agentleFS
nirholasnirholas/XActions/skills/algorithm-cultivation/SKILL.md

algorithm-cultivation

Skill648 starsChanged 9 months agoApache-2.0View on GitHub

Trains an X/Twitter account's algorithmic feed to surface niche-relevant content and positions the account as a thought leader. Browser scripts for manual operation, Persona Engine for identity management, and 24/7 Algorithm Builder with LLM-powered engagement via Puppeteer. Use when a user wants to build their algorithm, cultivate their feed for a niche, grow a fresh account, become a thought leader, or run automated engagement with AI-generated content.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search top tweets for niche keywords

    line 61
  2. Distinctive:

    Search latest tweets for niche keywords

    line 62
  3. Distinctive:

    Follow people from search results

    line 63
  4. Very specific:

    Create a persona with xactions persona create or configure algorithmTrainer manually

    line 85
  5. Distinctive:

    Use conservative/chill intensity -- X flags aggressive new accounts

    line 86
  6. Distinctive:

    Follow 5-10 niche accounts per day manually

    line 88
  7. Very specific:

    Use src/automation/algorithmTrainer.js on active intensity

    line 93
  8. Distinctive:

    Default engagement strategy: 1-3s delays between actions

    line 125

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Algorithm Cultivation & Thought Leadership

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

Quick Reference

GoalSolution
Create a persona (CLI)xactions persona create
Run 24/7 with LLM (CLI)xactions persona run <id>
Check persona statusxactions 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

Core Concepts

  • 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)

Algorithm Builder -- 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.

Algorithm Trainer -- src/automation/algorithmTrainer.js

Browser console script for manual training sessions. Requires src/automation/core.js pasted first.

Training Phases (cycles through all 8)

  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)

Controls

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

Intensity Presets

PresetActions/hourDaily cap
chill10-15100
normal20-30300
active40-60500

Strategy Guide

Fresh account (week 1-2)

  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

Established account pivoting niches

  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

Running 24/7 with LLM

  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

Environment Variables

VariablePurpose
OPENROUTER_API_KEYRequired for LLM-generated comments and posts
XACTIONS_SESSION_COOKIEX auth token (alternative to --token flag)

Detailed References

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

Notes

  • 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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.