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 693 of 1,836
- View details
metasploitSkillSearch
Lets your agent run penetration-testing commands like network scans, exploit searches, and reverse shell handlers.
Ready to connect★ 323
- View details
ncbi-sequence-fetchSkillSearch
Lets your agent fetch protein and nucleotide sequences from NCBI databases by accession, gene, or organism.
Ready to connect★ 324
- View details
ndaySkillSecurity
Lets your agent analyze security patches to find the bug they fix and build proof-of-concept exploits.
Ready to connect★ 323
- View details
next-moveSkillDev tools
Lets your agent rank and explain the highest-value next steps during a security engagement.
Ready to connect★ 323
- View details
openfda-databaseSkillSearch
Lets your agent search FDA data on drugs, devices, foods, recalls, adverse events, and approvals.
Ready to connect★ 324
- View details
pr-triageSkillDev tools
Lets your agent summarize your GitHub pull requests into a morning triage report, flag stale ones, and post the rundown to chat.
Ready to connect★ 324
- View details
prime-intellect-cliSkillDev tools
Lets your agent rent and manage Prime Intellect GPU compute, run RL training, and publish RL environments.
Ready to connect★ 324
- View details
protein-sequence-msaSkillSearch
Lets your agent align multiple protein sequences to compare similarity and conserved regions.
Ready to connect★ 324
- View details
protein-sequence-similarity-searchSkillSearch
Lets your agent find proteins similar to a given protein sequence and infer what it might do.
Ready to connect★ 324
- View details
pt-workflowSkillSecurity
Runs an automated penetration test campaign end to end, telling your agent the exact next action each step.
Ready to connect★ 323
- View details
pubchem-databaseSkillSearch
Lets your agent look up chemicals and drugs in PubChem, fetching properties, structures, and bioactivity data.
Ready to connect★ 324
- View details
pymolSkillMedia
Lets your agent visualize, analyze, and render 3D protein and molecular structures, creating images and measuring features.
Ready to connect★ 324
- View details
quickgo-databaseSkillDatabases & data
Lets your agent look up gene functions and biological pathways using the Gene Ontology database.
Ready to connect★ 324
- View details
redteamleadSkillDocs & knowledge
Lets your agent get senior red-team guidance at decision points, returning ranked next directions from your engagement wiki.
Ready to connect★ 323
- View details
research-ingestSkillDocs & knowledge
Lets your agent fetch security writeups and repo docs and file them into the right wiki pages, deduplicated and re-indexed.
Ready to connect★ 323
- View details
scienceskillscommonSkillAI & models
Provides shared plumbing, like a rate-limited HTTP client, used by other science skills rather than doing tasks itself.
Ready to connect★ 324
- View details
screenshot-burpSkillMedia
Lets your agent capture a Burp Suite request and response as a screenshot proof-of-concept image.
Ready to connect★ 323
- View details
string-databaseSkillDatabases & data
Lets your agent look up protein-protein interactions, enrichment, and homology in the STRING database.
Ready to connect★ 324
- View details
swiftui-specialistSkillAI & models
Guides your agent to write and review SwiftUI code using idiomatic patterns and best practices.
Ready to connect★ 324
- View details
swiftui-whats-new-27SkillAI & models
Lets your agent look up the new SwiftUI APIs and fixes for compile errors in the 2027 Apple OS releases.
Ready to connect★ 324
- View details
test-modernizerSkillAI & models
Lets your agent update Swift test suites to modern Swift Testing features or migrate from XCTest.
Ready to connect★ 324
- View details
triton-kernel-programmingSkillDev tools
Gives your agent a hands-on template and API reference for writing, tuning, debugging, and benchmarking Triton GPU kernels.
Ready to connect★ 324
- View details
ubiquitous-languageSkillDocs & knowledge
Gives your agent a shared, persistent vocabulary so long-running multi-agent work stays consistent and auditable.
Ready to connect★ 324
- View details
ucsc-conservation-and-tfbsSkillWeb & browsing
Lets your agent fetch evolutionary conservation scores and transcription factor binding sites for genomic regions from UCSC.
Ready to connect★ 324
- View details
uikit-app-modernizationSkillAI & models
Lets your agent update old iOS UIKit code to modern APIs for multi-window apps, like replacing mainScreen and lifecycle calls.
Ready to connect★ 324
- View details
unibind-databaseSkillDatabases & data
Lets your agent look up experimentally validated transcription factor binding sites and download the data.
Ready to connect★ 324
- View details
uniprot-databaseSkillSearch
Lets your agent look up protein information, sequences, and functions from the UniProt databases.
Ready to connect★ 324
- View details
wiki-arsenalSkillSearch
Lets your agent quickly search a security wiki of techniques, payloads, tools, and cheatsheets for a target or vulnerability.
Ready to connect★ 323
- View details
wiki-reconSkillWeb & browsing
Lets your agent run reconnaissance on a target, finding subdomains, live hosts, and scanning for known vulnerabilities.
Ready to connect★ 323
- View details
workflow-skill-creatorSkillAI & models
Lets your agent turn a workflow you just completed into a reusable skill.
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.