Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
9,019 results · page 145 of 301
- View details
quark-torch-llm-ptq-workflowSkillAI & models
Torch LLM PTQ workflow for AMD Quark — from model selection to quantized output. Use when the user wants a complete PTQ pipeline: model inspection, quantization planning, script generation, and optional execution. Stops at the quantized output. Trigger for "quantize my model", "run PTQ", "run model
Ready to connect★ 166
- View details
quark-torch-model-intakeSkillAI & models
Inspect a HuggingFace transformers / safetensors model and prepare metadata for Quark Torch PTQ planning. Use for model path validation, architecture detection, quantization target discovery, layer counting, risk assessment, or transformers compatibility checks. Trigger for "analyze my model", "chec
Ready to connect★ 166
- View details
quark-torch-ptqSkillAI & models
Torch LLM PTQ workflow for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input). Use when the user wants a complete PTQ pipeline: model inspection, quantization planning, script generation, and optional execution. Stops at the quantized output. Trigger for "quantize my model
Ready to connect★ 166
- View details
quark-torch-quant-planSkillAI & models
Build a Quark Torch LLM PTQ quantization plan from model analysis and user intent. Use when the user needs quantization scheme recommendations, exclusion lists, algorithm selection, KV cache decisions, per-layer overrides, or a draft quant_plan. Trigger for "quantize with FP8", "what scheme should I
Ready to connect★ 166
- View details
quark-torch-skill-syncSkillAI & models
Detect upstream Quark changes that affect the skill system and classify required updates. Use when Quark docs, CLI flags, quantization templates, model support, or source behavior may have drifted from the skill contracts. Trigger for "check if skills are up to date", "sync skills with Quark", "has
Ready to connect★ 166
- View details
creating-superfans-hodakSkillAI & models
Apply Brittany Hodak's SUPER Model for customer loyalty, referrals, word of mouth, personalization, service recovery, and scalable customer experience.
Ready to connect★ 164
- View details
munger-mental-models-worldly-wisdomSkillAI & models
Apply Charlie Munger mental models to investments, decisions, and bias diagnosis. Trigger on Munger checklist or spot biases.
Ready to connect★ 164
- View details
query-loop-implementationSkillAI & models
Implement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, tool_result feedback, max-turn exits, or Claude Code-like
Ready to connect★ 164
- View details
drug-mmpbsa-gbsaSkillAI & models
Compute single-trajectory MM-GBSA and / or MM-PBSA binding free energy estimates from a protein-ligand MD trajectory. Two backends: a fast OpenMM GBn2 path (no extra dependencies) and an AmberTools MMPBSA.py path that supports both GB (multiple igb models) and Poisson-Boltzmann PB on the same trajec
Ready to connect★ 164
- View details
mat-calphad-property-diagramSkillAI & models
Calculate temperature-dependent thermodynamic properties like Equilibrium Phase Fractions for a specific alloy composition using CALPHAD models.
Ready to connect★ 164
- View details
mat-grand-canonical-mcSkillAI & models
Run Grand Canonical Monte Carlo (GCMC) simulations with cluster expansion models to map composition-temperature phase diagrams via chemical potential sweeps.
Ready to connect★ 164
- View details
ml-committee-uncertaintySkillAI & models
Quantify prediction uncertainty of MACE MLIPs using committee (ensemble) models; flag high-uncertainty structures for DFT verification.
Ready to connect★ 164
- View details
ml-foundation-potentialsSkillAI & models
Guide for selecting the most appropriate foundation MLIP model based on simulation requirements.
Ready to connect★ 164
- View details
ml-generative-aditSkillAI & models
Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.
Ready to connect★ 164
- View details
ml-generative-mattergenSkillAI & models
Generate inorganic material structures using MatterGen, a diffusion-based generative model.
Ready to connect★ 164
- View details
ml-mlip-nvalchemiSkillAI & models
GPU-accelerated batched inference for MACE, MatGL (TensorNet/M3GNet/CHGNet), and FairChem MLIPs using NValchemi, enabling parallel static, relax, and MD workflows across multiple structures simultaneously.
Ready to connect★ 164
- View details
ml-mlip-speedSkillAI & models
Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).
Ready to connect★ 164
- View details
ml-property-predict-scdSkillAI & models
Train a model to predict custom properties of molecules or periodic materials using pretrained SelfConditionedDenoisingAtoms (SCD) foundation models.
Ready to connect★ 164
- View details
ai-product-managerSkillAI & models
Elite AI Product Manager skill with expertise in AI product strategy, LLM product development, ML feature prioritization, AI ethics and fairness. Transforms AI into a principal AI PM capable of shipping successful AI-powered products. Use when: ai-product, product-management, llm-products, ai-strate
Ready to connect★ 163
- View details
ai-safety-researcherSkillAI & models
Expert AI Safety Researcher with deep specialization in LLM alignment, Constitutional AI, RLHF/DPO, red-teaming, interpretability, and safety evaluation frameworks
Ready to connect★ 163
- View details
llm-research-scientistSkillAI & models
Expert-level LLM Research Scientist with deep knowledge of transformer architectures, RLHF, DPO, Constitutional AI, alignment research, evaluation benchmarks, and scaling laws
Ready to connect★ 163
- View details
llm-training-engineerSkillAI & models
Expert LLM Training Engineer with 6+ years of experience in large-scale model pre-training, fine-tuning, alignment, and efficient inference. Use when building, training, or optimizing large language models. Triggers: "llm training", "pre-training", "fine-tuning", "RLHF", "loss spike", "LoRA", "FSDP"
Ready to connect★ 163
- View details
simulation-platform-engineerSkillAI & models
Expert-level Simulation Platform Engineer specializing in autonomous driving simulation, scenario generation, sensor model validation, and large-scale regression testing pipelines. Expert-level Simulation Platform Engineer specializing in autonomous driving... Use when: autono...
Ready to connect★ 163
- View details
claude-handoffSkillAI & models
Hand the current conversation off to a fresh background agent that picks up the work immediately.
Ready to connect★ 161
- View details
exportSkillAI & models
Extract your persona into CLAUDE.md or AGENTS.md for use in any AI agent
Ready to connect★ 162
- View details
hwp-model-specSkillAI & models
1:1 field mapping table between HWP 5.0 and HWPX (OWPML). Referenced when designing, implementing, and verifying the hwp-model crate.
Ready to connect★ 161
- View details
kmp-starter-feature-purchasesSkillAI & models
The KMP Starter Template purchases system (RevenueCat) — setup, PurchasesViewModel vs PurchasesLogics, paywall navigation + customization, publish/purchases.json metadata, and entitlement checks.
Ready to connect★ 162
- View details
kmp-starter-koinSkillAI & models
Dependency injection with Koin on the KMP Starter Template — one module per layer, plugin selection, singleOf bindings, registration in InitKoin, viewModelOf/parameterized koinViewModel, and scoped navigators + ViewModels for nested nav.
Ready to connect★ 162
- View details
kmp-starter-mviSkillAI & models
How to implement MVI on the KMP Starter Template — State, Actions, Events, and the MviViewModel base class (initialState, onAction, onStateStart, emitEvent/emitEventAsync).
Ready to connect★ 162
- View details
roundtableSkillAI & models
Convene a roundtable of sub-agents that debate a decision or proposal from opposing perspectives — parallel independent statements, anonymous cross-review, then a chaired verdict reporting consensus and dissent.
Ready to connect★ 161
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.