Skip to content
View Fascinax's full-sized avatar
3 followers · 5 following

Achievements

Achievement: YOLOAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: Pull Shark

Block or report Fascinax

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
Fascinax/README.md

Animated banner

Hi, I'm Fascinax

Software engineer building AI developer tools, agent workflows, and reliable LLM products

Most of my work sits at the intersection of AI and software engineering : code audits, reliable retrieval, test generation, failure recovery, and LLM products that can point to evidence instead of bluffing.

🚀 Selected Projects

Inspectra

Multi-agent code audit system : MCP + GitHub Copilot Custom Agents

Coordinates 12 specialized audit agents (security, architecture, tests, perf, docs…) and ships as an npm package with setups for Copilot, Claude Code, and Codex. 650+ passing tests.

Veridicta (private)

RAG assistant for explainable legal answers : BM25 + FAISS + evaluation loop

Hybrid retrieval with 100% citation faithfulness on a gold-standard benchmark. Built for traceable, production-minded output.

clean-code-skills

Agent skills to enforce clean code : 7 languages, 50+ rules

Encodes Robert Martin's Clean Code catalog for AI coding agents in Python, Java, TypeScript, JavaScript, Go, Rust, and C#. Keeps generated code maintainable, not just functional.

noesis-zc (private)

Full-stack knowledge mapping : AI quizzes + cognitive graph

Interactive D3.js concept graph, AI-generated quizzes with competency radar, Supabase auth and persistence, Playwright E2E coverage.

Enterprise Work


E2E Test Generation
AI-generated Playwright specs from live web exploration, with Page Object Model and auto-correction
API Test Generation
QuarkusTest + Karate suites generated from OpenAPI specs via LLM pipeline
Self-Healing Pipelines
Failure classification, LLM patch generation, syntax validation & automatic MR delivery
Dev Tooling & CI/CD
GitLab CI templates, developer tools, and automation for distributed Java microservices

🛠️ Tech

GitHub Stats

GitHub stats Top languages

AI tooling · agent workflows · RAG evaluation · test automation

Pinned Loading

  1. Inspectra Inspectra Public

    Hybrid code audit system powered by deterministic MCP tools and conditional hotspot exploration. Audits 12 domains: security, tests, architecture, conventions, performance, documentation, tech-debt…

    TypeScript 1

  2. clean-code-skills clean-code-skills Public

    Forked from ertugrul-dmr/clean-code-skills

    Teach your AI agents to write and refactor clean, idiomatic code in multiple languages by applying Robert C. Martin’s Clean Code principles through reusable Agent Skills.

    Python

  3. jobsfr jobsfr Public

    Forked from mariodian/jobs

    Analyzing how susceptible every occupation in the FR economy is to AI and automation, using data from France Travail

    Python

  4. packmind packmind Public

    Forked from PackmindHub/packmind

    Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance.

    TypeScript