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.
Filter by category
54,680 results · page 610 of 1,823
- View details
headlinesSkillAI & models
Lets your agent write and sharpen headlines, titles, and subject lines.
Ready to connect★ 419
- View details
hill-climbSkillDocs & knowledge
Lets your agent improve a metric like speed or memory by testing one change at a time and keeping only measured wins.
Ready to connect★ 419
- View details
html-artifactSkillDocs & knowledge
Lets your agent create polished self-contained HTML pages like reports, prototypes, and diagrams instead of plain markdown.
Ready to connect★ 419
- View details
integration-checkerSkillAI & models
Lets your agent check that connected components are wired correctly and data flows between them.
Ready to connect★ 419
- View details
joy-checkSkillAI & models
Lets your agent score how joyful or grievance-heavy a piece of writing sounds before it's shared.
Ready to connect★ 419
- View details
kotlinSkillAI & models
Gives your agent guidance on Kotlin development, including coroutines, Flow, Channels, and testing with JUnit 5 and Kotest.
Ready to connect★ 419
- View details
kubernetesSkillCloud & infra
Lets your agent inspect and manage Kubernetes clusters, including debugging, security, and access controls.
Ready to connect★ 419
- View details
markdown-converterSkillDocs & knowledge
Lets your agent convert PDFs, Office files, HTML, data, media, and ZIP archives into Markdown.
Ready to connect★ 419
- View details
marketingSkillCommunication
Lets your agent plan marketing campaigns, run SEO audits, draft email sequences, and analyze competitors.
Ready to connect★ 419
- View details
motion-pipelineSkillAI & models
Lets your agent process game animation motion data: import BVH files, detect foot contacts, blend motions, and run inverse kinematics on CPU.
Ready to connect★ 419
- View details
multi-persona-critiqueSkillMedia
Lets your agent critique a proposal from 5 philosophical viewpoints and combine the feedback.
Ready to connect★ 419
- View details
news-collectionSkillAI & models
Lets your agent collect news items, filter them, and check how fresh they are.
Ready to connect★ 419
- View details
objective-loopSkillAI & models
Lets your agent repeat work cycles until it checks that a goal is met or a budget limit stops it.
Ready to connect★ 419
- View details
opensearch-detection-engineerSkillMonitoring & ops
Lets your agent write and validate security detection rules for OpenSearch, including SIGMA rules and MITRE ATT&CK mapping.
Ready to connect★ 419
- View details
parallel-code-reviewSkillSecurity
Runs a code review from three angles at once: security, business logic, and architecture.
Ready to connect★ 419
- View details
phaser-gamedevSkillAI & models
Lets your agent build 2D browser games with Phaser 3 using scenes, physics, tilemaps and sprites.
Ready to connect★ 419
- View details
phpSkillAI & models
Gives your agent guidance for writing PHP code that follows PSR standards and includes PHPUnit tests.
Ready to connect★ 419
- View details
plant-seedSkillMedia
Lets your agent save a forward-looking idea as a seed for future feature design.
Ready to connect★ 419
- View details
public-web-deploySkillWeb & browsing
Lets your agent publish a public website, setting up DNS, web server, HTTPS, security hardening, and verification.
Ready to connect★ 419
- View details
python-quality-gateSkillAI & models
Lets your agent run Python code quality checks like linting, tests, type checking, and security scans in order.
Ready to connect★ 419
- View details
read-only-opsSkillAI & models
Lets your agent explore code, config, and state and produce reports without changing anything.
Ready to connect★ 419
- View details
reference-enrichmentSkillFiles & storage
Lets your agent check reference files for depth and generate missing domain-specific reference documents.
Ready to connect★ 419
- View details
repo-value-analysisSkillAI & models
Lets your agent analyze external code repositories for ideas and patterns you can adopt.
Ready to connect★ 419
- View details
roastSkillAI & models
Lets your agent critique your work through 5 HackerNews-style personas while checking claims.
Ready to connect★ 419
- View details
routing-table-updaterSkillAI & models
Lets your agent update /do routing tables so they stay correct as skills or agents change.
Ready to connect★ 419
- View details
sapcc-auditSkillAI & models
Lets your agent audit a Go repository for compliance with review standards.
Ready to connect★ 419
- View details
sapcc-reviewSkillAI & models
Lets your agent review Go code in SAP CC style using ten parallel specialist reviewers.
Ready to connect★ 419
- View details
series-plannerSkillAI & models
Lets your agent plan multi-part content series with structure, cross-linking, and publishing cadence.
Ready to connect★ 419
- View details
service-health-checkSkillMonitoring & ops
Lets your agent check whether services are healthy, validate endpoints, and audit CVE sources.
Ready to connect★ 419
- View details
shell-configSkillAI & models
Helps your agent set up and configure the Fish or Zsh shell, including PATH, completions, and plugins.
Ready to connect★ 419
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.
54,249 of the 54,680 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.