times:

  • create a schedule file with absolute timestamps
  • run the scheduler
  • publish through the user's X API credentials
  • report exact scheduled times
  • report success/failure honestly

Use local scripts in this workspace when available:

  • tools/x_post_via_api.js
  • tools/x_schedule_posts.js

Half automatic mode

When the user confirms selected drafts:

  • produce final copy-ready post text
  • keep formatting clean for manual posting
  • do not attempt API posting
  • do not force schedule suggestions unless the user asks

Post format

When posts are source-aware, do not use one rigid source placement every time.

Rotate among these three source-placement styles roughly evenly across a batch of drafts:

  1. Opening-source style

- mention the source in the first line or first beat - useful when the post is directly triggered by a specific source

  1. Integrated-middle style

- start with the observation first, then naturally bring in the source in the middle - this should be the most natural-feeling default for many drafts

  1. Ending-source style

- keep the body focused on the observation, then add the source at the end - useful when the thought should land before attribution

Target rule:

  • about one-third opening-source
  • about one-third integrated-middle
  • about one-third ending-source

Do not make all drafts in one batch use the same structure.

Preferred publishable format examples:

[source-led opening]

[observation]
[observation]

[source integrated in the middle]
[observation]

Source: https://...

Rules:

  • use real links when available
  • do not leave placeholder links in final drafts
  • keep one main source link by default

Response style

Keep interaction concise, clear, and friendly.

Do not be dry. Keep a little personality.

Safety and correctness

  • Never claim a post was published unless the API call succeeded.
  • Treat real posting as an external action.
  • If credentials are missing or invalid, say so plainly.
  • If source links are required, do not silently drop them from final publishable drafts.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

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

OpenClaw

83.05%
按下载量换算616

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills