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
In this repository60 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- python/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- python/CLAUDE.mdCLAUDE.md
- xspace-agents/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms-full.txtllms.txt
- llms.txtllms.txt
- python/llms-full.txtllms.txt
- python/llms.txtllms.txt
- a2a-multi-agentSkill
- account-backupSkill
- account-toolsSkill
- analytics-insightsSkill
- articles-longformSkill
- billing-managementSkill
- blocking-muting-managementSkill
- bookmarks-managementSkill
- business-adsSkill
- community-health-monitoringSkill
- community-managementSkill
- community-notesSkill
- competitor-intelligenceSkill
- content-cleanupSkill
- content-postingSkill
- content-repurposingSkill
- creator-monetizationSkill
- crm-managementSkill
- delegate-accessSkill
- direct-messagesSkill
- discovery-exploreSkill
- engagement-interactionSkill
- follower-monitoringSkill
- graph-analysisSkill
- grok-aiSkill
- growth-automationSkill
- lead-generationSkill
- lists-managementSkill
- media-studioSkill
- notifications-managementSkill
- post-editingSkill
- premium-subscriptionsSkill
- profile-managementSkill
- reputation-auditSkill
- saved-searchesSkill
- settings-privacySkill
- spaces-liveSkill
- teams-managementSkill
- timeline-viewingSkill
- topic-managementSkill
- twitter-scrapingSkill
- unfollow-managementSkill
- video-downloadingSkill
- viral-thread-generationSkill
- webhooksSkill
- x402-paymentsSkill
- xactions-cliSkill
- xactions-mcp-serverSkill
- x-pro-managementSkill
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
- Distinctive: line 61
Search top tweets for niche keywords
- Distinctive: line 62
Search latest tweets for niche keywords
- Distinctive: line 63
Follow people from search results
- Very specific: line 85
Create a persona with xactions persona create or configure algorithmTrainer manually
- Distinctive: line 86
Use conservative/chill intensity -- X flags aggressive new accounts
- Distinctive: line 88
Follow 5-10 niche accounts per day manually
- Very specific: line 93
Use src/automation/algorithmTrainer.js on active intensity
- Distinctive: line 125
Default engagement strategy: 1-3s delays between actions
≈ “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.
Files
Algorithm Cultivation & Thought Leadership
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
Quick Reference
| 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 |
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)
- 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)
Controls
stopTrainer()-- Stop trainingtrainerStatus()-- Current phase, actions taken, rate limitstrainerReset()-- Reset counters
Intensity Presets
| Preset | Actions/hour | Daily cap |
| chill | 10-15 | 100 |
| normal | 20-30 | 300 |
| active | 40-60 | 500 |
Strategy Guide
Fresh account (week 1-2)
- Create a persona with
xactions persona createor 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
Established account pivoting niches
- Aggressively engage with new niche content for 1-2 weeks
- Use
src/automation/algorithmTrainer.jsonactiveintensity - Unfollow accounts from the old niche gradually with
src/automation/smartUnfollow.js - The algorithm typically adjusts within 3-7 days of consistent signals
Running 24/7 with LLM
- Set
OPENROUTER_API_KEYfor AI-generated replies xactions persona create-- configure niche, strategy, schedulexactions 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
Environment Variables
| Variable | Purpose |
OPENROUTER_API_KEY | Required for LLM-generated comments and posts |
XACTIONS_SESSION_COOKIE | X 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.jsandalgorithmTrainer.jsrequire pastingsrc/automation/core.jsfirstthoughtLeaderCultivator.jsis standalone (no dependencies)- Default engagement strategy: 1-3s delays between actions
- Fresh accounts should start with conservative strategy for 1-2 weeks
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
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.

