AI & ML Agent Skills
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
AI & ML
5,020 skills
ziri22 UX Writer Ia
Expert en rédaction UX (microcopie, textes d'onboarding, messages d'erreur, tone of voice, localisation)
6
ziri22 Agent Copywriter
Copywriter IA — Expert en rédaction persuasive (landing pages, emails, ads, framework AIDA, psychologie de la persuasion).
6
ziri22 Govtech V3 Ia
Expert en technologies gouvernementales avancées (e-administration, digital identity, open data, civic tech, DZ context)
6
ziri22 Agent Resto Tech
Resto tech — POS, menu digital, livraison, Uber Eats DZ, facturation restaurants
6
ziri22 Agent Zero Trust
Expert en architecture zero trust (identity-based, micro-segmentation, ZTNA, BeyondCorp)
6
ziri22 Proptech V3 Ia
Expert en technologies immobilières avancées (virtual tours, AVM, mortgage calculators, smart contracts, DZ context)
6
ziri22 Agent Data Quality
Data Quality Specialist IA — Expert en qualité des données (profiling, cleaning, déduplication, validation de schéma, Great Expectations)
6
ziri22 Agent Event Driven
Expert en architecture événementielle (Kafka, RabbitMQ, event sourcing, CQRS, saga patterns)
6
ziri22 Agent Hr Recruiter
HR & Recruiter IA — Expert en recrutement RH (job descriptions, screening, ATS, onboarding, culture fit)
6
ziri22 Metaverse V3 Ia
Expert en metaverse avancé (virtual worlds, digital twins, spatial computing, XR, DZ market)
6
ziri22 Agent Scrum Master
Scrum master — ceremonies, facilitation, impediments, retrospectives, metrics
6
ziri22 Video Editor Ia
Expert en montage vidéo (Premiere, DaVinci, CapCut, color grading, transitions, formats d'export)
6
ziri22 Agent Agent Testing
Expert en tests d'agents IA (tests unitaires, intégration, régression, guardrails, red teaming agents)
6
ziri22 Agent Dao Architect
DAO Architect IA — Expert en architecture DAO (governance, proposals, voting mechanisms, treasury management)
6
tianhao909 Faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
1 · bundle
tianhao909 Crewai Multi Agent
Orchestrates teams of specialized AI agents with role-based collaboration, memory, and sequential or hierarchical execution for complex multi-step tasks.
1 · bundle
tianhao909 Hqq Quantization
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
1 · bundle
tianhao909 Gptq
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
1 · bundle
tianhao909 Whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
1 · bundle
tianhao909 Slime Rl Training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
1 · bundle
tianhao909 Serving Llms Vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
1 · bundle
tianhao909 Mamba Architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
1 · bundle
tianhao909 Implementing Llms Litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
1 · bundle
tianhao909 Nanogpt
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
1 · bundle
tianhao909 Guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
1 · bundle
tianhao909 Optimizing Attention Flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
1 · bundle
tianhao909 Grpo Rl Training
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
1 · bundle
tianhao909 Nemo Guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
1
tianhao909 Model Pruning
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
1 · bundle
tianhao909 Pyvene Interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
1 · bundle
tianhao909 Speculative Decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
1 · bundle
qcmuu Faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
0 · bundle
qcmuu Clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
0 · bundle
qcmuu Tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
0 · bundle
qcmuu Whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
0 · bundle
qcmuu Slime Rl Training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
0 · bundle
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include implementing-llms-litgpt, nanogpt, speculative-decoding. Rankings shift as installs change; sort this page by "Most downloaded" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds add <owner>/<name>, or copy the file into your agent's skills directory.