Back to Details

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:
  1. Browser script -- paste into DevTools console for manual sessions
  2. CLI + Persona Engine -- create personas and run from the command line
  3. 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：
  1. 浏览器脚本 —— 粘贴到DevTools控制台进行手动操作会话
  2. CLI + Persona Engine —— 创建角色并通过命令行运行
  3. 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

GoalSolution
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.
js
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.
js
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）

  1. Search top tweets for niche keywords
  2. Search latest tweets for niche keywords
  3. Follow people from search results
  4. Engage with home feed (like/reply)
  5. Visit influencer profiles
  6. Browse random profiles in niche
  7. Explore page browsing
  8. Idle dwell time (human-like pauses)
  1. 搜索细分领域关键词的热门推文
  2. 搜索细分领域关键词的最新推文
  3. 关注搜索结果中的用户
  4. 与首页信息流互动（点赞/回复）
  5. 访问领域内意见领袖的主页
  6. 浏览细分领域内的随机主页
  7. 探索页面浏览
  8. 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

PresetActions/hourDaily cap
chill10-15100
normal20-30300
active40-60500
预设每小时操作数每日上限
佛系10-15100
常规20-30300
活跃40-60500

Strategy Guide

策略指南

Fresh account (week 1-2)

新账号（第1-2周）

  1. Create a persona with 
    xactions persona create
    or configure algorithmTrainer manually
  2. Use conservative/chill intensity -- X flags aggressive new accounts
  3. Focus on phases 1-2 (search) and 7 (explore) to signal interests
  4. Follow 5-10 niche accounts per day manually
  5. Like 20-30 niche tweets per day
  1. 通过
    xactions persona create
    创建角色，或手动配置algorithmTrainer
  2. 使用保守/佛系强度 —— X平台会标记行为激进的新账号
  3. 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
  4. 每天手动关注5-10个细分领域账号
  5. 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

  1. Aggressively engage with new niche content for 1-2 weeks
  2. Use 
    src/automation/algorithmTrainer.js
    on 
    active
    intensity
  3. Unfollow accounts from the old niche gradually with 
    src/automation/smartUnfollow.js
  4. The algorithm typically adjusts within 3-7 days of consistent signals
  1. 连续1-2周积极互动新领域内容
  2. 将
    src/automation/algorithmTrainer.js
    设为「活跃」强度运行
  3. 通过
    src/automation/smartUnfollow.js
    逐步取消关注旧领域账号
  4. 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

  1. Set 
    OPENROUTER_API_KEY
    for AI-generated replies
  2. xactions persona create
    -- configure niche, strategy, schedule
  3. xactions persona run <id>
    -- starts headless Puppeteer session
  4. Monitor: 
    xactions persona status <id>
  5. Cost estimate: ~$0.50-2.00/day depending on model and activity level
  1. 配置
    OPENROUTER_API_KEY
    以启用AI生成回复
  2. 执行
    xactions persona create
    —— 配置细分领域、策略、日程
  3. 执行
    xactions persona run <id>
    —— 启动无头Puppeteer会话
  4. 监控状态：
    xactions persona status <id>
  5. 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

VariablePurpose
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