algorithm-cultivation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Algorithm Cultivation & Thought Leadership

算法培养与意见领袖打造

Train your X/Twitter algorithm for a specific niche. Three approaches:

Browser script -- paste into DevTools console for manual sessions
CLI + Persona Engine -- create personas and run from the command line
24/7 Algorithm Builder -- headless Puppeteer + LLM running continuously

针对特定细分领域训练你的X/Twitter账号算法。提供三种实现方式：

浏览器脚本 —— 粘贴到DevTools控制台进行手动操作会话
CLI + Persona Engine —— 创建角色并通过命令行运行
7×24小时算法构建工具 —— 无头模式Puppeteer + 持续运行的LLM

Quick Reference

快速参考

Goal	Solution
Create a persona (CLI)	`xactions persona create`
Run 24/7 with LLM (CLI)	`xactions persona run <id>`
Check persona status	`xactions persona status <id>`
Browser console (with core.js)	`src/automation/algorithmBuilder.js`
Browser console (standalone)	`scripts/thoughtLeaderCultivator.js`
Browser console (algorithm trainer)	`src/automation/algorithmTrainer.js`
Persona Engine (Node.js module)	`src/personaEngine.js`
Algorithm Builder (Node.js module)	`src/algorithmBuilder.js`

目标	解决方案
创建角色（CLI）	`xactions persona create`
结合LLM实现7×24小时运行（CLI）	`xactions persona run <id>`
查看角色状态	`xactions persona status <id>`
浏览器控制台（依赖core.js）	`src/automation/algorithmBuilder.js`
浏览器控制台（独立版）	`scripts/thoughtLeaderCultivator.js`
浏览器控制台（算法训练器）	`src/automation/algorithmTrainer.js`
Persona Engine（Node.js模块）	`src/personaEngine.js`
算法构建工具（Node.js模块）	`src/algorithmBuilder.js`

Core Concepts

核心概念

Persona -- identity config: niche, activity pattern, engagement strategy, topics
Session -- one period of activity (search, browse, engage, post)
Strategy -- engagement limits (aggressive/moderate/conservative/thoughtleader)
Activity pattern -- human-like schedule (night-owl/early-bird/nine-to-five/always-on/weekend-warrior)

Persona（角色） —— 身份配置：细分领域、活动模式、互动策略、关注话题
会话 —— 一段活动周期（搜索、浏览、互动、发帖）
策略 —— 互动限制（激进/中等/保守/意见领袖模式）
活动模式 —— 类人类日程安排（夜猫子/早起型/朝九晚五/全天候/周末活跃）

Algorithm Builder --

src/algorithmBuilder.js

算法构建工具 --

src/algorithmBuilder.js

24/7 headless automation: Puppeteer + stealth + OpenRouter LLM.

import { startAlgorithmBuilder } from './algorithmBuilder.js';

await startAlgorithmBuilder({
  personaId: 'persona_1234',
  authToken: 'your_auth_token',
  headless: true,
  dryRun: false,
  maxSessions: 0, // 0 = infinite
});

Requires

OPENROUTER_API_KEY

env var for LLM-generated comments and posts.

7×24小时无头自动化：Puppeteer + stealth + OpenRouter LLM.

import { startAlgorithmBuilder } from './algorithmBuilder.js';

await startAlgorithmBuilder({
  personaId: 'persona_1234',
  authToken: 'your_auth_token',
  headless: true,
  dryRun: false,
  maxSessions: 0, // 0 = 无限循环
});

生成LLM驱动的评论和发帖需要配置

OPENROUTER_API_KEY

环境变量。

Algorithm Trainer --

src/automation/algorithmTrainer.js

算法训练器 --

src/automation/algorithmTrainer.js

Browser console script for manual training sessions. Requires

src/automation/core.js

pasted first.

用于手动训练会话的浏览器控制台脚本，需先粘贴

src/automation/core.js

。

Training Phases (cycles through all 8)

训练阶段（循环执行全部8个阶段）

Search top tweets for niche keywords
Search latest tweets for niche keywords
Follow people from search results
Engage with home feed (like/reply)
Visit influencer profiles
Browse random profiles in niche
Explore page browsing
Idle dwell time (human-like pauses)

搜索细分领域关键词的热门推文
搜索细分领域关键词的最新推文
关注搜索结果中的用户
与首页信息流互动（点赞/回复）
访问领域内意见领袖的主页
浏览细分领域内的随机主页
探索页面浏览
闲置停留时间（类人类停顿）

Controls

控制命令

```
stopTrainer()
```
-- Stop training
```
trainerStatus()
```
-- Current phase, actions taken, rate limits
```
trainerReset()
```
-- Reset counters

```
stopTrainer()
```
—— 停止训练
```
trainerStatus()
```
—— 查看当前阶段、已执行操作、速率限制
```
trainerReset()
```
—— 重置计数器

Intensity Presets

强度预设

Preset	Actions/hour	Daily cap
chill	10-15	100
normal	20-30	300
active	40-60	500

预设	每小时操作数	每日上限
佛系	10-15	100
常规	20-30	300
活跃	40-60	500

Strategy Guide

策略指南

Fresh account (week 1-2)

新账号（第1-2周）

Create a persona with
```
xactions persona create
```
or configure algorithmTrainer manually
Use conservative/chill intensity -- X flags aggressive new accounts
Focus on phases 1-2 (search) and 7 (explore) to signal interests
Follow 5-10 niche accounts per day manually
Like 20-30 niche tweets per day

通过
```
xactions persona create
```
创建角色，或手动配置algorithmTrainer
使用保守/佛系强度 —— X平台会标记行为激进的新账号
重点执行阶段1-2（搜索）和7（探索），以此向平台传递兴趣信号
每天手动关注5-10个细分领域账号
每天点赞20-30条细分领域推文

Established account pivoting niches

转型细分领域的成熟账号

Aggressively engage with new niche content for 1-2 weeks

Use

src/automation/algorithmTrainer.js

active

intensity

Unfollow accounts from the old niche gradually with
```
src/automation/smartUnfollow.js
```
The algorithm typically adjusts within 3-7 days of consistent signals

连续1-2周积极互动新领域内容
将
```
src/automation/algorithmTrainer.js
```
设为「活跃」强度运行
通过
```
src/automation/smartUnfollow.js
```
逐步取消关注旧领域账号
持续传递信号后，平台算法通常会在3-7天内完成调整

Running 24/7 with LLM

结合LLM实现7×24小时运行

Set
```
OPENROUTER_API_KEY
```
for AI-generated replies
```
xactions persona create
```
-- configure niche, strategy, schedule
```
xactions persona run <id>
```
-- starts headless Puppeteer session
Monitor:
```
xactions persona status <id>
```
Cost estimate: ~$0.50-2.00/day depending on model and activity level

配置
```
OPENROUTER_API_KEY
```
以启用AI生成回复
执行
```
xactions persona create
```
—— 配置细分领域、策略、日程
执行
```
xactions persona run <id>
```
—— 启动无头Puppeteer会话
监控状态：
```
xactions persona status <id>
```
成本估算：每天约0.5-2.0美元，具体取决于模型和活动强度

Environment Variables

环境变量

Variable	Purpose
`OPENROUTER_API_KEY`	Required for LLM-generated comments and posts
`XACTIONS_SESSION_COOKIE`	X auth token (alternative to `--token` flag)

变量	用途
`OPENROUTER_API_KEY`	生成LLM驱动的评论和发帖所需
`XACTIONS_SESSION_COOKIE`	X平台认证令牌（替代 `--token` 参数）

Detailed References

详细参考资料

Load these on demand for deeper context:

Persona Engine details --

skills/algorithm-cultivation/references/persona-engine.md

Browser scripts --

skills/algorithm-cultivation/references/browser-scripts.md

Algorithm internals --

skills/algorithm-cultivation/references/algorithm-internals.md

Research: algorithm internals --
```
docs/research/algorithm-cultivation.md
```

Research: LLM architecture --

docs/research/llm-powered-thought-leader.md

按需加载以下内容获取更深入的信息：

Persona Engine详情 ——

skills/algorithm-cultivation/references/persona-engine.md

浏览器脚本 ——

skills/algorithm-cultivation/references/browser-scripts.md

算法内部机制 ——

skills/algorithm-cultivation/references/algorithm-internals.md

研究：算法内部机制 ——
```
docs/research/algorithm-cultivation.md
```

研究：LLM架构 ——

docs/research/llm-powered-thought-leader.md

Notes

注意事项

Browser scripts require navigating to x.com first

algorithmBuilder.js

and

algorithmTrainer.js

require pasting

src/automation/core.js

first

```
thoughtLeaderCultivator.js
```
is standalone (no dependencies)
Default engagement strategy: 1-3s delays between actions
Fresh accounts should start with conservative strategy for 1-2 weeks

浏览器脚本需先导航至x.com

algorithmBuilder.js

和

algorithmTrainer.js

需先粘贴

src/automation/core.js

```
thoughtLeaderCultivator.js
```
为独立脚本（无依赖）
默认互动策略：操作间隔1-3秒延迟
新账号前1-2周应采用保守策略