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 706 of 1,836
- View details
gx-paid-ads-expertSkillAI & models
Lets your agent plan, launch, and manage paid ad campaigns on Meta Ads and Google Ads.
Ready to connect★ 289
- View details
gx-seo-technical-expertSkillWeb & browsing
Lets your agent audit a website's crawlability, indexing, page speed, and structured data for SEO issues.
Ready to connect★ 289
- View details
huggingface-models-expertSkillDatabases & data
Lets your agent choose, fine-tune, and deploy Hugging Face models using transformers, datasets, and inference endpoints.
Ready to connect★ 289
- View details
incident-response-triageSkillCommunication
Lets your agent triage a security incident and plan initial containment following NIST guidance.
Ready to connect★ 289
- View details
kubernetes-security-auditorSkillCloud & infra
Lets your agent scan Kubernetes configs for security problems and suggest fixes ranked by impact.
Ready to connect★ 289
- View details
llm-finetuning-strategistSkillDatabases & data
Lets your agent plan LLM fine-tuning runs, choosing methods, datasets, hyperparameters, and evaluation approach.
Ready to connect★ 289
- View details
local-skillSkillDev tools
Lets your agent run a test fixture that checks how commands work in Rust and WebAssembly environments.
Ready to connect★ 309
- View details
long-form-writerSkillAI & models
Lets your agent draft structured long-form documents from a brief and outline, with controls for tone and reading level.
Ready to connect★ 289
- View details
meta-ads-optimizerSkillAI & models
Lets your agent audit and rewrite Meta Facebook and Instagram ad campaigns, including audiences, creatives, and budgets.
Ready to connect★ 289
- View details
microsoft-typescriptSkillFiles & storage
Gives your agent guidance for writing, editing, and debugging TypeScript code files.
Ready to connect★ 309
- View details
od-design-briefSkillMedia
Lets your agent turn a structured design brief into a concrete design spec.
Ready to connect★ 289
- View details
od-design-mdSkillFiles & storage
Lets your agent create and manage DESIGN.md files in your project.
Ready to connect★ 289
- View details
od-faq-pageSkillSearch
Lets your agent build a FAQ page with collapsible sections, search, and category filtering.
Ready to connect★ 289
- View details
od-gsap-coreSkillAI & models
Lets your agent animate web page elements using GSAP with tweens, easing, duration, and stagger effects.
Ready to connect★ 289
- View details
osint-investigatorSkillSecurity
Lets your agent plan and correlate open-source intelligence on domains, organizations and infrastructure for investigations.
Ready to connect★ 289
- View details
owasp-code-auditSkillFiles & storage
Lets your agent scan source code for the top 10 security flaws and get a prioritized list of fixes.
Ready to connect★ 289
- View details
pcap-triage-analystSkillAI & models
Lets your agent analyze packet capture summaries to flag suspicious traffic, indicators of compromise, and suggest next steps.
Ready to connect★ 289
- View details
prompt-injection-testerSkillAI & models
Lets your agent test an LLM app for prompt injection and jailbreak weaknesses and score the results.
Ready to connect★ 289
- View details
rag-system-architectSkillAI & models
Lets your agent design retrieval-augmented generation systems, covering chunking, embeddings, vector stores, reranking, and evaluation.
Ready to connect★ 289
- View details
recon-attack-surfaceSkillAI & models
Lets your agent scan a target's external footprint (DNS, subdomains, ports, web tech) and produce a prioritized report.
Ready to connect★ 289
- View details
review-skillSkillAI & models
Lets your agent check an Agent Skill for valid structure, clear triggers, and risky or unclear actions.
Ready to connect★ 309
- View details
sigma-detection-engineerSkillDocs & knowledge
Lets your agent turn a threat description or log sample into a validated Sigma detection rule with MITRE ATT&CK mapping.
Ready to connect★ 289
- View details
simpSkillDev tools
Lets your agent help you write sincere, heartfelt messages to win over your crush.
Ready to connect★ 309
- View details
sindresorhus-log-updateSkillMonitoring & ops
Lets your agent update terminal output in place to show progress bars or animations.
Ready to connect★ 309
- View details
skilldSkillSecurity
Lets your agent manage AI agent skills from the command line, including finding, installing, updating, and removing them.
Ready to connect★ 309
- View details
sql-translatorSkillDatabases & data
Lets your agent turn plain-English questions into a single safe, read-only SQL query against a known schema.
Ready to connect★ 289
- View details
sqlite-vec-skilldSkillDatabases & data
Gives your agent up-to-date guidance and debugging help for writing code that uses the sqlite-vec vector search extension.
Ready to connect★ 309
- View details
stripe-payments-expertSkillCommerce & finance
Lets your agent write Stripe payment code for checkout, subscriptions, webhooks, and tax.
Ready to connect★ 289
- View details
- View details
unjs-cittySkillDev tools
Gives your agent guidance for writing and debugging code that uses the citty command-line framework.
Ready to connect★ 309
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.