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
55,384 results · page 1186 of 1,847
- View details
agentcore-ops-reviewSkillCloud & infra
Lets your agent run operational review checks on your Amazon Bedrock setup.
Ready to connect★ 82
- View details
aiml-access-diagnosticsSkillCloud & infra
Lets your agent diagnose why Bedrock or SageMaker access is denied and pinpoint the failing permission.
Ready to connect★ 82
- View details
analytics-opensearch-expertiseSkillDatabases & data
Lets your agent check the health, performance, security, and cost of an Amazon OpenSearch domain.
Ready to connect★ 82
- View details
api-planSkillDev tools
Lets your agent apply a plan skill to update API contract specs, recording additions, changes, or removals of endpoints.
Ready to connect★ 82
- View details
api-reviewerSkillAI & models
Lets your agent review API contracts across OpenAPI, GraphQL, gRPC and more before implementation begins.
Ready to connect★ 82
- View details
api-writerSkillAI & models
Lets your agent write API contracts and interface specifications such as OpenAPI, GraphQL, or gRPC definitions.
Ready to connect★ 82
- View details
aresSkillCloud & infra
Lets your agent operate and debug the Ares red/blue attack platform, launching red ops, blue investigations, and reading reports.
Ready to connect★ 82
- View details
ares-debugSkillDatabases & data
Lets your agent diagnose stuck or broken Ares operations by checking live logs, historical logs, and traces.
Ready to connect★ 82
- View details
ares-grafanaSkillMonitoring & ops
Lets your agent check Grafana dashboards and Loki queries to monitor Ares operation health, errors, and restarts.
Ready to connect★ 82
- View details
attack-path-diversity-sweepSkillFiles & storage
Lets your agent run varied simulated attack exercises and compare coverage results against a baseline in a CSV.
Ready to connect★ 82
- View details
aws-health-eventsSkillCloud & infra
Lets your agent use an AWS Claude skill at the start of incident investigations to find root causes.
Ready to connect★ 82
- View details
aws-vpc-dns-investigationSkillCloud & infra
An aws claude skill that helps your agent investigate DNS resolution failures inside an AWS VPC.
Ready to connect★ 82
- View details
bauhaus-visualSkillMedia
Lets your agent turn your design intent into a ready-to-use image prompt in the Bauhaus visual style.
Ready to connect★ 82
- View details
bddSkillFiles & storage
Lets your agent advance BDD/TDD implementation inside a chosen feature file using red, green, and refactor steps.
Ready to connect★ 82
- View details
bedrock-adoption-readinessSkillCloud & infra
Lets your agent assess whether your Amazon Bedrock setup is ready for production, covering security, data retention, and capacity.
Ready to connect★ 82
- View details
bedrock-operation-reviewSkillCloud & infra
Lets your agent review your Amazon Bedrock setup and check it against AWS best practices.
Ready to connect★ 82
- View details
brand-icon-bannerSkillMedia
Lets your agent turn a design observation into an image prompt for a 3D app-icon banner with brand logo and text.
Ready to connect★ 82
- View details
brd-interviewerSkillAI & models
Lets your agent interview you step by step to turn vague business ideas into a clear business requirements document.
Ready to connect★ 82
- View details
clarify-over-specsSkillDev tools
Lets your agent scan a written spec for unclear requirements, ask you clarifying questions, and write the answers back into the spec.
Ready to connect★ 82
- View details
claude-gladiatorSkillAI & models
Lets your agent learn from its mistakes by observing failures and reflecting on them to improve over time.
Ready to connect★ 82
- View details
claude-historianSkillSearch
Lets your agent search its past conversation history before starting new research, planning, or debugging.
Ready to connect★ 82
- View details
claude-oracleSkillSearch
Lets your agent automatically search 17 sources for information before planning and after errors.
Ready to connect★ 82
- View details
claude-oratorSkillAI & models
Lets your agent score and rewrite your prompts to follow Anthropic's best practices.
Ready to connect★ 82
- View details
claude-praetorianSkillDocs & knowledge
Lets your agent remember important context across sessions by saving key details at high-impact moments.
Ready to connect★ 82
- View details
claude-vigilSkillFiles & storage
Lets your agent auto-save file checkpoints before risky changes so you can roll back if something goes wrong.
Ready to connect★ 82
- View details
craft-diorama-still-lifeSkillMedia
Lets your agent turn articles or product claims into skeuomorphic still-life image prompts, one object per statement.
Ready to connect★ 82
- View details
create-kr-patchSkillDev tools
Create a Claude skill that translates retro games into Korean, from ROM analysis to Hangul fonts and patch builds.
Ready to connect★ 82
- View details
crm-production-investigation-guidelinesSkillDatabases & data
Lets your agent investigate CRM production incidents using a crm claude skill with AWS observability tools.
Ready to connect★ 82
- View details
cyber-terminal-schematicSkillMedia
Turns article topics and tech concepts into image prompts styled like a neon green cyber terminal schematic.
Ready to connect★ 82
- View details
data-planSkillDev tools
Lets your agent update data truth spec files from a plan, adding, changing, or removing data definitions.
Ready to connect★ 82
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
55,384 of the 55,384 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 workspace 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.