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 692 of 1,836
- View details
gtex-databaseSkillDatabases & data
Lets your agent look up gene RNA expression levels and variant eQTL data from the GTEx database across 54 tissue sites.
Ready to connect★ 324
- View details
hf-datasetsSkillDatabases & data
Lets your agent load, process, split, and publish datasets using the HuggingFace datasets library.
Ready to connect★ 324
- View details
human-protein-atlas-databaseSkillDatabases & data
Lets your agent retrieve protein expression and location data from the Human Protein Atlas database.
Ready to connect★ 324
- View details
hunt-adSkillDocs & knowledge
Lets your agent hunt for Active Directory attacks, from user enumeration to finding paths to full domain control.
Ready to connect★ 323
- View details
hunt-apiSkillDocs & knowledge
Lets your agent hunt for security flaws in APIs like broken access control, data leaks, and weak authentication.
Ready to connect★ 323
- View details
hunt-authSkillDocs & knowledge
Lets your agent hunt for authentication bypasses and account takeover flaws during authorized security tests.
Ready to connect★ 323
- View details
hunt-bizlogicSkillDocs & knowledge
Hunts business-logic flaws like price tampering, coupon abuse, and state bypasses in web apps during security testing.
Ready to connect★ 323
- View details
hunt-burpSkillDocs & knowledge
Lets your agent analyze Burp Suite proxy history, replay requests, and fuzz for web vulnerabilities.
Ready to connect★ 323
- View details
hunt-cacheSkillDocs & knowledge
Lets your agent find web cache poisoning and cache deception flaws in web apps.
Ready to connect★ 323
- View details
hunt-cloudSkillDocs & knowledge
Lets your agent scan cloud accounts for security weaknesses like exposed credentials, risky permissions, and attacker access paths.
Ready to connect★ 323
- View details
hunt-coreSkillDocs & knowledge
Lets your agent run security hunts with shared rules for scoping, authorization checks, and confirming real findings.
Ready to connect★ 323
- View details
hunt-federationSkillDocs & knowledge
Lets your agent hunt for OAuth and SAML flaws like redirect bypasses and XML signature wrapping.
Ready to connect★ 323
- View details
hunt-icsSkillDev tools
Lets your agent test and exploit industrial control systems like PLCs, Modbus, and SCADA devices.
Ready to connect★ 323
- View details
hunt-injectionSkillFiles & storage
Lets your agent test websites for injection flaws like IDOR, XXE, SSRF, and template injection during security audits.
Ready to connect★ 323
- View details
hunt-llmSkillDocs & knowledge
Lets your agent hunt for AI security flaws like prompt injection, data leakage, and excessive agency using OWASP guidance.
Ready to connect★ 323
- View details
hunt-m365SkillDocs & knowledge
Lets your agent probe Microsoft 365 and Entra ID tenants for users and security weaknesses.
Ready to connect★ 323
- View details
hunt-macosSkillDocs & knowledge
Lets your agent research macOS attack techniques like privilege escalation, persistence, and security bypasses.
Ready to connect★ 323
- View details
hunt-mcpSkillDocs & knowledge
Lets your agent spot security risks in other tools it uses, like prompt injection and over-permissioned tools.
Ready to connect★ 323
- View details
hunt-smugglingSkillDocs & knowledge
Lets your agent test websites for HTTP request smuggling vulnerabilities using timing and differential checks.
Ready to connect★ 323
- View details
hunt-vpnSkillDocs & knowledge
Lets your agent look up known vulnerabilities and default credentials for enterprise VPN gateways.
Ready to connect★ 323
- View details
hunt-windowsSkillProductivity
Lets your agent find and run local Windows privilege escalation checks to go from a basic shell to SYSTEM.
Ready to connect★ 323
- View details
inbox-triageSkillCommunication
Lets your agent summarize your Gmail inbox and send a concise, action-oriented digest to chat.
Ready to connect★ 324
- View details
jaspar-databaseSkillDatabases & data
Lets your agent look up transcription factor binding profiles and gene-to-matrix IDs in the JASPAR database.
Ready to connect★ 324
- View details
label-quality-auditSkillDev tools
Lets your agent audit training data labels and flag likely mislabeled examples for review.
Ready to connect★ 324
- View details
literature-search-arxivSkillSearch
Lets your agent search arXiv for research papers and pull abstracts or full-text PDFs.
Ready to connect★ 324
- View details
literature-search-biorxivSkillSearch
Lets your agent search, filter, and download biology and medical preprints from bioRxiv and medRxiv by date, category, keyword, or DOI.
Ready to connect★ 324
- View details
literature-search-europepmcSkillSearch
Lets your agent search Europe PMC for scientific papers and download open-access full texts and citations.
Ready to connect★ 324
- View details
literature-search-openalexSkillSearch
Lets your agent search a scholarly database for research papers, authors, and citation data and resolve DOIs.
Ready to connect★ 324
- View details
llm-assisted-curationSkillDatabases & data
Lets your agent filter, score, label, and generate training data using local LLMs.
Ready to connect★ 324
- View details
lsp-code-analysisSkillDocs & knowledge
Lets your agent run long-lived tasks through a persistent platform that tracks work, memory, and approvals.
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.