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
65,240 results · page 1361 of 2,175
- View details
catel-mvvmSkillDev tools
Checks your .NET/C# WPF code against MVVM best practices for the solution or project.
Ready to connect★ 114
- View details
chaos-dr-testSkillDev tools
Lets your agent add and edit chaos engineering steps, fault injections, and probes in Harness pipelines.
Ready to connect★ 112
- View details
chatgpt-searchSkillSearch
Lets your agent send a query to ChatGPT in Chrome and extract the full response as structured data.
Ready to connect★ 114
- View details
cline-fix-volatile-msgSkillAI & models
Checks and tunes Anthropic prompt caching in Cline, verifying the cache ladder and adjusting breakpoints and TTL.
Ready to connect★ 113
- View details
cline-openai-cache-keySkillProductivity
Lets your agent add a stable cache key to OpenAI requests so prompt caching works and responses cost less.
Ready to connect★ 113
- View details
cline-pin-timestampSkillAI & models
Pins a fixed timestamp in Cline's system prompt so the prompt cache stays valid between requests.
Ready to connect★ 113
- View details
commit-msgSkillFiles & storage
Writes clear git commit messages based on your current code changes.
Ready to connect★ 114
- View details
configure-agent-pr-attestationSkillAI & models
Lets your agent set up and fix signed pull-request checks that prove AI-made changes were verified.
Ready to connect★ 112
- View details
configure-container-scanSkillCloud & infra
Lets your agent add container image security scanning steps to existing Harness pipelines.
Ready to connect★ 112
- View details
configure-repo-scanSkillSecurity
Lets your agent add code security scanning steps to Harness CI pipelines and pick suitable scanners.
Ready to connect★ 112
- View details
configure-secret-scanSkillSecurity
Lets your agent add secret scanning steps to Harness pipelines to find exposed API keys and credentials.
Ready to connect★ 112
- View details
continue-enable-defaultsSkillAI & models
Lets your agent switch Continue's settings so prompt caching is on by default instead of off.
Ready to connect★ 113
- View details
continue-fix-volatile-msgSkillAI & models
Lets your agent verify and enable Anthropic prompt-cache ladder settings with TTL coverage.
Ready to connect★ 113
- View details
continue-gemini-explicitSkillAI & models
Adds explicit caching for Gemini sessions that exceed the minimum token threshold.
Ready to connect★ 113
- View details
create-agent-templateSkillFiles & storage
Lets your agent create Claude skill-style Harness agent templates with metadata, pipeline YAML, and wiki files.
Ready to connect★ 112
- View details
create-connectorSkillCloud & infra
Lets your agent create claude skill files that generate Harness connector YAML for AWS, Git, Docker, and other services.
Ready to connect★ 112
- View details
create-environmentSkillCloud & infra
Lets your agent create claude skill YAML for Harness deployment environments across dev, staging, and production.
Ready to connect★ 112
- View details
create-infrastructureSkillCloud & infra
Lets your agent create claude skill YAML that defines Harness infrastructure deployment targets for where workloads run.
Ready to connect★ 112
- View details
create-pipelineSkillCloud & infra
Lets your agent create Claude skill pipelines by generating Harness CI/CD YAML for build, test, and deploy workflows.
Ready to connect★ 112
- View details
create-pipeline-v1SkillDev tools
Lets your agent write Harness pipeline YAML files for CI and CD stages using a simplified syntax.
Ready to connect★ 112
- View details
create-policySkillCloud & infra
Lets your agent write OPA governance policies that enforce compliance rules on Harness pipelines, services, and more.
Ready to connect★ 112
- View details
create-sbomSkillCloud & infra
Lets your agent add a software bill of materials (SBOM) generation step to an existing Harness pipeline.
Ready to connect★ 112
- View details
create-secretSkillCloud & infra
Lets your agent create and manage secrets in Harness, including text, files, SSH keys and Windows credentials.
Ready to connect★ 112
- View details
create-templateSkillDev tools
Lets your agent create Claude skill YAML templates for reusable Harness pipeline steps, stages, and pipelines.
Ready to connect★ 112
- View details
create-triggerSkillProductivity
Lets your agent create a Claude skill that generates Harness trigger YAML so pipelines run automatically.
Ready to connect★ 112
- View details
csharp-asyncSkillDev tools
Lets your agent follow best practices when writing async code in C#.
Ready to connect★ 114
- View details
dbops-changesetSkillDatabases & data
Lets your agent generate Liquibase database change scripts and commit them after your review.
Ready to connect★ 112
- View details
debug-pipelineSkillMonitoring & ops
Lets your agent analyze pipeline executions to find failures, slow steps, and bottlenecks in a structured report.
Ready to connect★ 112
- View details
deployment-readinessSkillCloud & infra
Lets your agent check if a service is ready to deploy by running readiness checks and comparing environments.
Ready to connect★ 112
- View details
dora-metricsSkillCloud & infra
Lets your agent generate DORA metrics reports like deployment frequency, lead time, change failure rate, and MTTR.
Ready to connect★ 112
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 how to install
- Best Claude skills for humanizer
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.
65,240 of the 65,240 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.