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: AI & models
8,700 results · page 19 of 290
- View details
story-long-scanSkillAI & models
Lets your agent scan web novel ranking charts from Qidian, Fanqie and Jinjiang to spot market trends and popular themes.
Ready to connect★ 7k
- View details
story-short-scanSkillAI & models
Lets your agent scan trending short fiction charts on Chinese reading platforms to spot popular genres.
Ready to connect★ 7k
- View details
rdd-advisory-transportSkillAI & models
Trigger: reviewer transport, advisory transport, review adapter, lens prompt/schema, OpenCode reviewer plugin, Codex reviewer, ReviewProviderContract. Enforce the shared Go advisory reviewer transport contract.
Ready to connect★ 7k
- View details
liger-autopatchSkillAI & models
Lets your agent add Liger Kernel support for a HuggingFace model by generating patch code, tests, and docs.
Ready to connect★ 7k
- View details
moltbookSkillAI & models
Lets your agent register, post, comment, upvote, and create communities on a social network for AI agents.
Ready to connect★ 7k
- View details
add-providerSkillAI & models
Lets your agent add a new LLM provider to DeepChat by making reviewed code changes.
Ready to connect★ 6k
- View details
vueSkillAI & models
Gives your agent a reference for writing Vue 3 components with the Composition API and script setup.
Ready to connect★ 6k
- View details
ouroboros-helpSkillAI & models
Gives your agent a reference guide for Ouroboros commands and agents.
Ready to connect★ 6k
- View details
bnbchain-mcpSkillAI & models
Lets your agent query blocks, transactions, tokens and wallets on BNB Chain and send transactions.
Ready to connect★ 6k
- View details
heliusSkillAI & models
Lets your agent build and run Solana apps: send transactions, query NFTs, stream blockchain events, and analyze wallets.
Ready to connect★ 6k
- View details
metaplexSkillAI & models
Lets your agent create and manage Solana NFTs, tokens, and candy machines using Metaplex tools.
Ready to connect★ 6k
- View details
nla-arbitrateSkillAI & models
Lets your agent manually review and decide pending NLA escrow arbitration requests instead of relying on the automated oracle.
Ready to connect★ 6k
- View details
openserv-ideaboard-apiSkillAI & models
Lets your agent submit ideas, pick up tasks, and collaborate with other agents on the OpenServ Ideaboard.
Ready to connect★ 6k
- View details
starknet-identitySkillAI & models
Lets your agent register an on-chain identity as an NFT and collect feedback and validation.
Ready to connect★ 6k
- View details
trustless-agentsSkillAI & models
Lets your agent look up on-chain identity and reputation records for other agents and build a registration card.
Ready to connect★ 6k
- View details
yellow-settlement-roomSkillAI & models
Lets your agent join a shared settlement room with other agents to pool funds and settle a final split.
Ready to connect★ 6k
- View details
sn-ppt-standardSkillAI & models
Lets your agent build PowerPoint decks by running a ready-made pipeline that calls AI models for you.
Ready to connect★ 6k
- View details
- View details
sn-team-harnessSkillAI & models
Use when a user asks what SenseNova Team Harness is, wants an introduction or overview, is getting started, or is deciding whether it fits — a self-hosted workspace where people and local AI agents collaborate on conversations, projects, work items, and artifacts. Covers its core concepts (Workspace
Ready to connect★ 6k
- View details
sn-updateSkillAI & models
Lets your agent update the SenseNova skill bundle in its own install when you ask for it.
Ready to connect★ 6k
- View details
humanize-koreanSkillAI & models
Rewrites Korean text written by AI so it reads like natural, human-written Korean without changing the content.
Ready to connect★ 5k
- View details
ask-user-authoritySkillAI & models
Gives your agent a decision procedure for judging findings and escalating only genuinely ambiguous ones to you.
Ready to connect★ 5k
- View details
bootstrap-diagnosticsSkillAI & models
Lets your agent follow a playbook to diagnose and fix session-start bootstrap and network-check issues.
Ready to connect★ 5k
- View details
captain-hold-lifecycleSkillAI & models
Lets your agent follow a policy that keeps unresolved captain calls tracked until investigations and reviews are truly complete.
Ready to connect★ 5k
- View details
diagnostic-reasoningSkillAI & models
Guides your agent through diagnosing reported bugs by reproducing them, separating causes, and testing counterfactuals.
Ready to connect★ 5k
- View details
firstmate-codexappSkillAI & models
Gives your agent a playbook for creating, steering, and reviewing Codex Desktop threads while working with Firstmate.
Ready to connect★ 5k
- View details
fmx-respondSkillAI & models
Lets your agent handle Relay mentions by reading, classifying, and replying to requests autonomously.
Ready to connect★ 5k
- View details
harness-adaptersSkillAI & models
Gives your agent reference instructions for spawning, resuming, interrupting, and managing other agents in the firstmate harness.
Ready to connect★ 5k
- View details
process-event-sourcesSkillAI & models
Lets your agent set up watches that wake it when a process or condition fires an event.
Ready to connect★ 5k
- View details
quota-array-dispatchSkillAI & models
Lets your agent pick the right model profile when a dispatch rule matches more than one candidate.
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.