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: Media
5,297 results · page 89 of 177
- View details
guardrail-designSkillMedia
Defining behavioral boundaries — what the AI should and shouldn't do.
Ready to connect★ 173
- View details
handoff-protocolsSkillMedia
Designing smooth transitions between agents and between AI and humans.
Ready to connect★ 173
- View details
harm-anticipationSkillMedia
Proactively identifying failure modes, misuse, and unintended consequences.
Ready to connect★ 173
- View details
heuristic-evaluation-aiSkillMedia
Adapting Nielsen's heuristics and new AI-specific heuristics for AI interfaces.
Ready to connect★ 173
- View details
longitudinal-measurementSkillMedia
Tracking AI product quality over time — drift, degradation, and improvement.
Ready to connect★ 173
- View details
mixed-initiative-flowSkillMedia
When the AI leads vs. when the user leads, and how to hand off control.
Ready to connect★ 173
- View details
multimodal-orchestrationSkillMedia
Coordinating text, image, voice, and tool-use modalities in a single interaction.
Ready to connect★ 173
- View details
output-quality-rubricsSkillMedia
Defining what "good" looks like for AI outputs — accuracy, relevance, helpfulness.
Ready to connect★ 173
- View details
persona-architectureSkillMedia
Defining AI character, voice, and personality traits.
Ready to connect★ 173
- View details
progressive-disclosureSkillMedia
Revealing AI capability gradually to match user mental models.
Ready to connect★ 173
- View details
prompt-versioningSkillMedia
Managing prompt iterations, testing changes, and tracking what works.
Ready to connect★ 173
- View details
system-prompt-structureSkillMedia
Anatomy of effective system prompts — role, context, constraints, format.
Ready to connect★ 173
- View details
task-decompositionSkillMedia
Breaking complex user goals into subtasks that agents can handle.
Ready to connect★ 173
- View details
template-designSkillMedia
Creating reusable, parameterised prompt templates for consistent outputs.
Ready to connect★ 173
- View details
tone-calibrationSkillMedia
Adjusting formality, warmth, confidence, and style per context.
Ready to connect★ 173
- View details
transparency-patternsSkillMedia
Showing users what the AI knows, doesn't know, and how confident it is.
Ready to connect★ 173
- View details
trust-calibrationSkillMedia
Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.
Ready to connect★ 173
- View details
user-satisfaction-signalsSkillMedia
Interpreting implicit and explicit feedback — edits, regenerations, abandonment.
Ready to connect★ 173
- View details
value-specificationSkillMedia
Translating organisational values and user expectations into system constraints.
Ready to connect★ 173
- View details
angular-dddSkillMedia
Domain-Driven Design for Angular/TypeScript: functional patterns with `type` aliases, `readonly` fields, pure rule functions, immutable value types, branded IDs, and ports as abstract classes. Use when creating or reviewing domain models, aggregates, rule functions, ports, bounded contexts, or domai
Ready to connect★ 172
- View details
bump-openstack-imageSkillMedia
Bump an OpenStack service container image to the latest digest in `roles/defaults/vars/main.yml`, across one or more Atmosphere branches. Use this when asked to bump, refresh, or update the digest for a service image such as Magnum, Neutron, Nova, Cinder, Keystone, Glance, Heat, Manila, Barbican, Oc
Ready to connect★ 172
- View details
create-videoSkillMedia
Creates a NEW video for this repo's "compare / differentiate knowledge" series — a vertical TikTok/Reels/Shorts clip of 30-40s, with a fixed 3-zone layout per DESIGN.md, Vietnamese voiceover generated with Edge TTS (default, free) or Vbee TTS, edited with HyperFrames. Use this skill when the user sa
Ready to connect★ 172
- View details
dotnet-dddSkillMedia
Domain-Driven Design best practices for .NET 10 domain code. Use when creating or reviewing entities, value objects, aggregates, aggregate roots, repositories, domain services, bounded contexts, or domain events in C#. Use when refactoring anemic models toward rich domain logic, enforcing aggregate
Ready to connect★ 172
- View details
iso-24495-4SkillMedia
Provisional task skill for organisational plain language implementation (based on ISO/CD 24495-4, committee draft). Activates for plain language gap analysis, policy drafting, review workflow design, and organisational readiness for the future published standard. Does not activate for ordinary writi
Ready to connect★ 172
- View details
socratic-designSkillMedia
evidence-first decision-gating for planning, design, architecture, and refactor requests with unresolved requirements, scope, constraints, facts, or tradeoffs. use when the next safe step is to ask exactly one dependency-safe question before proposing a plan or implementation, especially when critic
Ready to connect★ 172
- View details
content-performanceSkillMedia
Analyze content performance across YouTube, TikTok, Instagram, and Twitter to identify what works. Compares engagement rates, format effectiveness, posting cadence impact, and audience response patterns across platforms for content strategy optimization.
Ready to connect★ 164
- View details
habit-hooks-reviewSkillMedia
Spawn a reviewer sub-agent to assess a change set against habit-hooks's coding principles. Use AFTER habit-hooks reports clean — habit-hooks catches structural smells; this catches what it cannot (correctness, tests, design, missed edge cases).
Ready to connect★ 170
- View details
kol-discoverySkillMedia
Discover and evaluate KOLs (Key Opinion Leaders) and creators across TikTok, Instagram, YouTube, and Xiaohongshu through SandBase. Use when asked for influencer research, creator outreach lists, KOL evaluation, or partnership prospecting.
Ready to connect★ 164
- View details
visionSkillMedia
Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images. Use when you need to understand screenshots, UI layouts, diagrams, or any image content. Supports png/jpg/webp/gif.
Ready to connect★ 170
- View details
godot-wechat-minigame-adapterSkillMedia
Apply the bundled self-contained Godot WeChat Mini Game adapter kit to an official Godot checkout. Use when the user wants to port official Godot to WeChat Mini Game, refresh a nearby 4.6-based port, or inspect the shipped patch/source bundle for WXMEMFS, `wx.request`, audio cleanup, display/input,
Ready to connect★ 169
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.
54,764 of the 55,196 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.