Azaan Ali Raza
Community@azaanaliraza
Driven by a passion for coding, I'm eager to explore the possibilities of AI and machine learning. With a foundational understanding of Java, JavaScript, Python
Agent Skills by Azaan Ali Raza
Showing 126 vetted skills indexed across 1 GitHub repositories.
azaanalirazaparallel-cli
Runs web search, extraction, deep research, enrichment, and monitoring via the Parallel CLI.
azaanalirazagitnexus-explorer
Index codebases into knowledge graphs and serve an interactive web UI via Cloudflare tunnel.
azaanalirazaqmd
Search local markdown notes and documents using hybrid BM25, vector, and LLM reranking retrieval.
azaanalirazadrug-discovery
Queries ChEMBL, PubChem, OpenFDA, and OpenTargets APIs to analyze compounds and drug-likeness properties.
azaanalirazaduckduckgo-search
Searches the web via DuckDuckGo for text, news, images, and videos without an API key.
azaanalirazascrapling
Scrapes web pages using HTTP fetching, stealth browser automation, and spider crawling via Scrapling.
azaanalirazabioinformatics
Indexes and fetches 400+ bioinformatics skills covering genomics, transcriptomics, and variant calling pipelines.
azaanalirazadomain-intel
Performs passive domain reconnaissance including subdomain discovery, SSL inspection, WHOIS lookups, and DNS queries.
azaanalirazadocker-management
Manage Docker containers, images, volumes, networks, and Compose stacks via CLI commands.
azaanalirazainference-sh-cli
Run 150+ cloud AI apps for image, video, audio, and search via the infsh CLI.
azaanalirazasherlock
Searches 400+ social networks for accounts matching a given username using the Sherlock CLI.
azaanalirazaoss-forensics
Investigate GitHub repositories for supply chain compromise using multi-source forensic evidence collection.
azaanaliraza1password
Configure 1Password CLI and read or inject secrets into commands and templates.
azaanalirazafitness-nutrition
Search exercises and food nutrition data, then compute BMI, TDEE, one-rep max, and macro splits.
azaanalirazaneuroskill-bci
Reads real-time EEG and biometric metrics from a NeuroSkill BCI session to inform responses.
azaanalirazanemo-curator
Curate and deduplicate LLM training datasets on GPUs with NeMo Curator.
azaanalirazahuggingface-accelerate
Adds distributed training support to PyTorch scripts with a unified API for DDP, DeepSpeed, FSDP, and Megatron.
azaanalirazachroma
Store embeddings and metadata in Chroma for vector search and RAG applications.
azaanalirazasimpo-training
Train LLMs with reference-free SimPO preference optimization using HuggingFace alignment-handbook configs.
azaanalirazaslime-rl-training
Guides LLM post-training with reinforcement learning using Megatron-LM and SGLang.
azaanalirazaguidance
Control LLM output with regex constraints, grammars, and token healing for structured generation.
azaanalirazalambda-labs-gpu-cloud
Provision and manage Lambda Labs GPU cloud instances for ML training and inference.
azaanalirazahuggingface-tokenizers
Train and apply fast BPE, WordPiece, and Unigram tokenizers for NLP pipelines.
azaanalirazapinecone
Manage vector indexes, upserts, and hybrid queries with the Pinecone API.
Frequently Asked Questions About Azaan Ali Raza
FAQPage SchemaWhat tasks can I accomplish with Azaan Ali Raza's skill registry?▼
The registry covers LLM fine-tuning (TRL, Axolotl, Unsloth, PEFT), distributed training (FSDP, torchtitan, Accelerate), inference serving (vLLM, TensorRT-LLM, llama.cpp), vector databases (Qdrant, Pinecone, FAISS, Chroma), GitHub PR/issue management, OSINT username search, Docker management, PDF/OCR extraction, and creative generation (Stable Diffusion, Manim, p5.js, Blender).
Who is the target audience for these skills?▼
ML engineers fine-tuning and serving language models, data scientists curating training corpora with NeMo Curator, security researchers running OSINT and repository forensics, DevOps engineers managing Docker stacks, and creative coders producing diagrams, animations, and generative art through the Hermes Agent runtime.
How do I install and run these skills in practice?▼
Skills load inside the Hermes Agent environment and declare their own prerequisites. Most require python3 plus pip dependencies listed in frontmatter (e.g., torch, transformers, vllm); some need CLI binaries like sherlock, pygount, or himalaya, and a few require API tokens such as LINEAR_API_KEY, NOTION_API_KEY, or SIYUAN_TOKEN.
Are these skills open source and free to use?▼
Yes. Nearly all 128 skills carry the MIT license, including the training, inference, search, and security skills. The sole exception is the powerpoint skill, which is proprietary with terms in its LICENSE.txt file. External services like Lambda Labs, Modal, or 1Password may require their own paid accounts.
What prerequisites and dependencies do the ML skills require?▼
Training skills typically need torch>=2.0, transformers, datasets, peft, and accelerate; GPU-heavy ones add deepspeed, flash-attn, or RAPIDS/cudf. Serving skills require vllm or tensorrt-llm on NVIDIA GPUs, while llama-cpp runs on CPU and Apple Silicon. Vector search skills need their respective clients such as qdrant-client or pinecone-client.