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
8,898 results · page 297 of 297
- View details
overrelianceSkillAI & models
Detects systems that treat LLM output as authoritative fact in consequential
Ready to connect
- View details
paleo-jsonSkillAI & models
Use when user says "compact json", "minify output", "tight structured", or the agent must emit JSON / structured data. Strip insignificant whitespace, collapse long arrays, shorten keys where safe, keep it parseable. Cuts tokens on structured payloads. Off: "pretty print" / "human-readable".
Ready to connect
- View details
plan-reviewSkillAI & models
Adversarially review a plan, work order, spec, or agent brief before anything gets built. Use when the user wants a plan reviewed, stress-tested, audited, or countersigned, says "plan review" or "poke holes in this plan", or wants a pre-build check on an issue/brief/PRD.
Ready to connect
- View details
product-spec-builderSkillAI & models
Turns a one-sentence or vague product idea into an actionable Product Spec, and records incremental changes for existing products. Used for 0→1 product definition, or for product changes that add capabilities, alter user-visible behavior, public APIs, persistence formats, public data models, permiss
Ready to connect
- View details
q-decision-makingSkillAI & models
Use this skill when the user needs to choose between options, evaluate a path forward, or make a high stakes decision. Activate when the user feels too close to a situation to see it clearly or when multiple competing options need to be evaluated honestly.
Ready to connect
- View details
q-researchSkillAI & models
Use this skill when the user wants an idea, plan, or position pressure tested before committing to it. Activate when the user is about to spend significant time or money on something, wants the strongest case for or against a position, or suspects they are too attached to an outcome to judge it hone
Ready to connect
- View details
q-thinkingSkillAI & models
Use this skill when the user needs to understand a problem before solving it. Activate for complex situations where the answer is not clear, where assumptions need surfacing, or where the user feels stuck or overwhelmed. This skill helps map what is actually happening before any action is taken.
Ready to connect
- View details
sendmux-cliSkillAI & models
Use when a user wants Sendmux terminal commands for agent inbox registration, owner invites, profiles, key-scope preflight, JSON output, or Management, Mailbox, and Sending operations.
Ready to connect
- View details
sendmux-mailbox-agentSkillAI & models
Work efficiently with one Sendmux mailbox from an AI agent. Use for reading, searching, counting, syncing, triaging, filing, deleting, threading, or replying from a mailbox with an smx_mbx_ key or scoped smx_agent_ token, especially when the user asks an agent to inspect an inbox, find relevant mess
Ready to connect
- View details
senior-architect-agentSkillAI & models
Cognitive framework that transforms AI agents into senior architects — evidence-first system understanding, honest uncertainty mapping, architecture debt and convention assessment, knowledge-graph-assisted dependency mapping, impact and blast radius analysis, and architecture reasoning before action
Ready to connect
- View details
sensitive-disclosureSkillAI & models
Detects PII, credentials, and secrets passed to LLM APIs or embedded in system
Ready to connect
- View details
swift-focusengine-proSkillAI & models
Reviews, writes, and fixes focus management code for all Apple platforms (tvOS, iOS/iPadOS, watchOS, visionOS, macOS), covering SwiftUI, UIKit, AppKit, and RealityKit. Use when reading, writing, or reviewing apps that handle focus, hover, key view loops, or Digital Crown navigation.
Ready to connect
- View details
text-summarizerSkillAI & models
Lets your agent summarize text on your machine without sending it anywhere.
Ready to connect
- View details
token-smugglingSkillAI & models
Detects user input passed to LLMs without Unicode normalization, allowing RTL
Ready to connect
- View details
update-provider-modelsSkillAI & models
Add new or remove obsolete model IDs for existing AI SDK providers. Use when adding a model to a provider, removing an obsolete model, or processing a list of model changes from an issue. Triggers on "add model", "remove model", "new model ID", "obsolete model", "update model IDs".
Ready to connect
- View details
weather-forecastSkillAI & models
Fetch 7-day weather forecasts from Open-Meteo API. ALWAYS use get_coordinates.py first when given city names to look up coordinates, then use get_forecast.py with those coordinates. Use for weather forecasts, weather data, or temperature trends.
Ready to connect
- View details
webmcp-sdk-skillSkillAI & models
指导如何使用 WebMCP SDK库去开发WebAgent的技能包，将前端应用快速智能化。它包含 TinyRemoter，WebMcpServer，WebMcpClient，createRemoter， AI-Extension插件开发的文档及指南。
Ready to connect
- View details
writing-for-agentsSkillAI & models
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable — plus a doctor verb that audits the loaded skill and CLAUDE.md/AGENTS.md estate.
Ready to connect
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.
53,789 of the 54,221 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.