Agent skill

Create Connector

by harness in harness/harness-skills

Generate Harness Connector YAML for integrations and create/test via MCP.

Apache-2.0Auto-check passedDevOps & Cloud

Install Create Connector

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

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

GitHub CLI
$ gh skill install harness/harness-skills create-connector --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-connector .claude/skills/create-connector && 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-connector
GitHub stars
115
Token cost
~2k tokens
SKILL.md length
282 words
Files
1
Skills in repo
64
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate Harness Connector YAML for integrations and create/test via MCP.

  • Works in 4 steps: Identify connector type - Determine what… → Generate YAML using the templates below,… → Create via MCP using harness_create with… → …
  • User says create connector
  • SKILL.md covers Instructions, Git Connectors, Cloud Connectors and Registry Connectors, plus 8 more sections
  • Reaches github.com and gitlab.com

What it does

Create Connector is an agent skill from harness/harness-skills. Generate Harness Connector YAML for integrations and create/test via MCP. Use when user says "create connector", "git connector", "aws connector", "docker connector", "cloud connector", or wants to connect Harness to external services.

Its SKILL.md is about 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, Containers and Git workflow. It works with Amazon Web Services, Model Context Protocol, Docker and Git. 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

  • User says create connector
  • Docker connector
  • Cloud connector
  • Wants to connect Harness to external services

Example prompts

  • “create connector”
  • “git connector”
  • “aws connector”
  • “/create-connector”

Requirements

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

Workflow steps

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

  1. Identify connector type - Determine what service to connect (Git provider, cloud provider, container registry, Kubernetes cluster)
  2. Generate YAML using the templates below, filling in credentials and endpoint details
  3. Create via MCP using harness_create with resource_type connector
  4. Test connection using harness_execute with action test_connection to verify

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

    Hosts in commands or code, which the agent is likely to contact:

    • github.com
    • gitlab.com
    • bitbucket.org
    • index.docker.io

    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 Connector loads about 2k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 282 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~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). 282 words, ~1,987 tokens.

Download SKILL.mdSave it as .claude/skills/create-connector/SKILL.md (or your agent's skills folder).
name
create-connector
description
Generate Harness Connector YAML for integrations and create/test via MCP. Use when user says "create connector", "git connector", "aws connector", "docker connector", "cloud connector", or wants to connect Harness to external services.
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 Connector

Generate Harness Connector YAML and create/test via MCP.

Instructions

  1. Identify connector type - Determine what service to connect (Git provider, cloud provider, container registry, Kubernetes cluster)
  2. Generate YAML using the templates below, filling in credentials and endpoint details
  3. Create via MCP using harness_create with resource_type connector
  4. Test connection using harness_execute with action test_connection to verify

Git Connectors

GitHub
yaml
connector:
  name: GitHub
  identifier: github_connector
  type: Github
  spec:
    url: https://github.com/myorg
    type: Account                    # Account or Repo
    authentication:
      type: Http
      spec:
        type: UsernameToken
        spec:
          username: myuser
          tokenRef: github_pat       # Secret reference
    apiAccess:
      type: Token
      spec:
        tokenRef: github_pat
    executeOnDelegate: false
GitLab
yaml
connector:
  name: GitLab
  identifier: gitlab_connector
  type: Gitlab
  spec:
    url: https://gitlab.com/myorg
    type: Account
    authentication:
      type: Http
      spec:
        type: UsernameToken
        spec:
          username: myuser
          tokenRef: gitlab_token
Bitbucket
yaml
connector:
  name: Bitbucket
  identifier: bitbucket_connector
  type: Bitbucket
  spec:
    url: https://bitbucket.org/myorg
    type: Account
    authentication:
      type: Http
      spec:
        type: UsernameToken
        spec:
          username: myuser
          tokenRef: bitbucket_app_password

Cloud Connectors

AWS
yaml
connector:
  name: AWS
  identifier: aws_connector
  type: Aws
  spec:
    credential:
      type: ManualConfig          # ManualConfig, InheritFromDelegate, Irsa, OidcAuthentication
      spec:
        accessKeyRef: aws_access_key
        secretKeyRef: aws_secret_key
    delegateSelectors: []         # Optional: target specific delegates
    executeOnDelegate: false
GCP
yaml
connector:
  name: GCP
  identifier: gcp_connector
  type: Gcp
  spec:
    credential:
      type: ManualConfig          # ManualConfig, InheritFromDelegate, OidcAuthentication
      spec:
        secretKeyRef: gcp_service_account_key
    executeOnDelegate: false
Azure
yaml
connector:
  name: Azure
  identifier: azure_connector
  type: Azure
  spec:
    credential:
      type: ManualConfig
      spec:
        auth:
          type: Secret
          spec:
            secretRef: azure_client_secret
        applicationId: <app_id>
        tenantId: <tenant_id>
    azureEnvironmentType: AZURE     # AZURE, AZURE_US_GOVERNMENT
    executeOnDelegate: false

Registry Connectors

Docker Hub
yaml
connector:
  name: Docker Hub
  identifier: dockerhub
  type: DockerRegistry
  spec:
    dockerRegistryUrl: https://index.docker.io/v2/
    providerType: DockerHub
    auth:
      type: UsernamePassword
      spec:
        username: myuser
        passwordRef: dockerhub_password
AWS ECR
yaml
connector:
  name: ECR
  identifier: ecr_connector
  type: Aws
  spec:
    credential:
      type: ManualConfig
      spec:
        accessKeyRef: aws_access_key
        secretKeyRef: aws_secret_key

Kubernetes Connector

yaml
connector:
  name: K8s Cluster
  identifier: k8s_connector
  type: K8sCluster
  spec:
    credential:
      type: ManualConfig          # ManualConfig, InheritFromDelegate
      spec:
        masterUrl: https://k8s-api.example.com
        auth:
          type: ServiceAccount
          spec:
            serviceAccountTokenRef: k8s_sa_token
            caCertRef: k8s_ca_cert

Helm Repository Connector

HTTP Helm Repo
yaml
connector:
  name: Helm Repo
  identifier: helm_repo
  type: HttpHelmRepo
  spec:
    helmRepoUrl: https://charts.example.com
    auth:
      type: UsernamePassword      # UsernamePassword or Anonymous
      spec:
        username: myuser
        passwordRef: helm_password
    delegateSelectors: []
OCI Helm Repo
yaml
connector:
  name: OCI Helm
  identifier: oci_helm
  type: OciHelmRepo
  spec:
    helmRepoUrl: oci://registry.example.com/charts
    auth:
      type: UsernamePassword
      spec:
        username: myuser
        passwordRef: oci_password

Artifact Repository Connectors

Nexus
yaml
connector:
  name: Nexus
  identifier: nexus_connector
  type: Nexus
  spec:
    nexusServerUrl: https://nexus.example.com
    version: "3.x"               # "2.x" or "3.x"
    auth:
      type: UsernamePassword
      spec:
        username: admin
        passwordRef: nexus_password
Artifactory
yaml
connector:
  name: Artifactory
  identifier: artifactory_connector
  type: Artifactory
  spec:
    artifactoryServerUrl: https://artifactory.example.com
    auth:
      type: UsernamePassword
      spec:
        username: admin
        passwordRef: artifactory_password

Ticketing Connectors

Jira
yaml
connector:
  name: Jira
  identifier: jira_connector
  type: Jira
  spec:
    jiraUrl: https://mycompany.atlassian.net
    auth:
      type: UsernamePassword
      spec:
        username: user@company.com
        passwordRef: jira_api_token
ServiceNow
yaml
connector:
  name: ServiceNow
  identifier: servicenow_connector
  type: ServiceNow
  spec:
    serviceNowUrl: https://mycompany.service-now.com
    auth:
      type: UsernamePassword
      spec:
        username: admin
        usernameRef: snow_username
        passwordRef: snow_password

Creating and Testing via MCP

Create connector:

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

Test connection:

Call MCP tool: harness_execute
Parameters:
  resource_type: "connector"
  action: "test_connection"
  resource_id: "<connector_identifier>"
  org_id: "<organization>"
  project_id: "<project>"

Browse available connector types:

Call MCP tool: harness_list
Parameters:
  resource_type: "connector_catalogue"

Examples

  • "Create a GitHub connector with PAT" - Github type with token auth
  • "Set up AWS connector" - Aws type with access key credentials
  • "Create Docker Hub connector" - DockerRegistry type
  • "Connect to my K8s cluster" - K8sCluster with service account
  • "Create a Helm repo connector" - HttpHelmRepo type for chart repositories
  • "Set up Jira connector" - Jira type for approval and ticketing integration
  • "Create Nexus connector" - Nexus type for artifact repository

Performance Notes

  • Always test the connection after creation using harness_execute with action test_connection.
  • Verify that referenced secrets exist before creating the connector.
  • For cloud connectors, confirm IAM permissions match the intended usage (read-only vs. read-write).

Troubleshooting

Connection Test Fails
  • Verify credentials/tokens are valid and not expired
  • Check network connectivity (delegate may need access)
  • Ensure proper IAM permissions for cloud connectors
Secret References
  • Secrets must exist before creating the connector
  • Use format: account.secret_name for account-level secrets
  • Use just secret_name for project-level secrets
Delegate Selectors
  • Use delegateSelectors to target connectors at specific delegates
  • Required when the service is only reachable from specific network locations
  • Match delegate tags exactly (case-sensitive)

© 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-connector of harness/harness-skills.

Open the folder on GitHubat commit c25faee

Compare with similar skills

Create Connector 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 Connector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Connector this skillharness/harness-skills115—~2kAutomated safety check: PassApache-2.0
Ksaildevantler-tech/ksail166—~1.1kAutomated safety check: PassCustom licence
Logfire Infrastructurepydantic/skills140—~1.8kAutomated safety check: PassMIT
Pluggedin Stack OpsVeriTeknik/pluggedin-app103—~1.3kAutomated safety check: NotesMIT
Tokf Runmpecan/tokf199—~571Automated safety check: PassMIT
Aspire DeploymentCommunityToolkit/Aspire629—~4.5kAutomated safety check: NotesMIT

Similar skills

  • 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
  • Logfire Infrastructure

    pydantic/skills

    Official

    Monitor hosts, Docker containers, Kubernetes clusters, database/queue/cache servers, and cloud-provider metrics with Pydantic Logfire — no application code required.

    140 GitHub stars~1.8k tokensUpdated 6 days ago
    DevOps & CloudAuto-check passed
  • Pluggedin Stack Ops

    VeriTeknik/pluggedin-app

    A skill your agent uses when deploying, restarting, verifying or rolling back the containerised plugged.in production stack, when the site returns 404 or 5xx after a deploy or git operation, or when…

    103 GitHub stars~1.3k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Tokf Run

    mpecan/tokf

    Compress verbose CLI output with tokf before returning results.

    199 GitHub stars~571 tokensUpdated 5 days ago
    DevOps & CloudAuto-check passed
  • Aspire Deployment

    CommunityToolkit/Aspire

    WORKFLOW SKILL — Deploy Aspire apps from AppHost models to Docker Compose, Kubernetes, Azure, AWS, or preview Radius.

    629 GitHub stars~4.5k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Performing Container Security Scanning With Trivy

    mukul975/Anthropic-Cybersecurity-Skills

    Runs Trivy across every target type it supports - container images, filesystems, Git repositories, and Kubernetes clusters - for OS and dependency vulnerabilities, IaC misconfiguration, exposed…

    34k GitHub stars~818 tokensUpdated 1 mo ago
    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 today
    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 today
    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 today
    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 today
    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 today
    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 today
    Auto-check passed

Categories

Questions about Create Connector

What does Create Connector do?

Generate Harness Connector YAML for integrations and create/test via MCP. Create Connector is an agent skill from harness/harness-skills. Generate Harness Connector YAML for integrations and create/test via MCP.

When should I use Create Connector?

Create Connector fits situations like: user says create connector; Docker connector; cloud connector; wants to connect Harness to external services.

How do I install Create Connector in Claude Code?

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

How do I install Create Connector in Codex?

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

Can I use Create Connector 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-connector -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-connector, .gemini/skills/create-connector, .github/skills/create-connector and .opencode/skills/create-connector in your project.

What does Create Connector need to run?

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

Does Create Connector access the network?

SKILL.md names 4 domains. In commands or code: github.com, gitlab.com, bitbucket.org and index.docker.io; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Create Connector 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 Connector use?

Create Connector 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 Connector use?

About 2k tokens (SKILL.md is roughly 7.9k 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 Connector?

Skills that share tags, products or a category with Create Connector: Ksail (devantler-tech/ksail, 166 stars), Logfire Infrastructure (pydantic/skills, 140 stars), Pluggedin Stack Ops (VeriTeknik/pluggedin-app, 103 stars) and Tokf Run (mpecan/tokf, 199 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Connector?

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.