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: Communication
1,651 results · page 4 of 56
- View details
better-writingSkillCommunication
Helps your agent write and review user-facing text like button labels, error messages, and onboarding copy.
Ready to connect★ 10k
- View details
ads-competitorSkillCommunication
Lets your agent research competitors' paid ads, creative, and landing pages from public ad libraries.
Ready to connect★ 9k
- View details
ads-createSkillCommunication
Lets your agent draft paid-ad campaign concepts, ad copy, and creative briefs from your brand profile and goals.
Ready to connect★ 9k
- View details
ads-creativeSkillCommunication
Lets your agent review paid-ad copy, images, and video for quality, fatigue, and platform rules.
Ready to connect★ 9k
- View details
ads-landingSkillCommunication
Lets your agent audit paid-ad landing pages for message match, mobile UX, speed, trust, forms, and conversion friction.
Ready to connect★ 9k
- View details
frame-macos-notificationSkillCommunication
Lets your agent create a fake macOS notification banner image with app icon and title text for video overlays.
Ready to connect★ 9k
- View details
gog-gmailSkillCommunication
Lets your agent manage Gmail like sending, reading, and organizing email messages.
Ready to connect★ 8k
- View details
gog-inbox-triageSkillCommunication
Lets your agent sort unread Gmail, read messages safely, and draft replies for you.
Ready to connect★ 8k
- View details
gog-weekly-digestSkillCommunication
Lets your agent create a weekly summary of your Google Calendar events, Gmail, and Tasks.
Ready to connect★ 8k
- View details
cairo-vulnerability-scannerSkillCommunication
Scans Cairo and StarkNet smart contracts for six critical vulnerability types before they cause problems.
Ready to connect★ 7k
- View details
crypto-protocol-diagramSkillCommunication
Lets your agent turn crypto protocol descriptions or code into Mermaid sequence diagrams of message flows.
Ready to connect★ 7k
- View details
ui-primitivesSkillCommunication
Guides your agent to build UI components using your project's existing primitives instead of rewriting basic controls.
Ready to connect★ 7k
- View details
eol-messageSkillCommunication
Lets your agent draft end-of-life announcements for retiring a product, feature, or plan, from brief notices to phased comms.
Ready to connect★ 7k
- View details
incoming-request-advisorSkillCommunication
Lets your agent break down an incoming message into the literal ask and the underlying goal so you can reply well.
Ready to connect★ 7k
- View details
jobs-to-be-doneSkillCommunication
Lets your agent analyze customer needs in a structured jobs-to-be-done format for product positioning and messaging.
Ready to connect★ 7k
- View details
positioning-workshopSkillCommunication
Lets your agent run a positioning workshop to define your target customer, need, category, benefits, and differentiation.
Ready to connect★ 7k
- View details
comment-writerSkillCommunication
Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.
Ready to connect★ 7k
- View details
git-commitSkillCommunication
Lets your agent write clean, standardized git commit messages for your code changes.
Ready to connect★ 6k
- View details
wechat-official-messagesSkillCommunication
Lets your agent draft WeChat follower-message automation plans and send confirmed customer-service texts to a chosen user.
Ready to connect★ 6k
- View details
debridgeSkillCommunication
Lets your agent build cross-chain bridges and move tokens between Solana and EVM chains using the deBridge SDK.
Ready to connect★ 6k
- View details
genlayer-erc7710-connectorSkillCommunication
Lets your agent design delegated-authority links between GenLayer contract decisions and EVM revocation controls.
Ready to connect★ 6k
- View details
near-ai-cloudSkillCommunication
Lets your agent run AI inference through NEAR AI Cloud and verify the hardware attestation behind it.
Ready to connect★ 6k
- View details
afkSkillCommunication
Lets your agent enter an away mode so routine tasks run with minimal supervision while you're gone.
Ready to connect★ 5k
- View details
ahoySkillCommunication
Lets your agent recap session events and surface unanswered decisions when you invoke /ahoy.
Ready to connect★ 5k
- View details
parsing-hl7v2-messagesSkillCommunication
Lets your agent decode pipe-delimited HL7 v2 healthcare messages into structured fields and extract narrative text.
Ready to connect★ 5k
- View details
claude-maintain-modelsSkillCommunication
Lets your agent add new AI models to a model list file and draft a Discord announcement about it.
Ready to connect★ 5k
- View details
release-digestSkillCommunication
Lets your agent post a Slack recap of changes since the last release, grouping merged PRs by author and type.
Ready to connect★ 5k
- View details
better-auth-best-practicesSkillCommunication
Gives your agent guidance for setting up Better Auth authentication, including sessions, OAuth, and database adapters.
Ready to connect★ 5k
- View details
define-errorsSkillCommunication
Helps your agent create and review well-structured error types in TypeScript code.
Ready to connect★ 5k
- View details
type-level-error-messagesSkillCommunication
Helps your agent write TypeScript code that shows clear, readable error messages when wrong values are passed.
Ready to connect★ 5k
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.
52,524 of the 52,958 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.