Emin Hadziabdic
Community@ehadziabdic · Sarajevo
Emin Hadziabdic maintains a 192-skill registry spanning offensive security tradecraft, MLOps/LLMOps pipelines, HyperFrames video composition, and UI/UX design systems.
Agent Skills by Emin Hadziabdic
Showing 128 vetted skills indexed across 1 GitHub repositories.
ehadziabdicllm-rag
Build and evaluate retrieval-augmented generation pipelines with vector stores and reranking.
ehadziabdichyperframes
Routes video and animation creation requests to HyperFrames HTML-composition workflows.
ehadziabdicui-ux-pro-max
Searches local UI/UX datasets to generate design systems, palettes, typography, and stack-specific guidelines.
ehadziabdicllm-agent-orchestration
Build and orchestrate tool-using LLM agents with LangGraph, CrewAI, and OpenAI function calling.
ehadziabdicdevops-dr-review
Reviews backup, restore, and disaster-recovery readiness against stated RTO/RPO targets.
ehadziabdichyperframes-cli
Orchestrates the HyperFrames CLI loop for authoring, checking, previewing, and rendering video compositions.
ehadziabdicthink-review-ask
Dispatches a code reviewer subagent to evaluate git diffs against requirements before merging.
ehadziabdicobsidian-defuddle
Extract clean Markdown content from web pages using Defuddle CLI.
ehadziabdicoffensive-windows-mitigations
Analyzes Windows exploit mitigations like ASLR, DEP, CFG, and CET with detection and bypass techniques.
ehadziabdicmodel-observability
Implement ML observability with SHAP/LIME explainability, prediction logging, tracing, and fairness metrics.
ehadziabdictaste-skill-minimalist-skill
Generates minimalist editorial-style web interfaces with warm monochrome palettes and bento-grid layouts.
ehadziabdictaste-skill-brandkit
Generates premium brand-kit overview images with logo systems, palettes, and presentation boards.
ehadziabdicllm-data-preparation
Generate, curate, deduplicate, and format training datasets for LLM fine-tuning and alignment.
ehadziabdicdocument-skills-doc-coauthoring
Guides collaborative document drafting through context gathering, iterative refinement, and reader testing.
ehadziabdictaste-skill-image-to-code-skill
Generates website section design images, analyzes them, then implements matching frontend code.
ehadziabdicui-ux-design
Generates logos, CIP mockups, banners, icons, slides, and social images via Gemini APIs and HTML/CSS.
ehadziabdicllm-evaluation
Evaluate LLM quality with automated metrics, LLM-as-judge, RAGAS, and safety test suites.
ehadziabdicdocument-skills-pdf
Extract, merge, split, create, and fill PDF documents using Python libraries and command-line tools.
ehadziabdicmodel-serving
Deploy and serve ML models as production APIs with FastAPI, BentoML, and Kubernetes.
ehadziabdichyperframes-animation
Compose deterministic GSAP animations for HyperFrames compositions using atomic motion rules and scene blueprints.
ehadziabdichyperframes-registry
Search, install, and wire registry blocks and components into HyperFrames compositions.
ehadziabdicoffensive-parameter-pollution
Tests web applications for HTTP parameter pollution and duplicate-parameter parsing flaws.
ehadziabdicllm-deployment
Deploy and serve large language models with vLLM, TGI, Ollama, and Kubernetes.
ehadziabdicllm-observability
Monitor LLM applications with cost tracking, latency metrics, tracing, and feedback collection.
Frequently Asked Questions About Emin Hadziabdic
FAQPage SchemaWhat tasks can I perform using ehadziabdic's skills?▼
The registry covers authorized red team operations (phishing, Active Directory attacks, Wi-Fi/BLE/Zigbee exploitation, container escape, C2 frameworks, exfiltration), MLOps/LLMOps (fine-tuning, RAG, model serving, drift detection), HyperFrames video and animation production, UI/UX design systems, and Obsidian note management.
Who is the target audience for these skills?▼
Penetration testers and red team operators running authorized engagements, ML engineers building training, serving, and observability pipelines, LLM engineers deploying RAG and agent systems, plus designers and developers producing HyperFrames motion graphics and interface design work.
Are the offensive security skills safe to use?▼
The offensive skills explicitly assume written authorization and a defined scope before execution, targeting authorized red team engagements, penetration tests, and CTF competitions. Many include detection signatures and defender-side visibility guidance to support purple team operations and engagement reporting.
What licensing applies to these skills?▼
The MLOps and LLMOps skill families (model-training, llm-rag, llm-fine-tuning, and related entries) carry Apache-2.0 licenses, while base skills such as base-webapp-testing-basics and base-architecture-blueprint are MIT licensed. Other skills do not declare a license in their frontmatter.
What tools and dependencies do the skills reference?▼
Offensive skills reference operator tooling including Cobalt Strike, Sliver, Metasploit, BloodHound, mimikatz, hashcat, Frida, and Burp Suite. ML skills reference PyTorch, HuggingFace, vLLM, MLflow, Airflow, and Feast. HyperFrames skills use GSAP, Lottie, and Three.js runtimes with local or AWS Lambda and Cloud Run rendering.