Agent skill

Create Service

by harness in harness/harness-skills

Generate Harness Service YAML for deployable workloads and create via MCP.

Apache-2.0Auto-check passedDevOps & Cloud

Install Create Service

skills CLI
$ npx skills add harness/harness-skills --skill create-service -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install harness/harness-skills create-service --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/harness/harness-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/create-service .claude/skills/create-service && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
create-service
GitHub stars
115
Token cost
~2.2k tokens
SKILL.md length
346 words
Files
1
Skills in repo
64
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate Harness Service YAML for deployable workloads and create via MCP.

  • Works in 5 steps: Detect service type from codebase (if… → Detect artifact source - Match… → Confirm with user - Present detected… → …
  • Asked to create a service
  • SKILL.md covers Instructions, Service Structure, Deployment Types and Artifact Source Types, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Create Service is an agent skill from harness/harness-skills. Generate Harness Service YAML for deployable workloads and create via MCP. Supports Kubernetes, Helm, ECS, Serverless, SSH, and WinRm deployment types with artifact sources from Docker Hub, ECR, GCR, ACR, Nexus, and S3. Use when asked to create a service, define a Kubernetes service, set up a Helm chart deployment, configure an ECS service, or define what gets deployed. Trigger phrases: create service, service definition, Kubernetes service, Helm service, ECS service, deployment service, artifact source.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires Harness MCP v2 server (harness-mcp-v2)

It sits in DevOps & Cloud, covering Container orchestration. It works with Kubernetes, Model Context Protocol, Docker and Helm. The repository describes itself as: A collection of structured AI agent skills that enable Claude Code, Cursor, GitHub Copilot, and other AI coding assistants to create, operate, debug, and govern Harness CI/CD… The licence is Apache-2.0.

When your agent uses it

  • Asked to create a service
  • Define a Kubernetes service
  • Set up a Helm chart deployment
  • Configure an ECS service

Example prompts

  • “/create-service”

Requirements

  • Docker
  • Compatibility (from SKILL.md): Requires Harness MCP v2 server (harness-mcp-v2)

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Detect service type from codebase (if source code is available) - Scan the project for deployment manifests to auto-select the correct…
  2. Detect artifact source - Match Dockerfile registry references to artifact source type
  3. Confirm with user - Present detected service type, manifest type, and artifact source for confirmation
  4. Generate YAML following the structure below
  5. Create via MCP using harness_create with resource_type service

What it can do on your machine

Read from SKILL.md and the folder at commit c25faee. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires Harness MCP v2 server (harness-mcp-v2)

    From compatibility in the SKILL.md frontmatter.

Context cost

Create Service loads about 2.2k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 346 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from harness/harness-skills at commit c25faee, republished under its Apache-2.0 licence (© harness). 346 words, ~2,168 tokens.

Download SKILL.mdSave it as .claude/skills/create-service/SKILL.md (or your agent's skills folder).
name
create-service
description
Generate Harness Service YAML for deployable workloads and create via MCP. Supports Kubernetes, Helm, ECS, Serverless, SSH, and WinRm deployment types with artifact sources from Docker Hub, ECR, GCR, ACR, Nexus, and S3. Use when asked to create a service, define a Kubernetes service, set up a Helm chart deployment, configure an ECS service, or define what gets deployed. Trigger phrases: create service, service definition, Kubernetes service, Helm service, ECS service, deployment service, artifact source.
compatibility
Requires Harness MCP v2 server (harness-mcp-v2)
metadata.author
Harness
metadata.version
2.0.0
metadata.mcp-server
harness-mcp-v2
license
Apache-2.0

Create Service

Generate Harness Service YAML and push to Harness via MCP.

Instructions

  1. Detect service type from codebase (if source code is available) - Scan the project for deployment manifests to auto-select the correct serviceDefinition.type and manifest configuration:
    • k8s/, kubernetes/, manifests/ with YAML files → Kubernetes with K8sManifest
    • kustomization.yaml → Kubernetes with Kustomize
    • Chart.yaml, charts/, helm/ → NativeHelm with HelmChart
    • task-definition.json → ECS with EcsTaskDefinition
    • serverless.yml / template.yaml (SAM) → ServerlessAwsLambda
    • function.json (Azure) → AzureWebApp
    • .NET + Windows → WinRm
    • Traditional app (JAR/WAR) without containers → Ssh
    • See create-pipeline/references/codebase-analysis.md Step 4 for the full decision tree
  2. Detect artifact source - Match Dockerfile registry references to artifact source type:
    • Docker Hub → DockerRegistry
    • *.dkr.ecr.*.amazonaws.com → Ecr
    • gcr.io / *-docker.pkg.dev → Gcr
    • *.azurecr.io → Acr
  3. Confirm with user - Present detected service type, manifest type, and artifact source for confirmation
  4. Generate YAML following the structure below
  5. Create via MCP using harness_create with resource_type service

Service Structure

yaml
service:
  name: My Service
  identifier: my_service
  orgIdentifier: default
  projectIdentifier: my_project
  serviceDefinition:
    type: Kubernetes        # Kubernetes, NativeHelm, ECS, ServerlessAwsLambda, Ssh, WinRm, AzureWebApp, AzureFunction, CustomDeployment
    spec:
      artifacts:
        primary:
          primaryArtifactRef: docker_image
          sources:
            - identifier: docker_image
              type: DockerRegistry
              spec:
                connectorRef: dockerhub
                imagePath: myorg/myimage
                tag: <+input>
      manifests:
        - manifest:
            identifier: k8s_manifest
            type: K8sManifest
            spec:
              store:
                type: Github
                spec:
                  connectorRef: github_connector
                  repoName: my-manifests
                  branch: main
                  paths: [manifests/]
      variables:
        - name: replicas
          type: String
          value: "3"

Deployment Types

Kubernetes Service
yaml
serviceDefinition:
  type: Kubernetes
  spec:
    artifacts:
      primary:
        primaryArtifactRef: main_image
        sources:
          - identifier: main_image
            type: DockerRegistry
            spec:
              connectorRef: dockerhub
              imagePath: myorg/api
              tag: <+input>
    manifests:
      - manifest:
          identifier: manifests
          type: K8sManifest
          spec:
            store:
              type: Github
              spec:
                connectorRef: github
                repoName: k8s-manifests
                branch: main
                paths: [deploy/]
Helm Service
yaml
serviceDefinition:
  type: NativeHelm
  spec:
    artifacts:
      primary:
        primaryArtifactRef: chart
        sources:
          - identifier: chart
            type: DockerRegistry
            spec:
              connectorRef: dockerhub
              imagePath: myorg/api
              tag: <+input>
    manifests:
      - manifest:
          identifier: helm_chart
          type: HelmChart
          spec:
            store:
              type: Http
              spec:
                connectorRef: helm_repo
            chartName: my-chart
            chartVersion: <+input>
            helmVersion: V3
Kustomize Service
yaml
serviceDefinition:
  type: Kubernetes
  spec:
    artifacts:
      primary:
        primaryArtifactRef: main_image
        sources:
          - identifier: main_image
            type: DockerRegistry
            spec:
              connectorRef: dockerhub
              imagePath: myorg/api
              tag: <+input>
    manifests:
      - manifest:
          identifier: kustomize
          type: Kustomize
          spec:
            store:
              type: Github
              spec:
                connectorRef: github
                repoName: k8s-config
                branch: main
                folderPath: overlays/production
            pluginPath: ""
ECS Service
yaml
serviceDefinition:
  type: ECS
  spec:
    artifacts:
      primary:
        primaryArtifactRef: ecr_image
        sources:
          - identifier: ecr_image
            type: Ecr
            spec:
              connectorRef: aws_connector
              region: us-east-1
              imagePath: my-image
              tag: <+input>
    manifests:
      - manifest:
          identifier: task_def
          type: EcsTaskDefinition
          spec:
            store:
              type: Github
              spec:
                connectorRef: github
                repoName: ecs-config
                branch: main
                paths: [task-definition.json]
Serverless Lambda Service
yaml
serviceDefinition:
  type: ServerlessAwsLambda
  spec:
    artifacts:
      primary:
        primaryArtifactRef: s3_artifact
        sources:
          - identifier: s3_artifact
            type: AmazonS3
            spec:
              connectorRef: aws_connector
              region: us-east-1
              bucketName: my-deployments
              filePath: serverless-app.zip
    manifests:
      - manifest:
          identifier: serverless_manifest
          type: ServerlessAwsLambda
          spec:
            store:
              type: Github
              spec:
                connectorRef: github
                repoName: serverless-config
                branch: main
                paths: [serverless.yml]

Artifact Source Types

  • DockerRegistry - Docker Hub (connectorRef, imagePath, tag)
  • Ecr - AWS ECR (connectorRef, region, imagePath, tag)
  • Gcr - Google GCR (connectorRef, registryHostname, imagePath, tag)
  • GoogleArtifactRegistry - Google Artifact Registry (connectorRef, region, repositoryName, package, version)
  • Acr - Azure ACR (connectorRef, subscriptionId, registry, repository, tag)
  • ArtifactoryRegistry - JFrog Artifactory (connectorRef, repository, artifactPath, repositoryFormat, tag)
  • Nexus3Registry - Nexus (connectorRef, repository, artifactPath, repositoryFormat, tag)
  • GithubPackageRegistry - GitHub Packages (connectorRef, packageType, org, packageName, version)
  • AmazonS3 - S3 (connectorRef, region, bucketName, filePath)
  • GoogleCloudStorage - GCS (connectorRef, project, bucket, artifactPath)
  • CustomArtifact - Custom source (scripts, delegateSelectors, version)

Creating via MCP

Call MCP tool: harness_create
Parameters:
  resource_type: "service"
  org_id: "<organization>"
  project_id: "<project>"
  body: <service YAML>

List existing services:

Call MCP tool: harness_list
Parameters:
  resource_type: "service"
  org_id: "<organization>"
  project_id: "<project>"

Examples

  • "Create a K8s service with Docker Hub artifact" - Kubernetes type with DockerRegistry source
  • "Create a Helm service" - NativeHelm type with HelmChart manifest
  • "Create an ECS service with ECR" - ECS type with Ecr artifact source

Performance Notes

  • Verify that referenced connectors exist before creating the service definition.
  • Ensure the deployment type matches the infrastructure type that will be used in the pipeline.
  • For artifact sources, confirm the image path and registry are accessible.
  • Quality of service configuration is more important than speed.

Troubleshooting

  • CONNECTOR_NOT_FOUND - Create connector first or fix connectorRef
  • DUPLICATE_IDENTIFIER - Service exists; use harness_update
  • Artifact tag <+input> means the tag is provided at runtime

© harness, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/create-service of harness/harness-skills.

Open the folder on GitHubat commit c25faee

Compare with similar skills

Create Service next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Create Service compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Service this skillharness/harness-skills115—~2.2kAutomated safety check: PassApache-2.0
Ama Logs Update Charts Release Notesmicrosoft/Docker-Provider173—~2.6kAutomated safety check: PassCustom licence
Ksaildevantler-tech/ksail166—~1.1kAutomated safety check: PassCustom licence
Vss Deploy Helmopen-edge-platform/edge-ai-libraries168—~3.8kAutomated safety check: PassApache-2.0
Security Review Skill For Dockerxwtro0tk1t-cloud/harness265—~2.8kAutomated safety check: WarnNone
Kubernetes Deploymentaiskillstore/marketplace4305 repos~839Automated safety check: PassNone

Similar skills

  • Ama Logs Update Charts Release Notes

    microsoft/Docker-Provider

    Official

    Prepare an ama-logs release PR: bump the image tag (X.Y.Z) across Helm charts, manifests, and Dockerfiles, and add a formatted ReleaseNotes.md entry.

    173 GitHub stars~2.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Ksail

    devantler-tech/ksail

    Use the ksail CLI to spin up and manage Kubernetes clusters (Kind/K3d/Talos/vCluster/KWOK — local via Docker; EKS — cloud via AWS) and GitOps workloads declaratively.

    166 GitHub stars~1.1k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Vss Deploy Helm

    open-edge-platform/edge-ai-libraries

    A skill your agent uses whenever a developer needs to deploy VSS to Kubernetes, helm install VSS, configure values.yaml for VSS, or run VSS on k8s with GPU/vLLM for the…

    168 GitHub stars~3.8k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Security Review Skill For Docker

    xwtro0tk1t-cloud/harness

    审计 Docker/容器部署安全。检测 Dockerfile、docker-compose.yml、Kubernetes manifests 中的安全问题:特权容器、root 运行、敏感挂载、资源无限制、密钥泄露、Base Image 不合规、网络暴露等。当审计容器配置、Docker 安全、K8s 部署安全、或检查基础设施安全时使用。支持…

    265 GitHub stars~2.8k tokensUpdated 5 mo ago
    DevOps & CloudAuto-check: warnings
  • Kubernetes Deployment

    aiskillstore/marketplace

    Kubernetes deployment workflow for container orchestration, Helm charts, service mesh, and production-ready K8s configurations.

    430 GitHub starsUsed in 5 repos~839 tokens
    DevOps & CloudAuto-check passed
  • Kubernetes Ops

    CoWork-OS/CoWork-OS

    Kubernetes cluster operations: kubectl commands, manifest generation, Helm charts, RBAC, debugging, and deployment strategies.

    473 GitHub stars~445 tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from harness/harness-skills

All 64 skills in this repo
  • Audit Report

    harness/harness-skills

    Generate audit reports and compliance trails using Harness audit trail data via MCP v2 tools.

    115 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Chaos Dr Test

    harness/harness-skills

    A skill your agent uses when working with Chaos Engineering steps inside a Harness pipeline.

    115 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Chaos Experiment

    harness/harness-skills

    A skill your agent uses when the user asks to create, edit, update, design, or configure a Harness Chaos Experiment — including faults, probes, actions, experiment YAML, fault injection, pod-delete…

    115 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Cleanup Feature Flags

    harness/harness-skills

    Remove a launched Harness FME feature flag from application code, keeping the treatment FME serves today, and open a pull request.

    115 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Configure Repo Scan

    harness/harness-skills

    Configure code scanning in Harness pipelines using STO security scanners.

    115 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Create Agent Template

    harness/harness-skills

    Generate Harness Agent Template files for AI-powered automation agents.

    115 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Create Service

What does Create Service do?

Generate Harness Service YAML for deployable workloads and create via MCP. Create Service is an agent skill from harness/harness-skills. Generate Harness Service YAML for deployable workloads and create via MCP.

When should I use Create Service?

Create Service fits situations like: asked to create a service; define a Kubernetes service; set up a Helm chart deployment; configure an ECS service.

How do I install Create Service in Claude Code?

Run `npx skills add harness/harness-skills --skill create-service -a claude-code`. Or copy the skill folder (skills/create-service in harness/harness-skills) into .claude/skills/create-service in your project. Claude Code loads it when a task matches its description.

How do I install Create Service in Codex?

Run `npx skills add harness/harness-skills --skill create-service -a codex`. Or copy the skill folder (skills/create-service in harness/harness-skills) into .agents/skills/create-service in your project. Codex loads it when a task matches its description.

Can I use Create Service in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add harness/harness-skills --skill create-service -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-service, .gemini/skills/create-service, .github/skills/create-service and .opencode/skills/create-service in your project.

What does Create Service need to run?

SKILL.md names no scripts, command-line tools or credentials: Create Service is instructions for the agent only. Our summary lists: Docker. Compatibility (from SKILL.md): Requires Harness MCP v2 server (harness-mcp-v2).

Does Create Service access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Create Service safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Create Service use?

Create Service is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Create Service use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Create Service?

Skills that share tags, products or a category with Create Service: Ama Logs Update Charts Release Notes (microsoft/Docker-Provider, 173 stars), Ksail (devantler-tech/ksail, 166 stars), Vss Deploy Helm (open-edge-platform/edge-ai-libraries, 168 stars) and Security Review Skill For Docker (xwtro0tk1t-cloud/harness, 265 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Service?

harness (a GitHub organization) maintains it in harness/harness-skills, which has 115 GitHub stars. The repository holds 64 skills in this directory. The repository was last updated on October 6, 2026.

Source: harness/harness-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.