{"id":49165727,"url":"https://github.com/harness/harness-skills","last_synced_at":"2026-04-22T15:04:01.952Z","repository":{"id":348165734,"uuid":"1179203140","full_name":"harness/harness-skills","owner":"harness","description":"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 workflows through   natural language.","archived":false,"fork":false,"pushed_at":"2026-04-22T12:39:00.000Z","size":501,"stargazers_count":5,"open_issues_count":1,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-22T14:28:35.387Z","etag":null,"topics":["agent-skills","agents"],"latest_commit_sha":null,"homepage":"https://developer.harness.io/docs/platform/harness-ai/harness-skills/","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/harness.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-11T19:45:58.000Z","updated_at":"2026-04-22T12:39:04.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/harness/harness-skills","commit_stats":null,"previous_names":["harness/harness-skills"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/harness/harness-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harness%2Fharness-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harness%2Fharness-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harness%2Fharness-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harness%2Fharness-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/harness","download_url":"https://codeload.github.com/harness/harness-skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/harness%2Fharness-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32141506,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-22T14:31:12.705Z","status":"ssl_error","status_checked_at":"2026-04-22T14:27:43.037Z","response_time":58,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","agents"],"created_at":"2026-04-22T15:04:01.246Z","updated_at":"2026-04-22T15:04:01.943Z","avatar_url":"https://github.com/harness.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Harness Skills\n\nClaude Code skills for the [Harness.io](https://harness.io) CI/CD platform. Generate pipeline YAML, manage resources, debug failures, analyze costs, and more from natural language.\n\nThis repository is designed as a workflow system, not just a folder of prompts. The top-level instructions (`CLAUDE.md`, `AGENTS.md`, `.github/copilot-instructions.md`) establish shared behavior, while individual skills specialize in creation, debugging, governance, and reporting tasks.\n\n## Prerequisites\n\n- [Harness MCP v2 Server](https://github.com/harness/mcp-server) - required for MCP-powered skills. Most skills in this repo depend on it for Harness API access.\n\n## Setup\n\n### Claude Code\n\nClone the repo and run Claude Code from the project directory. Skills are automatically discovered from `CLAUDE.md` and `skills/*/SKILL.md`:\n\n```bash\ngit clone https://github.com/harness/harness-skills.git\ncd harness-skills\nclaude\n```\n\nTo add the Harness MCP server, configure it in your Claude Code settings (`~/.claude/settings.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"harness-mcp-v2\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"harness-mcp-v2\"],\n      \"env\": {\n        \"HARNESS_API_KEY\": \"\u003cyour-api-key\u003e\"\n      }\n    }\n  }\n}\n```\n\nInvoke skills by name:\n\n```\n/create-pipeline\nCreate a CI pipeline for a Node.js app that builds, runs tests,\nand pushes a Docker image to ECR\n```\n\n### Cursor\n\n1. Clone the repo into your project or as a reference workspace:\n\n```bash\ngit clone https://github.com/harness/harness-skills.git\n```\n\n2. The repo includes `.cursor/rules/harness.mdc`, which Cursor automatically loads as a project rule.\n\n3. Configure the Harness MCP server in Cursor (`~/.cursor/mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"harness-mcp-v2\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"harness-mcp-v2\"],\n      \"env\": {\n        \"HARNESS_API_KEY\": \"\u003cyour-api-key\u003e\"\n      }\n    }\n  }\n}\n```\n\n4. Reference individual skills in your prompts using `@file`:\n\n```\n@harness-skills/skills/create-pipeline/SKILL.md\nCreate a CI pipeline for my Go service\n```\n\n### OpenAI Codex\n\n1. Clone the repo into your working directory:\n\n```bash\ngit clone https://github.com/harness/harness-skills.git\n```\n\n2. The repo includes `AGENTS.md` at the root, which Codex automatically reads as system instructions.\n\n3. Configure the Harness MCP server in your Codex MCP config:\n\n```json\n{\n  \"mcpServers\": {\n    \"harness-mcp-v2\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"harness-mcp-v2\"],\n      \"env\": {\n        \"HARNESS_API_KEY\": \"\u003cyour-api-key\u003e\"\n      }\n    }\n  }\n}\n```\n\n4. Reference individual skill files as context when prompting:\n\n```\nUsing the instructions in harness-skills/skills/debug-pipeline/SKILL.md,\ndiagnose why my deploy pipeline failed\n```\n\n### GitHub Copilot\n\n1. Clone the repo into your project:\n\n```bash\ngit clone https://github.com/harness/harness-skills.git\n```\n\n2. The repo includes `.github/copilot-instructions.md`, which Copilot automatically reads as project-level context in both GitHub.com and VS Code.\n\n3. For VS Code, configure the Harness MCP server in your workspace settings (`.vscode/mcp.json`):\n\n```json\n{\n  \"servers\": {\n    \"harness-mcp-v2\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"harness-mcp-v2\"],\n      \"env\": {\n        \"HARNESS_API_KEY\": \"\u003cyour-api-key\u003e\"\n      }\n    }\n  }\n}\n```\n\n4. Reference skill files in Copilot Chat using `#file`:\n\n```\n#file:harness-skills/skills/create-pipeline/SKILL.md\nCreate a CI pipeline for my Python service\n```\n\n5. For GitHub Copilot on GitHub.com, attach skill files as context in Copilot Chat or add them as knowledge base references in your Copilot organization settings.\n\n### Windsurf / Other AI Editors\n\nThe skills in this repo are plain Markdown files with YAML frontmatter. They work with any AI coding tool that supports:\n\n1. **System instructions** - Use `CLAUDE.md` as project-level context.\n2. **MCP servers** - Connect the [Harness MCP v2 server](https://github.com/harness/mcp-server) for API access.\n3. **File context** - Reference individual `skills/*/SKILL.md` files in prompts.\n\n## Operating Model\n\nThe best Harness skills follow the same control flow even when they target different resource types:\n\n1. **Establish scope first** - confirm account/org/project context before listing, creating, updating, or deleting resources.\n2. **Verify dependencies before generating dependents** - do not reference connectors, secrets, environments, infrastructure, or templates that have not been confirmed to exist.\n3. **Discover schema before writing payloads** - use `harness_describe` and API validation feedback instead of guessing field names or payload shape.\n\nThese repo-level playbooks live in:\n\n- [`references/scope-establishment.md`](references/scope-establishment.md)\n- [`references/dependency-check-playbook.md`](references/dependency-check-playbook.md)\n- [`references/schema-validation-loop.md`](references/schema-validation-loop.md)\n- [`templates/operation-summary.md`](templates/operation-summary.md)\n\n## Workflow Modes\n\n| Workflow mode | Representative skills | Use when |\n|---------------|-----------------------|----------|\n| Create and scaffold | `/create-pipeline`, `/create-service`, `/create-connector`, `/create-template` | You need to define or generate new Harness resources and their YAML or MCP payloads. |\n| Run and debug | `/run-pipeline`, `/debug-pipeline`, `/migrate-pipeline`, `/manage-delegates` | You already have resources and need to execute, diagnose, or repair behavior. |\n| Govern and secure | `/manage-roles`, `/manage-users`, `/create-policy`, `/security-report`, `/audit-report` | You need RBAC, policy, compliance, or security workflows with blast-radius awareness. |\n| Analyze and report | `/dora-metrics`, `/analyze-costs`, `/scorecard-review`, `/template-usage` | You need structured reports, summaries, recommendations, or adoption analysis. |\n\n## End-to-End Workflows\n\n### New microservice setup\n\nUse these skills in order:\n\n1. `/create-connector`\n2. `/create-secret`\n3. `/create-service`\n4. `/create-environment`\n5. `/create-infrastructure`\n6. `/create-pipeline`\n7. `/create-trigger`\n\n### Debug a failed deployment\n\nTypical sequence:\n\n1. `/run-pipeline` to identify the latest execution or reproduce the issue\n2. `/debug-pipeline` to classify the failure and inspect root cause\n3. `/template-usage` if shared templates may have propagated the issue\n4. `/manage-delegates` if the failure points to delegate capacity or connectivity\n\n## Skills\n\n### Pipeline \u0026 Template Creation\n\n| Skill | Description |\n|-------|-------------|\n| [`/create-pipeline`](skills/create-pipeline/SKILL.md) | Generate v0 Pipeline YAML (CI, CD, approvals, matrix strategies) |\n| [`/create-pipeline-v1`](skills/create-pipeline-v1/SKILL.md) | Generate v1 simplified Pipeline YAML - **Alpha: internal testing only** |\n| [`/create-template`](skills/create-template/SKILL.md) | Create reusable Step, Stage, Pipeline, or StepGroup templates |\n| [`/create-trigger`](skills/create-trigger/SKILL.md) | Create webhook, scheduled, and artifact triggers |\n| [`/create-agent-template`](skills/create-agent-template/SKILL.md) | Create AI-powered agent templates - **Alpha: internal testing only** |\n\n### Resource Management\n\n| Skill | Description |\n|-------|-------------|\n| [`/create-service`](skills/create-service/SKILL.md) | Create service definitions (K8s, Helm, ECS, Lambda) |\n| [`/create-environment`](skills/create-environment/SKILL.md) | Create environment definitions with overrides |\n| [`/create-infrastructure`](skills/create-infrastructure/SKILL.md) | Create infrastructure definitions |\n| [`/create-connector`](skills/create-connector/SKILL.md) | Create connectors (Git, cloud, registries, clusters) |\n| [`/create-secret`](skills/create-secret/SKILL.md) | Create secrets (text, file, SSH, WinRM) |\n\n### Access Control \u0026 Feature Flags (MCP)\n\n| Skill | Description |\n|-------|-------------|\n| [`/manage-users`](skills/manage-users/SKILL.md) | Manage users, user groups, and service accounts |\n| [`/manage-roles`](skills/manage-roles/SKILL.md) | Manage role assignments and RBAC |\n| [`/manage-feature-flags`](skills/manage-feature-flags/SKILL.md) | Create, list, toggle, and delete feature flags |\n\n### Operations \u0026 Debugging (MCP)\n\n| Skill | Description |\n|-------|-------------|\n| [`/run-pipeline`](skills/run-pipeline/SKILL.md) | Execute pipelines, monitor progress, handle approvals |\n| [`/debug-pipeline`](skills/debug-pipeline/SKILL.md) | Analyze execution failures, diagnose root causes |\n| [`/migrate-pipeline`](skills/migrate-pipeline/SKILL.md) | Convert pipelines from v0 to v1 format |\n| [`/template-usage`](skills/template-usage/SKILL.md) | Track template dependencies and adoption |\n| [`/manage-delegates`](skills/manage-delegates/SKILL.md) | Monitor delegate health and manage tokens |\n\n### Platform Intelligence (MCP)\n\n| Skill | Description |\n|-------|-------------|\n| [`/analyze-costs`](skills/analyze-costs/SKILL.md) | Cloud cost analysis and optimization (CCM) |\n| [`/security-report`](skills/security-report/SKILL.md) | Vulnerability reports, SBOMs, compliance (SCS/STO) |\n| [`/dora-metrics`](skills/dora-metrics/SKILL.md) | DORA metrics and engineering performance (SEI) |\n| [`/gitops-status`](skills/gitops-status/SKILL.md) | GitOps application health and sync status |\n| [`/chaos-experiment`](skills/chaos-experiment/SKILL.md) | Create and run chaos experiments |\n| [`/scorecard-review`](skills/scorecard-review/SKILL.md) | Service maturity scorecards (IDP) |\n| [`/audit-report`](skills/audit-report/SKILL.md) | Audit trails and compliance reports |\n| [`/create-policy`](skills/create-policy/SKILL.md) | Create OPA governance policies for supply chain security |\n\n## Project Structure\n\n```\nharness-skills/\n├── skills/\n│   ├── create-pipeline/\n│   │   ├── SKILL.md\n│   │   └── references/\n│   ├── create-template/\n│   │   └── SKILL.md\n│   ├── debug-pipeline/\n│   │   └── SKILL.md\n│   └── ...                      # Skill definitions\n├── references/                  # Shared repo-level playbooks\n├── templates/                   # Shared repo-level output templates\n├── scripts/\n│   └── validate-skills.sh       # Structural validation\n├── examples/\n│   ├── v0/                      # v0 pipeline examples\n│   ├── v1/                      # v1 pipeline examples\n│   ├── templates/               # Template examples\n│   ├── triggers/                # Trigger examples\n│   ├── services/                # Service definition examples\n│   ├── environments/            # Environment examples\n│   ├── connectors/              # Connector examples\n│   └── ...\n├── .cursor/rules/harness.mdc    # Auto-loaded by Cursor\n├── .github/copilot-instructions.md\n├── AGENTS.md                    # Auto-loaded by OpenAI Codex\n├── CLAUDE.md                    # Auto-loaded by Claude Code\n├── CONTRIBUTING.md              # Contribution guidelines\n├── LICENSE\n└── README.md\n```\n\n## Shared Playbooks and Templates\n\nUse root-level shared assets for behavior that should stay consistent across many skills:\n\n- `references/` - reusable operating guidance such as scope establishment, dependency verification, and schema-validation loops\n- `templates/` - reusable output contracts such as operation summaries and report formats\n\nUse per-skill `references/` or `templates/` when the content is domain-specific and should not be imported broadly.\n\n## Skill Anatomy\n\nEach skill is a directory under `skills/` containing a `SKILL.md` with YAML frontmatter and a consistent markdown body:\n\n```yaml\n---\nname: my-skill\ndescription: \u003e-\n  Explain what the skill does, when to use it, when not to use it, and likely\n  trigger phrases. Keep it under 1024 characters.\nmetadata:\n  author: Harness\n  version: 1.0.0\n  mcp-server: harness-mcp-v2\nlicense: Apache-2.0\ncompatibility: Requires Harness MCP v2 server (harness-mcp-v2)\n---\n\n# My Skill\n\nOne or two sentences describing the operating mode and expected outcome.\n\n## Instructions\n\nPhase-based steps for Claude to follow.\n\n## Examples\n\nInvocation examples and, for complex skills, brief worked examples.\n\n## Performance Notes\n\nValidation checks, tradeoffs, or speed/accuracy guidance.\n\n## Troubleshooting\n\nCommon errors, recovery steps, and expected fallbacks.\n```\n\nFor complex skills, add `references/` or `templates/` under the skill directory rather than bloating `SKILL.md`.\n\n## MCP Tools\n\nMCP-powered skills use the [Harness MCP v2 server](https://github.com/harness/mcp-server), which provides 10 generic tools dispatched by `resource_type`:\n\n| Tool | Purpose |\n|------|---------|\n| `harness_list` | List resources |\n| `harness_get` | Get resource details |\n| `harness_create` | Create a resource |\n| `harness_update` | Update a resource |\n| `harness_delete` | Delete a resource |\n| `harness_execute` | Execute an action |\n| `harness_search` | Search across resources |\n| `harness_describe` | Get resource schema |\n| `harness_diagnose` | Diagnose issues |\n| `harness_status` | Check system status |\n\n## Schema References\n\n- [v0 Pipeline/Template/Trigger Schema](https://github.com/harness/harness-schema/tree/main/v0)\n- [v1 Pipeline Spec](https://github.com/thisrohangupta/spec)\n- [Agent Templates](https://github.com/thisrohangupta/agents)\n- [Harness MCP v2 Server](https://github.com/harness/mcp-server)\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for skill authoring standards, validation rules, and contribution workflow.\n\n## License\n\nThis project is licensed under the [Apache License 2.0](LICENSE).\n\nCopyright 2026 Harness Inc.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharness%2Fharness-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fharness%2Fharness-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fharness%2Fharness-skills/lists"}