[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75JJKRM1TH6HKP2CYJW7Y5D":3,"skill-same:01M75JJKRM1TH6HKP2CYJW7Y5D":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":13,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M75JJKRM1TH6HKP2CYJW7Y5D","create-pipeline",null,"Generate Harness v0 Pipeline YAML for CI\u002FCD workflows and create them via MCP. Supports CI stages (build, test, Docker push), CD stages (Kubernetes, Helm, ECS, serverless), approval gates, parallel execution, matrix strategies, and failure rollback. Use when asked to create a pipeline, build pipeline, deployment pipeline, CI\u002FCD workflow, or set up Harness pipelines. Do NOT use for v1 simplified pipelines (use create-pipeline-v1). Trigger phrases: create pipeline, build pipeline, deployment pipeline, CI\u002FCD, Harness pipeline, Kubernetes deploy pipeline.","AdmiralGallade\u002Fharness-repository","AdmiralGallade","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F59243621?v=4","01M759AG0891RDPWNGJBX1Y2TG","01M759AG10MS924J53ZWJ60AEC",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fcreate-pipeline\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: create-pipeline\ndescription: >-\n  Generate Harness v0 Pipeline YAML for CI\u002FCD workflows and create them via MCP. Supports CI stages\n  (build, test, Docker push), CD stages (Kubernetes, Helm, ECS, serverless), approval gates, parallel\n  execution, matrix strategies, and failure rollback. Use when asked to create a pipeline, build pipeline,\n  deployment pipeline, CI\u002FCD workflow, or set up Harness pipelines. Do NOT use for v1 simplified pipelines\n  (use create-pipeline-v1). Trigger phrases: create pipeline, build pipeline, deployment pipeline, CI\u002FCD,\n  Harness pipeline, Kubernetes deploy pipeline.\nmetadata:\n  author: Harness\n  version: 2.2.0\n  mcp-server: harness-mcp-v2\nlicense: Apache-2.0\ncompatibility: Requires Harness MCP v2 server (harness-mcp-v2)\n---\n\n# Create Pipeline\n\nGenerate Harness v0 Pipeline YAML and optionally push to Harness via MCP.\n\n## Instructions\n\n1. **Analyze codebase** (if source code is available) - Scan the project to auto-detect language, build tools, test frameworks, containerization, deployment manifests, and target infrastructure. Use the detection tables and decision tree in `references\u002Fcodebase-analysis.md` to determine:\n   - Language and runtime version (package.json → Node.js, go.mod → Go, pom.xml → Java, etc.)\n   - Build commands and base images\n   - Test framework and report format (Jest → JUnit, pytest → JUnit XML, etc.)\n   - Linter and formatter (ESLint, Prettier, Ruff, etc.)\n   - Dockerfile presence and registry type (Docker Hub, ECR, GCR, ACR)\n   - Deployment manifests → Harness service\u002Fdeployment type (k8s manifests → Kubernetes, Chart.yaml → NativeHelm, task-definition.json → ECS, serverless.yml → ServerlessAwsLambda)\n   - Existing CI\u002FCD configs for migration (GitHub Actions, Jenkins, GitLab CI, etc.)\n2. **Clarify requirements** - Confirm detected settings with the user. **Ask about anything that couldn't be auto-detected** — do not guess or use placeholders. If the user's request is ambiguous, ask before generating YAML. Examples of what to ask when missing:\n   - **Deployment target \u002F infrastructure:** region (e.g. us-east-1), cluster name or ID, account ID (e.g. AWS account for ECR\u002FECS)\n   - **Registry:** which registry (Docker Hub, ECR, GCR, ACR), registry identifier\u002FURL, repo path\n   - **Cloud provider:** which account, region, and resource identifiers for connectors\u002Finfrastructure\n   - **Approval gates, notification channels** if relevant\n   **Critical rule:** Never hardcode placeholder values (e.g. `123456789012`, `us-east-1`, `my-cluster`) for deployment target, region, registry, or cluster when the user did not specify them — ask the user instead. If the user did not specify region, account ID, cluster, or registry (e.g. \"deploys to ECS\" with no region or cluster), ask the user for those values before generating YAML.\n3. **Select native steps** - Always prefer Harness native steps over `Run` or `ShellScript` steps. Consult `references\u002Fnative-steps.md` for the full mapping. Key rules:\n   - Docker build\u002Fpush → use `BuildAndPushDockerRegistry` \u002F `BuildAndPushECR` \u002F `BuildAndPushGCR` \u002F `BuildAndPushACR` (never `Run: docker build && docker push`)\n   - K8s deploy → use `K8sRollingDeploy` \u002F `K8sBlueGreenDeploy` \u002F `K8sCanaryDeploy` (never `Run: kubectl apply`)\n   - Helm deploy → use `HelmDeploy` (never `Run: helm upgrade --install`)\n   - ECS deploy → use `EcsRollingDeploy` (never `Run: aws ecs update-service`)\n   - Terraform → use `TerraformPlan` \u002F `TerraformApply` (never `Run: terraform apply`)\n   - Security scanning → use native STO steps (`AquaTrivy`, `Snyk`, `Sonarqube`, `Semgrep`, etc.)\n   - Uploads → use `S3Upload` \u002F `GCSUpload` (never `Run: aws s3 cp`)\n   - Approvals → use `HarnessApproval` \u002F `JiraApproval` (never polling scripts)\n   - Ticketing → use `JiraCreate` \u002F `ServiceNowCreate` (never `Run: curl`)\n   - Use `Run` steps only for custom build\u002Ftest\u002Flint commands with no native equivalent\n   - **Test steps:** Any Run step that runs unit or integration tests must include a `reports` block (e.g. `type: JUnit`, `spec.paths`) so Harness can capture results; see `references\u002Fcodebase-analysis.md` for framework → report path.\n4. **Generate valid YAML** following the structure below, using the detected build\u002Ftest\u002Fdeploy commands. **Validation rules:** (a) Stage names must match `^[a-zA-Z_0-9-.][-0-9a-zA-Z_\\\\s.]{0,127}$` — use only letters, numbers, spaces, hyphens, underscores, or periods (no commas). (b) Every CI and CD stage must include a `failureStrategies` array (Approval stages do not require one). For CI use `MarkAsFailure` (never `Ignore` — it hides failures); for CD use `StageRollback`.\n5. **Optionally create via MCP** — First verify the project exists (see \"Creating via MCP\" section below), then use `harness_create` with resource_type `pipeline` and `body: { yamlPipeline: \"\u003CYAML string>\" }`\n\n## Pipeline Structure\n\n```yaml\npipeline:\n  identifier: my_pipeline       # ^[a-zA-Z_][0-9a-zA-Z_]{0,127}$\n  name: My Pipeline\n  orgIdentifier: default\n  projectIdentifier: my_project\n  tags: {}\n  properties:\n    ci:\n      codebase:                  # Required for CI stages\n        connectorRef: github_connector\n        repoName: my-repo\n        build:\n          type: branch\n          spec:\n            branch: \u003C+trigger.branch>\n  stages:\n    - stage: ...\n```\n\n## Stage Types\n\n### CI Stage (type: CI)\n\n```yaml\n- stage:\n    identifier: build\n    name: Build\n    type: CI\n    spec:\n      cloneCodebase: true\n      platform:\n        os: Linux\n        arch: Amd64\n      runtime:\n        type: Cloud    # Cloud, Kubernetes, VM, Docker\n        spec: {}\n      execution:\n        steps:\n          - step: ...\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: MarkAsFailure\n```\n\n### CD Stage (type: Deployment)\n\n```yaml\n- stage:\n    identifier: deploy\n    name: Deploy\n    type: Deployment\n    spec:\n      deploymentType: Kubernetes  # Kubernetes, NativeHelm, ECS, ServerlessAwsLambda, Ssh, WinRm, AzureWebApp\n      service:\n        serviceRef: my_service\n      environment:\n        environmentRef: dev\n        infrastructureDefinitions:\n          - identifier: k8s_dev\n      execution:\n        steps:\n          - step: ...\n        rollbackSteps:\n          - step: ...\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: StageRollback\n```\n\n### Approval Stage (type: Approval)\n\n`HarnessApproval` requires `approvers.disallowPipelineExecutor` (required by the API). Set it to `true` so the pipeline executor cannot approve their own run; omit it and the API returns \"disallowPipelineExecutor: is missing but it is required\".\n\n```yaml\n- stage:\n    identifier: approval\n    name: Approval\n    type: Approval\n    spec:\n      execution:\n        steps:\n          - step:\n              identifier: approve\n              name: Approve\n              type: HarnessApproval\n              spec:\n                approvalMessage: \"Please review and approve\"\n                approvers:\n                  userGroups: [prod_approvers]\n                  minimumCount: 1\n                  disallowPipelineExecutor: true\n                includePipelineExecutionHistory: true\n              timeout: 1d\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: Abort\n```\n\n## Common Step Types\n\n### Run Step\n\n```yaml\n- step:\n    identifier: run_tests\n    name: Run Tests\n    type: Run\n    spec:\n      shell: Bash          # Sh, Bash, Powershell, Pwsh, Python\n      command: |\n        npm ci\n        npm test\n      envVariables:\n        NODE_ENV: test\n      reports:\n        type: JUnit\n        spec:\n          paths: [\"junit.xml\"]\n```\n\n### Build and Push Docker\n```yaml\n- step:\n    identifier: docker_push\n    name: Build and Push\n    type: BuildAndPushDockerRegistry\n    spec:\n      connectorRef: dockerhub\n      repo: myorg\u002Fmyimage\n      tags: [latest, \u003C+pipeline.sequenceId>]\n      dockerfile: Dockerfile\n```\n\n### K8s Rolling Deploy\n```yaml\n- step:\n    identifier: rollout\n    name: Rollout\n    type: K8sRollingDeploy\n    spec:\n      skipDryRun: false\n    timeout: 10m\n```\n\n### K8s Rolling Rollback\n```yaml\n- step:\n    identifier: rollback\n    name: Rollback\n    type: K8sRollingRollback\n    spec: {}\n    timeout: 10m\n```\n\nFor the complete catalog of 300+ native step types (cloud deployments, security scanners, IaC, ticketing, approvals, GitOps, and more), consult `references\u002Fnative-steps.md`. Always check this reference before using a `Run` step.\n\n## Variables and Expressions\n\n```yaml\npipeline:\n  variables:\n    - name: env\n      type: String\n      default: dev\n    - name: api_key\n      type: Secret\n      value: \u003C+secrets.getValue(\"api_key\")>\n```\n\nCommon expressions:\n- `\u003C+pipeline.variables.env>` - Pipeline variable\n- `\u003C+stage.variables.VAR>` - Stage variable\n- `\u003C+steps.step_id.output.outputVariables.VAR>` - Step output\n- `\u003C+trigger.branch>`, `\u003C+trigger.commitSha>` - Trigger info\n- `\u003C+secrets.getValue(\"name\")>` - Secret reference\n- `\u003C+pipeline.sequenceId>` - Build number\n\n## Parallel Execution\n\n```yaml\n# Parallel steps\n- parallel:\n    - step: ...\n    - step: ...\n\n# Parallel stages\nstages:\n  - parallel:\n      - stage: ...\n      - stage: ...\n```\n\n## Failure Strategies\n\n```yaml\nfailureStrategies:\n  - onFailure:\n      errors: [AllErrors]     # AllErrors, Timeout, Authentication, Connectivity\n      action:\n        type: StageRollback   # Ignore, Retry, MarkAsSuccess, Abort, StageRollback, PipelineRollback\n```\n\n## Conditional Execution\n\n```yaml\n- stage:\n    when:\n      pipelineStatus: Success\n      condition: \u003C+pipeline.variables.deploy> == \"true\"\n```\n\n## Matrix Strategy\n\n**Placement:** `strategy` must be at the **stage level**, as a **sibling of `spec`**, not inside `spec`. If you put `strategy` under `spec`, the matrix will not be applied and the UI will not show matrix iterations.\n\nReference matrix values in steps with `\u003C+stage.matrix.TAG>` (e.g. `\u003C+stage.matrix.python_version>`). Use hyphen-free dimension names (e.g. `python_version` not `python-version`).\n\n```yaml\n- stage:\n    identifier: test_matrix\n    name: Test Matrix\n    type: CI\n    spec:\n      cloneCodebase: true\n      platform:\n        os: Linux\n        arch: Amd64\n      runtime:\n        type: Cloud\n        spec: {}\n      execution:\n        steps:\n          - step:\n              type: Run\n              spec:\n                image: node:\u003C+stage.matrix.node_version>\n                command: npm test\n    strategy:\n      matrix:\n        node_version: [\"16\", \"18\", \"20\"]\n        os: [linux, macos]\n      maxConcurrency: 3\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: Abort\n```\n\n## Creating via MCP\n\nAfter generating the YAML, create it in Harness:\n\n1. **Verify the project exists** — List projects with `harness_list` (resource_type: `project`, org_id) to confirm. If the project does not exist, create it first with `harness_create` (resource_type: `project`, body: `{ identifier, name }`) or ask the user.\n2. **Create the pipeline** — Use `harness_create` with the pipeline YAML serialized as a **`yamlPipeline`** string in the body. Do not pass a nested JSON `pipeline` object; it causes serialization errors.\n\n```\nCall MCP tool: harness_create\nParameters:\n  resource_type: \"pipeline\"\n  org_id: \"\u003Corganization>\"\n  project_id: \"\u003Cproject>\"\n  body: { yamlPipeline: \"\u003Cfull pipeline YAML string, including 'pipeline:' root key>\" }\n```\n\n**Example body** (abbreviated):\n```json\n{\n  \"yamlPipeline\": \"pipeline:\\n  identifier: nodejs_ci\\n  name: Node.js CI\\n  projectIdentifier: my_project\\n  orgIdentifier: default\\n  stages:\\n    - stage:\\n        identifier: build\\n        ...\"\n}\n```\n\nTo update an existing pipeline, use the same `yamlPipeline` format:\n\n```\nCall MCP tool: harness_update\nParameters:\n  resource_type: \"pipeline\"\n  resource_id: \"\u003Cpipeline_identifier>\"\n  org_id: \"\u003Corganization>\"\n  project_id: \"\u003Cproject>\"\n  body: { yamlPipeline: \"\u003Cfull updated pipeline YAML string>\" }\n```\n\nTo verify it was created:\n\n```\nCall MCP tool: harness_get\nParameters:\n  resource_type: \"pipeline\"\n  resource_id: \"\u003Cpipeline_identifier>\"\n  org_id: \"\u003Corganization>\"\n  project_id: \"\u003Cproject>\"\n```\n\n## Complete CI Example\n\n```yaml\npipeline:\n  identifier: nodejs_ci\n  name: Node.js CI\n  projectIdentifier: my_project\n  orgIdentifier: default\n  properties:\n    ci:\n      codebase:\n        connectorRef: github_connector\n        repoName: my-app\n        build:\n          type: branch\n          spec:\n            branch: \u003C+trigger.branch>\n  stages:\n    - stage:\n        identifier: build_and_test\n        name: Build and Test\n        type: CI\n        spec:\n          cloneCodebase: true\n          platform:\n            os: Linux\n            arch: Amd64\n          runtime:\n            type: Cloud\n            spec: {}\n          execution:\n            steps:\n              - step:\n                  identifier: install\n                  name: Install\n                  type: Run\n                  spec:\n                    shell: Bash\n                    command: npm ci\n              - parallel:\n                  - step:\n                      identifier: lint\n                      name: Lint\n                      type: Run\n                      spec:\n                        shell: Bash\n                        command: npm run lint\n                  - step:\n                      identifier: test\n                      name: Test\n                      type: Run\n                      spec:\n                        shell: Bash\n                        command: npm test\n                        reports:\n                          type: JUnit\n                          spec:\n                            paths: [\"junit.xml\"]\n              - step:\n                  identifier: docker_push\n                  name: Build and Push\n                  type: BuildAndPushDockerRegistry\n                  spec:\n                    connectorRef: dockerhub\n                    repo: myorg\u002Fmy-app\n                    tags: [\u003C+pipeline.sequenceId>, latest]\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: MarkAsFailure\n```\n\n## Complete CD Example\n\n```yaml\npipeline:\n  identifier: k8s_deploy\n  name: K8s Deploy\n  projectIdentifier: my_project\n  orgIdentifier: default\n  stages:\n    - stage:\n        identifier: deploy_staging\n        name: Deploy Staging\n        type: Deployment\n        spec:\n          deploymentType: Kubernetes\n          service:\n            serviceRef: my_service\n          environment:\n            environmentRef: staging\n            infrastructureDefinitions:\n              - identifier: k8s_staging\n          execution:\n            steps:\n              - step:\n                  identifier: rollout\n                  name: Rollout\n                  type: K8sRollingDeploy\n                  spec:\n                    skipDryRun: false\n                  timeout: 10m\n            rollbackSteps:\n              - step:\n                  identifier: rollback\n                  name: Rollback\n                  type: K8sRollingRollback\n                  spec: {}\n                  timeout: 10m\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: StageRollback\n    - stage:\n        identifier: approval\n        name: Production Approval\n        type: Approval\n        spec:\n          execution:\n            steps:\n              - step:\n                  identifier: approve\n                  name: Approve Prod\n                  type: HarnessApproval\n                  spec:\n                    approvalMessage: \"Approve production deployment?\"\n                    approvers:\n                      userGroups: [prod_approvers]\n                      minimumCount: 1\n                      disallowPipelineExecutor: true\n                    includePipelineExecutionHistory: true\n                  timeout: 1d\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: Abort\n    - stage:\n        identifier: deploy_prod\n        name: Deploy Production\n        type: Deployment\n        spec:\n          deploymentType: Kubernetes\n          service:\n            serviceRef: my_service\n          environment:\n            environmentRef: prod\n            infrastructureDefinitions:\n              - identifier: k8s_prod\n          execution:\n            steps:\n              - step:\n                  identifier: rollout\n                  name: Rollout\n                  type: K8sRollingDeploy\n                  spec:\n                    skipDryRun: false\n                  timeout: 10m\n            rollbackSteps:\n              - step:\n                  identifier: rollback\n                  name: Rollback\n                  type: K8sRollingRollback\n                  spec: {}\n                  timeout: 10m\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: StageRollback\n```\n\n## Examples\n\n### Create a CI pipeline\n\n```\n\u002Fcreate-pipeline\nCreate a CI pipeline for a Node.js app that builds, runs tests, and pushes to Docker Hub\n```\n\n### Create a CD pipeline with approvals\n\n```\n\u002Fcreate-pipeline\nCreate a Kubernetes deployment pipeline with staging, manual approval, and production stages\n```\n\n### Create a combined CI\u002FCD pipeline\n\n```\n\u002Fcreate-pipeline\nBuild a pipeline that runs tests, pushes a Docker image, and deploys to ECS with rollback\n```\n\n### Create a matrix build pipeline\n\n```\n\u002Fcreate-pipeline\nCreate a CI pipeline that tests across Node 16, 18, and 20 on both Linux and macOS\n```\n\n### Create a pipeline with parallel stages\n\n```\n\u002Fcreate-pipeline\nCreate a pipeline with parallel test stages for unit tests, integration tests, and linting\n```\n\n## Performance Notes\n\n- Always check `references\u002Fnative-steps.md` before using a Run step. Native steps provide better error handling and UI integration.\n- Verify the target project exists (`harness_list`, resource_type: `project`) before creating the pipeline.\n- Validate that all referenced connectors, services, and environments exist before creating the pipeline.\n- For CD pipelines, confirm the deployment type matches the service definition type.\n- Quality of generated YAML is more important than speed. Verify structure before submitting.\n\n## Troubleshooting\n\n### YAML Validation Errors\n- **Pipeline\u002Fstep identifier:** must match `^[a-zA-Z_][0-9a-zA-Z_]{0,127}$` (letters, numbers, underscores only).\n- **Stage name:** must match `^[a-zA-Z_0-9-.][-0-9a-zA-Z_\\\\s.]{0,127}$` — no commas; use letters, numbers, spaces, hyphens, underscores, or periods (e.g. use \"Build Test and Push\" not \"Build, Test and Push\").\n- **Every CI and CD stage** must include a `failureStrategies` array (Approval stages do not require one); omit it and the API returns \"failureStrategies: is missing but it is required\". For CI use `type: MarkAsFailure`; for CD use `type: StageRollback`.\n- Stage type is case-sensitive: `CI`, `Deployment`, `Approval`, `Custom`\n- Every stage must have a `spec` field\n- **Matrix not applied \u002F not visible in UI:** `strategy` must be a sibling of `spec` on the stage, not inside `spec`. Use `strategy.matrix` at the stage level and reference values as `\u003C+stage.matrix.TAG>`.\n- **HarnessApproval:** \"disallowPipelineExecutor: is missing but it is required\" — add `approvers.disallowPipelineExecutor: true` to the step spec.\n\n### MCP Creation Errors\n- **Project not found** — Verify the project exists with `harness_list` (resource_type: `project`, org_id). Create it first with `harness_create` (resource_type: `project`, body: `{ identifier, name }`) or confirm org_id\u002Fproject_id are correct.\n- **Missing required fields for pipeline: pipeline** — Pass the body as `{ yamlPipeline: \"\u003Cfull pipeline YAML string>\" }` instead of a nested JSON `pipeline` object. Nested JSON causes serialization errors.\n- `DUPLICATE_IDENTIFIER` — Pipeline already exists; use `harness_update` instead\n- `CONNECTOR_NOT_FOUND` — Create the connector first or fix connectorRef\n- `ACCESS_DENIED` — Check API key permissions\n\n### Ambiguous or Incomplete Requests\n- **\"Deploys to ECS\" \u002F \"K8s deploy\" \u002F \"push to registry\" with no specifics** — Ask the user for region, account ID, cluster name\u002FID, and which registry (ECR, Docker Hub, etc.) before generating YAML. Do not insert placeholder values (e.g. `us-east-1`, `123456789012`).\n\n### Execution Failures\n- Missing `\u003C+input>` values - provide via input sets or runtime inputs\n- Connector auth expired - test with `harness_execute` (resource_type: \"connector\", action: \"test_connection\")\n- Delegate offline - check with `harness_status`\n","# Create Pipeline\n\nGenerate Harness v0 Pipeline YAML and optionally push to Harness via MCP.\n\n## Instructions\n\n1. **Analyze codebase** (if source code is available) - Scan the project to auto-detect language, build tools, test frameworks, containerization, deployment manifests, and target infrastructure. Use the detection tables and decision tree in `references\u002Fcodebase-analysis.md` to determine:\n   - Language and runtime version (package.json → Node.js, go.mod → Go, pom.xml → Java, etc.)\n   - Build commands and base images\n   - Test framework and report format (Jest → JUnit, pytest → JUnit XML, etc.)\n   - Linter and formatter (ESLint, Prettier, Ruff, etc.)\n   - Dockerfile presence and registry type (Docker Hub, ECR, GCR, ACR)\n   - Deployment manifests → Harness service\u002Fdeployment type (k8s manifests → Kubernetes, Chart.yaml → NativeHelm, task-definition.json → ECS, serverless.yml → ServerlessAwsLambda)\n   - Existing CI\u002FCD configs for migration (GitHub Actions, Jenkins, GitLab CI, etc.)\n2. **Clarify requirements** - Confirm detected settings with the user. **Ask about anything that couldn't be auto-detected** — do not guess or use placeholders. If the user's request is ambiguous, ask before generating YAML. Examples of what to ask when missing:\n   - **Deployment target \u002F infrastructure:** region (e.g. us-east-1), cluster name or ID, account ID (e.g. AWS account for ECR\u002FECS)\n   - **Registry:** which registry (Docker Hub, ECR, GCR, ACR), registry identifier\u002FURL, repo path\n   - **Cloud provider:** which account, region, and resource identifiers for connectors\u002Finfrastructure\n   - **Approval gates, notification channels** if relevant\n   **Critical rule:** Never hardcode placeholder values (e.g. `123456789012`, `us-east-1`, `my-cluster`) for deployment target, region, registry, or cluster when the user did not specify them — ask the user instead. If the user did not specify region, account ID, cluster, or registry (e.g. \"deploys to ECS\" with no region or cluster), ask the user for those values before generating YAML.\n3. **Select native steps** - Always prefer Harness native steps over `Run` or `ShellScript` steps. Consult `references\u002Fnative-steps.md` for the full mapping. Key rules:\n   - Docker build\u002Fpush → use `BuildAndPushDockerRegistry` \u002F `BuildAndPushECR` \u002F `BuildAndPushGCR` \u002F `BuildAndPushACR` (never `Run: docker build && docker push`)\n   - K8s deploy → use `K8sRollingDeploy` \u002F `K8sBlueGreenDeploy` \u002F `K8sCanaryDeploy` (never `Run: kubectl apply`)\n   - Helm deploy → use `HelmDeploy` (never `Run: helm upgrade --install`)\n   - ECS deploy → use `EcsRollingDeploy` (never `Run: aws ecs update-service`)\n   - Terraform → use `TerraformPlan` \u002F `TerraformApply` (never `Run: terraform apply`)\n   - Security scanning → use native STO steps (`AquaTrivy`, `Snyk`, `Sonarqube`, `Semgrep`, etc.)\n   - Uploads → use `S3Upload` \u002F `GCSUpload` (never `Run: aws s3 cp`)\n   - Approvals → use `HarnessApproval` \u002F `JiraApproval` (never polling scripts)\n   - Ticketing → use `JiraCreate` \u002F `ServiceNowCreate` (never `Run: curl`)\n   - Use `Run` steps only for custom build\u002Ftest\u002Flint commands with no native equivalent\n   - **Test steps:** Any Run step that runs unit or integration tests must include a `reports` block (e.g. `type: JUnit`, `spec.paths`) so Harness can capture results; see `references\u002Fcodebase-analysis.md` for framework → report path.\n4. **Generate valid YAML** following the structure below, using the detected build\u002Ftest\u002Fdeploy commands. **Validation rules:** (a) Stage names must match `^[a-zA-Z_0-9-.][-0-9a-zA-Z_\\\\s.]{0,127}$` — use only letters, numbers, spaces, hyphens, underscores, or periods (no commas). (b) Every CI and CD stage must include a `failureStrategies` array (Approval stages do not require one). For CI use `MarkAsFailure` (never `Ignore` — it hides failures); for CD use `StageRollback`.\n5. **Optionally create via MCP** — First verify the project exists (see \"Creating via MCP\" section below), then use `harness_create` with resource_type `pipeline` and `body: { yamlPipeline: \"\u003CYAML string>\" }`\n\n## Pipeline Structure\n\n```yaml\npipeline:\n  identifier: my_pipeline       # ^[a-zA-Z_][0-9a-zA-Z_]{0,127}$\n  name: My Pipeline\n  orgIdentifier: default\n  projectIdentifier: my_project\n  tags: {}\n  properties:\n    ci:\n      codebase:                  # Required for CI stages\n        connectorRef: github_connector\n        repoName: my-repo\n        build:\n          type: branch\n          spec:\n            branch: \u003C+trigger.branch>\n  stages:\n    - stage: ...\n```\n\n## Stage Types\n\n### CI Stage (type: CI)\n\n```yaml\n- stage:\n    identifier: build\n    name: Build\n    type: CI\n    spec:\n      cloneCodebase: true\n      platform:\n        os: Linux\n        arch: Amd64\n      runtime:\n        type: Cloud    # Cloud, Kubernetes, VM, Docker\n        spec: {}\n      execution:\n        steps:\n          - step: ...\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: MarkAsFailure\n```\n\n### CD Stage (type: Deployment)\n\n```yaml\n- stage:\n    identifier: deploy\n    name: Deploy\n    type: Deployment\n    spec:\n      deploymentType: Kubernetes  # Kubernetes, NativeHelm, ECS, ServerlessAwsLambda, Ssh, WinRm, AzureWebApp\n      service:\n        serviceRef: my_service\n      environment:\n        environmentRef: dev\n        infrastructureDefinitions:\n          - identifier: k8s_dev\n      execution:\n        steps:\n          - step: ...\n        rollbackSteps:\n          - step: ...\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: StageRollback\n```\n\n### Approval Stage (type: Approval)\n\n`HarnessApproval` requires `approvers.disallowPipelineExecutor` (required by the API). Set it to `true` so the pipeline executor cannot approve their own run; omit it and the API returns \"disallowPipelineExecutor: is missing but it is required\".\n\n```yaml\n- stage:\n    identifier: approval\n    name: Approval\n    type: Approval\n    spec:\n      execution:\n        steps:\n          - step:\n              identifier: approve\n              name: Approve\n              type: HarnessApproval\n              spec:\n                approvalMessage: \"Please review and approve\"\n                approvers:\n                  userGroups: [prod_approvers]\n                  minimumCount: 1\n                  disallowPipelineExecutor: true\n                includePipelineExecutionHistory: true\n              timeout: 1d\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: Abort\n```\n\n## Common Step Types\n\n### Run Step\n\n```yaml\n- step:\n    identifier: run_tests\n    name: Run Tests\n    type: Run\n    spec:\n      shell: Bash          # Sh, Bash, Powershell, Pwsh, Python\n      command: |\n        npm ci\n        npm test\n      envVariables:\n        NODE_ENV: test\n      reports:\n        type: JUnit\n        spec:\n          paths: [\"junit.xml\"]\n```\n\n### Build and Push Docker\n```yaml\n- step:\n    identifier: docker_push\n    name: Build and Push\n    type: BuildAndPushDockerRegistry\n    spec:\n      connectorRef: dockerhub\n      repo: myorg\u002Fmyimage\n      tags: [latest, \u003C+pipeline.sequenceId>]\n      dockerfile: Dockerfile\n```\n\n### K8s Rolling Deploy\n```yaml\n- step:\n    identifier: rollout\n    name: Rollout\n    type: K8sRollingDeploy\n    spec:\n      skipDryRun: false\n    timeout: 10m\n```\n\n### K8s Rolling Rollback\n```yaml\n- step:\n    identifier: rollback\n    name: Rollback\n    type: K8sRollingRollback\n    spec: {}\n    timeout: 10m\n```\n\nFor the complete catalog of 300+ native step types (cloud deployments, security scanners, IaC, ticketing, approvals, GitOps, and more), consult `references\u002Fnative-steps.md`. Always check this reference before using a `Run` step.\n\n## Variables and Expressions\n\n```yaml\npipeline:\n  variables:\n    - name: env\n      type: String\n      default: dev\n    - name: api_key\n      type: Secret\n      value: \u003C+secrets.getValue(\"api_key\")>\n```\n\nCommon expressions:\n- `\u003C+pipeline.variables.env>` - Pipeline variable\n- `\u003C+stage.variables.VAR>` - Stage variable\n- `\u003C+steps.step_id.output.outputVariables.VAR>` - Step output\n- `\u003C+trigger.branch>`, `\u003C+trigger.commitSha>` - Trigger info\n- `\u003C+secrets.getValue(\"name\")>` - Secret reference\n- `\u003C+pipeline.sequenceId>` - Build number\n\n## Parallel Execution\n\n```yaml\n# Parallel steps\n- parallel:\n    - step: ...\n    - step: ...\n\n# Parallel stages\nstages:\n  - parallel:\n      - stage: ...\n      - stage: ...\n```\n\n## Failure Strategies\n\n```yaml\nfailureStrategies:\n  - onFailure:\n      errors: [AllErrors]     # AllErrors, Timeout, Authentication, Connectivity\n      action:\n        type: StageRollback   # Ignore, Retry, MarkAsSuccess, Abort, StageRollback, PipelineRollback\n```\n\n## Conditional Execution\n\n```yaml\n- stage:\n    when:\n      pipelineStatus: Success\n      condition: \u003C+pipeline.variables.deploy> == \"true\"\n```\n\n## Matrix Strategy\n\n**Placement:** `strategy` must be at the **stage level**, as a **sibling of `spec`**, not inside `spec`. If you put `strategy` under `spec`, the matrix will not be applied and the UI will not show matrix iterations.\n\nReference matrix values in steps with `\u003C+stage.matrix.TAG>` (e.g. `\u003C+stage.matrix.python_version>`). Use hyphen-free dimension names (e.g. `python_version` not `python-version`).\n\n```yaml\n- stage:\n    identifier: test_matrix\n    name: Test Matrix\n    type: CI\n    spec:\n      cloneCodebase: true\n      platform:\n        os: Linux\n        arch: Amd64\n      runtime:\n        type: Cloud\n        spec: {}\n      execution:\n        steps:\n          - step:\n              type: Run\n              spec:\n                image: node:\u003C+stage.matrix.node_version>\n                command: npm test\n    strategy:\n      matrix:\n        node_version: [\"16\", \"18\", \"20\"]\n        os: [linux, macos]\n      maxConcurrency: 3\n    failureStrategies:\n      - onFailure:\n          errors: [AllErrors]\n          action:\n            type: Abort\n```\n\n## Creating via MCP\n\nAfter generating the YAML, create it in Harness:\n\n1. **Verify the project exists** — List projects with `harness_list` (resource_type: `project`, org_id) to confirm. If the project does not exist, create it first with `harness_create` (resource_type: `project`, body: `{ identifier, name }`) or ask the user.\n2. **Create the pipeline** — Use `harness_create` with the pipeline YAML serialized as a **`yamlPipeline`** string in the body. Do not pass a nested JSON `pipeline` object; it causes serialization errors.\n\n```\nCall MCP tool: harness_create\nParameters:\n  resource_type: \"pipeline\"\n  org_id: \"\u003Corganization>\"\n  project_id: \"\u003Cproject>\"\n  body: { yamlPipeline: \"\u003Cfull pipeline YAML string, including 'pipeline:' root key>\" }\n```\n\n**Example body** (abbreviated):\n```json\n{\n  \"yamlPipeline\": \"pipeline:\\n  identifier: nodejs_ci\\n  name: Node.js CI\\n  projectIdentifier: my_project\\n  orgIdentifier: default\\n  stages:\\n    - stage:\\n        identifier: build\\n        ...\"\n}\n```\n\nTo update an existing pipeline, use the same `yamlPipeline` format:\n\n```\nCall MCP tool: harness_update\nParameters:\n  resource_type: \"pipeline\"\n  resource_id: \"\u003Cpipeline_identifier>\"\n  org_id: \"\u003Corganization>\"\n  project_id: \"\u003Cproject>\"\n  body: { yamlPipeline: \"\u003Cfull updated pipeline YAML string>\" }\n```\n\nTo verify it was created:\n\n```\nCall MCP tool: harness_get\nParameters:\n  resource_type: \"pipeline\"\n  resource_id: \"\u003Cpipeline_identifier>\"\n  org_id: \"\u003Corganization>\"\n  project_id: \"\u003Cproject>\"\n```\n\n## Complete CI Example\n\n```yaml\npipeline:\n  identifier: nodejs_ci\n  name: Node.js CI\n  projectIdentifier: my_project\n  orgIdentifier: default\n  properties:\n    ci:\n      codebase:\n        connectorRef: github_connector\n        repoName: my-app\n        build:\n          type: branch\n          spec:\n            branch: \u003C+trigger.branch>\n  stages:\n    - stage:\n        identifier: build_and_test\n        name: Build and Test\n        type: CI\n        spec:\n          cloneCodebase: true\n          platform:\n            os: Linux\n            arch: Amd64\n          runtime:\n            type: Cloud\n            spec: {}\n          execution:\n            steps:\n              - step:\n                  identifier: install\n                  name: Install\n                  type: Run\n                  spec:\n                    shell: Bash\n                    command: npm ci\n              - parallel:\n                  - step:\n                      identifier: lint\n                      name: Lint\n                      type: Run\n                      spec:\n                        shell: Bash\n                        command: npm run lint\n                  - step:\n                      identifier: test\n                      name: Test\n                      type: Run\n                      spec:\n                        shell: Bash\n                        command: npm test\n                        reports:\n                          type: JUnit\n                          spec:\n                            paths: [\"junit.xml\"]\n              - step:\n                  identifier: docker_push\n                  name: Build and Push\n                  type: BuildAndPushDockerRegistry\n                  spec:\n                    connectorRef: dockerhub\n                    repo: myorg\u002Fmy-app\n                    tags: [\u003C+pipeline.sequenceId>, latest]\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: MarkAsFailure\n```\n\n## Complete CD Example\n\n```yaml\npipeline:\n  identifier: k8s_deploy\n  name: K8s Deploy\n  projectIdentifier: my_project\n  orgIdentifier: default\n  stages:\n    - stage:\n        identifier: deploy_staging\n        name: Deploy Staging\n        type: Deployment\n        spec:\n          deploymentType: Kubernetes\n          service:\n            serviceRef: my_service\n          environment:\n            environmentRef: staging\n            infrastructureDefinitions:\n              - identifier: k8s_staging\n          execution:\n            steps:\n              - step:\n                  identifier: rollout\n                  name: Rollout\n                  type: K8sRollingDeploy\n                  spec:\n                    skipDryRun: false\n                  timeout: 10m\n            rollbackSteps:\n              - step:\n                  identifier: rollback\n                  name: Rollback\n                  type: K8sRollingRollback\n                  spec: {}\n                  timeout: 10m\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: StageRollback\n    - stage:\n        identifier: approval\n        name: Production Approval\n        type: Approval\n        spec:\n          execution:\n            steps:\n              - step:\n                  identifier: approve\n                  name: Approve Prod\n                  type: HarnessApproval\n                  spec:\n                    approvalMessage: \"Approve production deployment?\"\n                    approvers:\n                      userGroups: [prod_approvers]\n                      minimumCount: 1\n                      disallowPipelineExecutor: true\n                    includePipelineExecutionHistory: true\n                  timeout: 1d\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: Abort\n    - stage:\n        identifier: deploy_prod\n        name: Deploy Production\n        type: Deployment\n        spec:\n          deploymentType: Kubernetes\n          service:\n            serviceRef: my_service\n          environment:\n            environmentRef: prod\n            infrastructureDefinitions:\n              - identifier: k8s_prod\n          execution:\n            steps:\n              - step:\n                  identifier: rollout\n                  name: Rollout\n                  type: K8sRollingDeploy\n                  spec:\n                    skipDryRun: false\n                  timeout: 10m\n            rollbackSteps:\n              - step:\n                  identifier: rollback\n                  name: Rollback\n                  type: K8sRollingRollback\n                  spec: {}\n                  timeout: 10m\n        failureStrategies:\n          - onFailure:\n              errors: [AllErrors]\n              action:\n                type: StageRollback\n```\n\n## Examples\n\n### Create a CI pipeline\n\n```\n\u002Fcreate-pipeline\nCreate a CI pipeline for a Node.js app that builds, runs tests, and pushes to Docker Hub\n```\n\n### Create a CD pipeline with approvals\n\n```\n\u002Fcreate-pipeline\nCreate a Kubernetes deployment pipeline with staging, manual approval, and production stages\n```\n\n### Create a combined CI\u002FCD pipeline\n\n```\n\u002Fcreate-pipeline\nBuild a pipeline that runs tests, pushes a Docker image, and deploys to ECS with rollback\n```\n\n### Create a matrix build pipeline\n\n```\n\u002Fcreate-pipeline\nCreate a CI pipeline that tests across Node 16, 18, and 20 on both Linux and macOS\n```\n\n### Create a pipeline with parallel stages\n\n```\n\u002Fcreate-pipeline\nCreate a pipeline with parallel test stages for unit tests, integration tests, and linting\n```\n\n## Performance Notes\n\n- Always check `references\u002Fnative-steps.md` before using a Run step. Native steps provide better error handling and UI integration.\n- Verify the target project exists (`harness_list`, resource_type: `project`) before creating the pipeline.\n- Validate that all referenced connectors, services, and environments exist before creating the pipeline.\n- For CD pipelines, confirm the deployment type matches the service definition type.\n- Quality of generated YAML is more important than speed. Verify structure before submitting.\n\n## Troubleshooting\n\n### YAML Validation Errors\n- **Pipeline\u002Fstep identifier:** must match `^[a-zA-Z_][0-9a-zA-Z_]{0,127}$` (letters, numbers, underscores only).\n- **Stage name:** must match `^[a-zA-Z_0-9-.][-0-9a-zA-Z_\\\\s.]{0,127}$` — no commas; use letters, numbers, spaces, hyphens, underscores, or periods (e.g. use \"Build Test and Push\" not \"Build, Test and Push\").\n- **Every CI and CD stage** must include a `failureStrategies` array (Approval stages do not require one); omit it and the API returns \"failureStrategies: is missing but it is required\". For CI use `type: MarkAsFailure`; for CD use `type: StageRollback`.\n- Stage type is case-sensitive: `CI`, `Deployment`, `Approval`, `Custom`\n- Every stage must have a `spec` field\n- **Matrix not applied \u002F not visible in UI:** `strategy` must be a sibling of `spec` on the stage, not inside `spec`. Use `strategy.matrix` at the stage level and reference values as `\u003C+stage.matrix.TAG>`.\n- **HarnessApproval:** \"disallowPipelineExecutor: is missing but it is required\" — add `approvers.disallowPipelineExecutor: true` to the step spec.\n\n### MCP Creation Errors\n- **Project not found** — Verify the project exists with `harness_list` (resource_type: `project`, org_id). Create it first with `harness_create` (resource_type: `project`, body: `{ identifier, name }`) or confirm org_id\u002Fproject_id are correct.\n- **Missing required fields for pipeline: pipeline** — Pass the body as `{ yamlPipeline: \"\u003Cfull pipeline YAML string>\" }` instead of a nested JSON `pipeline` object. Nested JSON causes serialization errors.\n- `DUPLICATE_IDENTIFIER` — Pipeline already exists; use `harness_update` instead\n- `CONNECTOR_NOT_FOUND` — Create the connector first or fix connectorRef\n- `ACCESS_DENIED` — Check API key permissions\n\n### Ambiguous or Incomplete Requests\n- **\"Deploys to ECS\" \u002F \"K8s deploy\" \u002F \"push to registry\" with no specifics** — Ask the user for region, account ID, cluster name\u002FID, and which registry (ECR, Docker Hub, etc.) before generating YAML. Do not insert placeholder values (e.g. `us-east-1`, `123456789012`).\n\n### Execution Failures\n- Missing `\u003C+input>` values - provide via input sets or runtime inputs\n- Connector auth expired - test with `harness_execute` (resource_type: \"connector\", action: \"test_connection\")\n- Delegate offline - check with `harness_status`\n",{"name":5,"license":14,"metadata":23,"description":7,"compatibility":27},{"author":24,"version":25,"mcp-server":26},"Harness","2.2.0","harness-mcp-v2","Requires Harness MCP v2 server (harness-mcp-v2)","main","f3af6b6781621109871cca9e2989364afc509f3d","harnesses\u002Fharness-skills\u002Fskills\u002Fcreate-pipeline","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository","https:\u002F\u002Fgithub.com\u002FAdmiralGallade","Eager to learn!\r\nI'll do anything for more knowledge anywhere.","2026-06-06 07:34:31",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add AdmiralGallade\u002Fharness-repository --skill create-pipeline",{"tool":41,"command":42},"bunx","bunx skills add AdmiralGallade\u002Fharness-repository --skill create-pipeline",{"tool":44,"command":45},"pnpm","pnpm dlx skills add AdmiralGallade\u002Fharness-repository --skill create-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fcreate-pipeline\u002FSKILL.md",true,[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fcodebase-analysis.md","REFERENCE","参考文档",9704,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fcreate-pipeline\u002Freferences\u002Fcodebase-analysis.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fnative-steps.md",12811,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fcreate-pipeline\u002Freferences\u002Fnative-steps.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fv0-pipeline-schema.md",9665,"https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fcreate-pipeline\u002Freferences\u002Fv0-pipeline-schema.md",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M75JSM6WGJ71BTHM6VC8CJ1X","verify-sign","Add an Artifact Verification (SscaArtifactVerification) step to an existing Harness pipeline to verify Cosign signatures on container or local-stage artifacts. Supports CI, Security, and CD Deploy (containerized step group). Supports Third-Party registries (Docker, ECR, GCR, GAR, ACR), Harness Artifact Registry (HAR), and Harness Local Stage artifacts. Only works with existing pipelines. Use when asked to verify signed artifacts, verify artifact signature, verify-sign, validate Cosign signature, or configure SscaArtifactVerification. Trigger phrases: verify sign, verify artifact, artifact verification, verify signature, verify-sign, SscaArtifactVerification, verify signed image, verify Cosign, HAR verification.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fverify-sign\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M75JSDSTP77TFM3JFGBB8QKP","template-usage","Track Harness template dependencies, usage, and adoption via MCP v2 tools. Find which pipelines or other templates reference a given template, analyze update impact, identify unused templates, and compare version adoption. Use when asked about template usage, template references, template dependencies, impact analysis before updating a template, finding unused templates, or tracking template adoption across projects. Trigger phrases: template usage, who uses template, template references, template dependencies, template impact, unused templates, template adoption. Do NOT use for creating or updating templates (use create-template instead).","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Ftemplate-usage\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M75JS76Q2KC8PD598H2DZZRA","sign-artifact","Add an Artifact Signing (SscaArtifactSigning) step to an existing Harness pipeline to Cosign-sign container or local-stage artifacts with keyless, key-based, or Vault signing. Supports Third-Party registries (Docker, ECR, GCR, GAR, ACR), Harness Artifact Registry (HAR), and Harness Local Stage artifacts. Place after image build\u002Fpush; optionally upload .sig to the registry. Only works with existing pipelines. Use when asked to sign artifacts, add artifact signing, Cosign sign image, attach signature to registry, or configure SscaArtifactSigning. Trigger phrases: sign artifact, artifact signing, sign image, Cosign sign, add signing step, SscaArtifactSigning, attach signature, sign container image, HAR signing.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fsign-artifact\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M75JS16EEFFHA44EBNE8KWNT","sei-analytics","Advanced engineering analytics via Harness Software Engineering Insights (SEI) MCP. Configure sprint velocity and estimation accuracy tracking, engineering investment allocation breakdowns, sprint planning with capacity forecasts, and release readiness assessments. Use when asked about sprint analytics, investment allocation, sprint planning, capacity forecasting, or release readiness. Do NOT use for DORA metrics (use dora-metrics instead). Trigger phrases: sprint velocity, sprint analytics, investment allocation, capacity planning, sprint forecast, release readiness, engineering productivity, estimation accuracy, sprint planning, scope creep, code quality trends.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fsei-analytics\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M75JRWE3X3E7V9JFQ4ENZYZM","security-report","Generate security compliance reports using Harness SCS and STO via MCP. Analyze vulnerabilities, SBOMs, and manage exemptions. Use when user says \"security report\", \"vulnerabilities\", \"SBOM\", \"security scan\", \"compliance check\", or asks about application security.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fsecurity-report\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M75JRSFJSNZFZRFKX8MSPCS2","scorecard-review","Review service maturity scorecards and compliance using Harness IDP via MCP. Check production readiness, security, and documentation scores. Use when user says \"scorecard\", \"service maturity\", \"production readiness\", \"compliance score\", or asks about service health scores.","https:\u002F\u002Fgithub.com\u002FAdmiralGallade\u002Fharness-repository\u002Fblob\u002Fmain\u002Fharnesses\u002Fharness-skills\u002Fskills\u002Fscorecard-review\u002FSKILL.md",[],[]]