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
5,215 results · page 87 of 174
- View details
cultural-adaptationSkillMedia
Adapting AI behavior for different cultural contexts, languages, and norms.
Ready to connect★ 173
- View details
- View details
emotional-designSkillMedia
How the AI responds to user frustration, confusion, delight, and distress.
Ready to connect★ 173
- View details
error-personalitySkillMedia
How the AI communicates mistakes, uncertainty, and limitations gracefully.
Ready to connect★ 173
- View details
escalation-designSkillMedia
When and how AI should escalate to humans, refuse, or ask for clarification.
Ready to connect★ 173
- View details
failure-recoverySkillMedia
What happens when an agent fails — retry, fallback, escalate, or graceful degradation.
Ready to connect★ 173
- View details
failure-taxonomySkillMedia
Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.
Ready to connect★ 173
- View details
feedback-loopsSkillMedia
User correction, thumbs up/down, inline editing, and reinforcement signals.
Ready to connect★ 173
- View details
few-shot-patternsSkillMedia
Crafting examples that steer AI behavior effectively.
Ready to connect★ 173
- View details
frustration-detectionSkillMedia
Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.
Ready to connect★ 173
- 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
ai-game-world-designSkillMedia
Complete mastery guide for designing and building AI-powered game worlds — procedural world generation, NPC behavior trees, LLM-driven dialogue systems, emergent storytelling, economy simulation, player modeling, and real-time difficulty adaptation. Covers the full stack from world-building fundamen
Ready to connect★ 172
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.