Skip to content
View Evgeniy-Mikhailove's full-sized avatar
7 followers · 50 following

Block or report Evgeniy-Mikhailove

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Evgeniy-Mikhailove/README.md

Typing SVG

Hey, I'm Evgeniy

I build AI agent systems, automation pipelines, and tools that make AI actually useful in day-to-day work - not just chatbots, but real operational infrastructure.

Background in B2B sales. Now applying that mindset to AI: if it doesn't save time or make money, it doesn't ship.

What I work on

Prompt Engineering & AI Agents

  • Multi-model routing across Anthropic, OpenAI, Google (6 cost tiers)
  • Multi-agent orchestration with parallel wave execution and review gates
  • Production prompt systems: CoT, ReAct, RAG, Prompt Chaining, ToT
  • Agent development framework with triggering patterns and system prompt design
  • Skill lifecycle management (800+ skills, auto-routing, usage tracking, evolution)
  • Self-correcting quality loops with rubric scoring and convergence detection
  • AI text humanization (20-pattern checklist for removing machine traces)

Sales & Marketing Automation

  • AI-powered sales assistants and intake pipelines
  • CRM automation, lead scoring, follow-up sequences
  • Content production pipelines (reels, carousels, TTS voiceover)

No-Code / Low-Code Integrations

  • n8n workflow automation (Telegram bots, webhooks, API chains)
  • Google Workspace integrations (Calendar, Drive, Sheets)
  • End-to-end deployment on VPS and Railway

Stack

Python Claude OpenAI Gemini n8n VS Code Supabase Telegram FastAPI

Prompt Engineering & AI Agent Systems

Project What it does
multi-model-router Route tasks to the optimal model across 3 providers and 6 cost tiers Stars
prompt-techniques-library Decision matrix for 6 prompting techniques: CoT, ReAct, Chaining, ToT, RAG Stars
multi-agent-orchestration Parallel AI agent execution: Three-Tier Dispatch, Wave Execution, Review Gates Stars
agent-development-framework Templates for building AI agents: file format, triggering patterns, system prompts Stars
skill-lifecycle Manage 800+ AI skills - auto-routing, usage tracking, evolution, 6-tier routing Stars
rlm-claude-code-os Claude Code OS - skill router, RLM harness, 20 core skills, one-command install Stars

AI Workflow & Quality Tools

Project What it does
workflow-patterns 6 strategies for complex AI tasks: Fanout, Adversarial, Loop, Classify, Generate-Filter, Tournament Stars
loop-protocol Self-correcting iteration loops. Score against rubric, fix weaknesses, repeat until convergence Stars
ai-text-humanizer 20 patterns that make AI text sound machine-generated. Checklist for removing AI traces Stars

Sales & Automation

Project What it does
incoming-intel 7-step pipeline: process raw materials into working skills with adversarial critic Stars
zerocoder-sales-intake AI sales intake - qualification, objection handling, CRM integration Stars
exosales-assistant AI sales assistant for B2B outreach and follow-up automation Stars

Connect

Telegram Sponsor

Stats

Trophies

Top Languages

Activity Graph

MY PROGRESS 💪😎

Snake Animation

Building tools that work, not tools that demo well.

Pinned Loading

  1. skill-lifecycle skill-lifecycle Public

    Manage hundreds of Claude Code skills without losing track. Auto-categorize, route by task, track usage, and let skills learn from session experience via mandatory adaptation pattern.

    Python

  2. incoming-intel incoming-intel Public

    Process raw materials from external sources into Claude Code skills. 7-step pipeline: scan, extract, context check, evaluate, adversarial critic, report, integrate.

  3. multi-model-router multi-model-router Public

    Route AI tasks to the optimal model across 3 providers and 7 cost tiers. Haiku -> Gemini -> GPT -> Sonnet 4.6 -> Sonnet 5 -> Opus -> Fable.

    Python 2

  4. prompt-techniques-library prompt-techniques-library Public

    Decision matrix for choosing the right prompting technique. 6 production patterns: CoT, ReAct, Chaining, ToT, RAG, Self-Consistency.

  5. agent-development-framework agent-development-framework Public

    Templates and patterns for building AI agents. File format spec, triggering patterns, system prompt design, validation checklist.

  6. multi-agent-orchestration multi-agent-orchestration Public

    6 production patterns for parallel AI agent execution. Three-Tier Dispatch, Wave Execution, Git Worktree Isolation, Cross-Model Routing, Review Gates.