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
8,897 results · page 142 of 297
- View details
github-to-mcp-guideSkillAI & models
Guide to converting GitHub repositories into MCP servers automatically. Extract tools from OpenAPI, GraphQL, and REST APIs for Claude Desktop, Cursor, Windsurf, Cline, and VS Code. AI-powered code generation creates type-safe TypeScript/Python MCP servers. Zero config — just paste a repo URL.
Ready to connect★ 172
- View details
giza-zkml-visualizationSkillAI & models
Giza ZKML Agent Visualization — guide covering key concepts, implementation patterns, and best practices.
Ready to connect★ 172
- View details
- View details
mcp-tool-discovery-guideSkillAI & models
Guide to Lyra Tool Discovery — an AI-powered automation toolkit that discovers MCP servers for you. Point it at GitHub, npm, or configure custom discovery sources. Let GPT or Claude analyze APIs and generate ready-to-ship plugin configs. Zero manual work.
Ready to connect★ 172
- View details
okx-ai-guideSkillAI & models
OKX.AI (the Agent economic system) intro & onboarding entry. Use whenever the user asks what OKX.AI is, what it can do, how to use or get started with it, wants an OKX.AI tutorial / quickstart / help, or types the product name in any spelling / spacing / casing / typo variant (OKXAI, okx ai, okx-ai,
Ready to connect★ 172
- View details
rig-a-modelSkillAI & models
Auto-rig a static 3D GLB model into an animation-ready one. Use when you or the user have an existing GLB and want to rig it, add a skeleton, add bones, make it posable, or make it animatable — "rig this model", "add a skeleton to my GLB", "make this character animation-ready". Takes a GLB URL, adds
Ready to connect★ 172
- View details
sperax-ecosystem-overviewSkillAI & models
High-level overview of the Sperax ecosystem — USDs auto-yield stablecoin, SPA/veSPA governance, Sperax Farms, ERC-8004 on-chain agent identity, and SperaxOS AI Agent Workspace. Use when giving ecosystem overviews, comparing DeFi products, or explaining how Sperax components work together.
Ready to connect★ 172
- View details
tip-jarSkillAI & models
Let viewers send a USDC tip directly to the agent creator.
Ready to connect★ 172
- View details
- View details
x402-gas-stationSkillAI & models
Autonomous agent that spends money via x402 protocol to acquire premium data, like fueling up at a gas station.
Ready to connect★ 172
- View details
config-syncSkillAI & models
Sync configuration changes across the settings-opencode repo and live harness directories (OpenCode and Claude Code). Invoke when adding, updating, or removing agents, rules, hooks, commands, prompts, skills, or harness config. Keywords: "add agent", "change rule", "update skill", "modify config", "
Ready to connect★ 171
- View details
harness-paritySkillAI & models
Use whenever you add, edit, rename, or delete any harness artifact — a skill, agent, command, rule, or instruction — in either .claude/ or .opencode/. Replicate the equivalent change in the other harness with the correct frontmatter and registration translation, so the two trees stay in parity.
Ready to connect★ 171
- View details
strategic-compactSkillAI & models
Make compaction safe for fully autonomous multi-phase work. The agent prepares durable state so auto-compaction never requires user input and never breaks flow.
Ready to connect★ 171
- View details
wioSkillAI & models
Testing workflow skill for finding high-value test candidates, writing focused tests, generating realistic workloads, reviewing test value, and diagnosing test-suite health. Use for prompts about what to test next, adding or improving tests, reviewing whether a test is worth keeping, low-signal or f
Ready to connect★ 170
- View details
blue-teamSkillAI & models
Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing pytest/JUnit tests) — and wants the target patched until those failures are closed without breaking what already works. It
Ready to connect★ 169
- 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★ 170
- View details
hypothesis-genSkillAI & models
Use when the user wants to generate and literature-vet a pool of novel, testable research hypotheses for a question or domain. A multi-agent loop: a Generator proposes candidate hypotheses, a LiteratureScout grounds each in real retrieved literature (already known? closest prior work? what gap does
Ready to connect★ 169
- 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★ 170
- 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★ 170
- View details
ml-autoresearchSkillAI & models
Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/o
Ready to connect★ 169
- 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★ 170
- View details
ml-foundation-potentialsSkillAI & models
Guide for selecting the most appropriate foundation MLIP model based on simulation requirements.
Ready to connect★ 170
- 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★ 170
- View details
ml-generative-mattergenSkillAI & models
Generate inorganic material structures using MatterGen, a diffusion-based generative model.
Ready to connect★ 170
- 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★ 170
- View details
ml-mlip-speedSkillAI & models
Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).
Ready to connect★ 170
- 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★ 170
- View details
plan-loopSkillAI & models
Use when the user has a coding or engineering prompt and wants it refined into a detailed, executable plan before any code is written — the planning stage of a prompt → plan → execute → debug pipeline. It decomposes the prompt from first principles (objective, end state, environment, building blocks
Ready to connect★ 169
- View details
power-analysisSkillAI & models
Use when the user is planning a two-arm comparison (an A/B test, a simple RCT, a behavioral study, or a two-model/two-config evaluation) and needs to size it and preregister it before collecting data — finding the per-group sample size that hits target statistical power for the smallest effect worth
Ready to connect★ 169
- View details
prompt-optimizeSkillAI & models
Use when the user has a prompt that feeds a system they can already score, and wants that prompt automatically improved to raise the score against their own evaluation command. Makes one targeted quality edit per iteration — clarity, context, specificity, structure, examples, decomposition, guardrai
Ready to connect★ 169
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.
53,788 of the 54,220 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.