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.
Filter by category
55,055 results · page 690 of 1,836
- View details
warranty-trackerSkillDocs & knowledge
Lets your agent track construction warranties, including expiration dates, claims, and manufacturer documents.
Ready to connect★ 327
- View details
weather-apiSkillProductivity
Lets your agent fetch weather forecasts, historical data, and risk assessments to plan outdoor work.
Ready to connect★ 327
- View details
weather-impact-analysisSkillProductivity
Lets your agent predict weather delays and adjust construction schedules using forecast data.
Ready to connect★ 327
- View details
weather-impact-schedulerSkillProductivity
Lets your agent analyze weather forecasts to predict construction delays and adjust the schedule.
Ready to connect★ 327
- View details
xml-readerSkillProductivity
Lets your agent read construction XML files like P6 schedules and COBie exports and turn them into data tables.
Ready to connect★ 327
- View details
pydantic-resolve-3stepSkillCloud & infra
Guides your agent through a three-step workflow to design and build Python projects, from data modeling to deployment.
Ready to connect★ 326
- View details
albumentationsSkillDocs & knowledge
Lets your agent run long-lived goals on a platform that tracks memory, approvals, and audit history.
Ready to connect★ 324
- View details
alphafold-database-fetch-and-analyzeSkillDatabases & data
Lets your agent fetch and analyze AlphaFold predicted protein structures using a UniProt ID.
Ready to connect★ 324
- View details
alphagenome-single-variant-analysisSkillDev tools
Lets your agent analyze how a genetic variant affects gene expression and other genome signals via the AlphaGenome API.
Ready to connect★ 324
- View details
aml-complianceSkillMonitoring & ops
Lets your agent screen customers against sanctions lists, flag politically exposed persons, and draft suspicious activity reports.
Ready to connect★ 324
- View details
angelslimSkillAI & models
Lets you compress large AI models with quantization, pruning, and speculative decoding to run them faster and smaller.
Ready to connect★ 324
- View details
arsenalSkillDocs & knowledge
Lets your agent look up which automated tool or technique to use for a given service or vulnerability.
Ready to connect★ 323
- View details
audit-xcode-security-settingsSkillSecurity
Lets your agent audit and turn on security-focused Xcode build settings like compiler warnings and hardening features.
Ready to connect★ 324
- View details
autogenSkillAI & models
Lets your agent run multiple AI agents that chat with each other, write and run code, and use tools together.
Ready to connect★ 324
- View details
axolotlSkillAI & models
Lets your agent fine-tune large language models using simple YAML configs, with LoRA and multi-GPU support.
Ready to connect★ 324
- View details
bb-workflowSkillDev tools
Lets your agent run an autonomous bug-bounty campaign end to end, driving recon through reporting step by step.
Ready to connect★ 323
- View details
benchmark-contamination-scanSkillDatabases & data
Lets your agent scan training data for benchmark contamination via n-gram overlap, embedding similarity, and canary detection.
Ready to connect★ 324
- View details
bentomlSkillCloud & infra
Lets your agent package machine learning models into prediction services and deploy them to cloud platforms like Kubernetes, AWS, or GCP.
Ready to connect★ 324
- View details
bias-auditSkillDatabases & data
Lets your agent check a dataset for bias across groups like gender or race and report gaps with per-group metrics.
Ready to connect★ 324
- View details
biostatisticsSkillDev tools
Lets your agent run medical statistics tests like t-tests, ANOVA, chi-square, and survival analysis, plus power calculations.
Ready to connect★ 324
- View details
c-bounds-safetySkillAI & models
Lets your agent write and debug C code using the -fbounds-safety extension with pointer annotations and build settings.
Ready to connect★ 324
- View details
campaign-healthSkillDev tools
Lets your agent run a health check that verifies the bb/pt/ctf workflow driver is consistently set up across all machines.
Ready to connect★ 323
- View details
captumSkillAI & models
Lets your agent explain why a PyTorch model made a prediction using feature attribution methods.
Ready to connect★ 324
- View details
ccxtSkillCommerce & finance
Lets your agent fetch crypto market data and place trades across 100+ exchanges like Coinbase and Binance.
Ready to connect★ 324
- View details
chainladderSkillDev tools
Lets your agent run insurance loss reserving calculations like chain ladder and bootstrap simulation in Python.
Ready to connect★ 324
- View details
chembl-databaseSkillDatabases & data
Lets your agent look up drugs, drug targets, and bioactivity data like IC50 values in the ChEMBL database.
Ready to connect★ 324
- View details
chromadbSkillSearch
Lets your agent store and search text by meaning using embeddings, filters, and full-text search.
Ready to connect★ 324
- View details
chrome-devtools-browserSkillWeb & browsing
Lets your agent drive a real visible Chrome browser while you handle logins and captchas yourself.
Ready to connect★ 323
- View details
claude-md-improverSkillFiles & storage
Lets your agent audit and improve CLAUDE.md files by scanning them, scoring quality, and making targeted edits.
Ready to connect★ 323
- View details
cleanrlSkillDocs & knowledge
Lets your agent run long-term goals with persistent memory, approvals, and tracked multi-agent work.
Ready to connect★ 324
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.
54,624 of the 55,055 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.