{"id":"44c74119-2764-4c7f-8085-0dd5ed130643","shortId":"2Y9FJY","kind":"skill","title":"run-pipeline","tagline":">-","description":"# Run Pipeline\n\nExecute and monitor Harness pipeline runs via MCP.\n\n## Instructions\n\n### Step 1: Find the Pipeline\n\n```\nCall MCP tool: harness_search\nParameters:\n  query: \"<user's pipeline name or keyword>\"\n  resource_types: [\"pipeline\"]\n  compact: true\n```\n\nOr list all pipelines in a project:\n\n```\nCall MCP tool: harness_list\nParameters:\n  resource_type: \"pipeline\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n  search_term: \"<optional filter>\"\n```\n\n### Step 2: Get Pipeline Details\n\n```\nCall MCP tool: harness_get\nParameters:\n  resource_type: \"pipeline\"\n  resource_id: \"<pipeline_identifier>\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n```\n\nExtract from response:\n- Required runtime inputs (`<+input>` fields)\n- Pipeline variables with types and defaults\n- Stage structure and deployment targets\n\n### Step 3: Check Available Input Sets\n\n```\nCall MCP tool: harness_list\nParameters:\n  resource_type: \"input_set\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n```\n\nInput sets provide pre-configured values that can be used or overridden.\n\n### Step 4: Execute the Pipeline\n\n```\nCall MCP tool: harness_execute\nParameters:\n  resource_type: \"pipeline\"\n  action: \"run\"\n  resource_id: \"<pipeline_identifier>\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n```\n\n### Step 5: Monitor Execution\n\n```\nCall MCP tool: harness_get\nParameters:\n  resource_type: \"execution\"\n  resource_id: \"<execution_id>\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n```\n\nExecution statuses: Running, Success, Failed, Aborted, Waiting (approval/input), Expired\n\n### Step 6: Handle Approvals\n\nIf execution is waiting for approval:\n\n```\nCall MCP tool: harness_list\nParameters:\n  resource_type: \"approval_instance\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n```\n\nThen approve or reject:\n\n```\nCall MCP tool: harness_execute\nParameters:\n  resource_type: \"approval_instance\"\n  action: \"approve\"  # or \"reject\"\n  resource_id: \"<approval_id>\"\n```\n\n## Safety: Production Deployments\n\nCRITICAL: Before executing pipelines targeting production:\n\n1. Confirm intent with the user explicitly\n2. Show what will be deployed (version, service, environment)\n3. Check if pipeline has approval gates\n4. Verify the version was tested in lower environments\n\n## Response Format\n\n### Before Execution\n```\nPipeline: <name>\nProject: <project>\nRequired Inputs: <list variables needing values>\nAvailable Input Sets: <list>\nReady to execute? Confirm to proceed.\n```\n\n### After Trigger\n```\nPipeline: <name>\nExecution ID: <id>\nStatus: Running\nView in Harness: <openInHarness link>\n```\n\n### Execution Complete\n```\nPipeline: <name>\nStatus: Success/Failed\nDuration: <time>\nStages: <stage results table>\n```\n\n## Retrying Failed Executions\n\nRetry is an action on `pipeline` (not `execution`). Pass the pipeline ID as `resource_id` and the failed execution's ID as `execution_id`:\n\n```\nCall MCP tool: harness_execute\nParameters:\n  resource_type: \"pipeline\"\n  action: \"retry\"\n  resource_id: \"<pipeline_id>\"\n  execution_id: \"<execution_id>\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n```\n\n## Interrupting Running Executions\n\nTo abort an entire pipeline execution:\n\n```\nCall MCP tool: harness_execute\nParameters:\n  resource_type: \"execution\"\n  action: \"interrupt\"\n  resource_id: \"<execution_id>\"\n  org_id: \"<organization>\"\n  project_id: \"<project>\"\n  params:\n    interrupt_type: \"AbortAll\"\n```\n\nThe `interrupt_type` field inside `params` is required. Valid values:\n\n| interrupt_type | Effect |\n|----------------|--------|\n| `AbortAll` | Abort the entire pipeline execution |\n| `UserMarkedFailure` | Mark the execution as failed by user |\n\nTo abort multiple stuck executions, call `harness_execute` with `params: {interrupt_type: \"AbortAll\"}` for each execution ID.\n\n## Examples\n\n- \"Run the ci-pipeline\" - Search for pipeline, execute with defaults\n- \"Deploy version 2.0.0 to staging\" - Find deploy pipeline, provide version input, execute\n- \"What's the status of execution xyz123?\" - Get execution details\n- \"Retry the last failed deployment\" - List recent failed executions, retry\n- \"Abort all stuck executions\" - List running/waiting executions, interrupt each with `params: {interrupt_type: \"AbortAll\"}`\n- \"Stop execution abc123\" - Interrupt the specific execution with `params: {interrupt_type: \"AbortAll\"}`\n\n## Performance Notes\n\n- Always confirm the pipeline identifier and required inputs before triggering execution. A failed execution due to missing inputs wastes time.\n- When monitoring executions, wait for terminal status (Success, Failed, Aborted) before reporting results. Do not assume intermediate states are final.\n- If an execution fails, gather full error context from logs before suggesting fixes. Do not guess at root causes.\n\n## Troubleshooting\n\n### Pipeline Won't Start\n- Check delegate availability with `harness_status`\n- Validate all required inputs have values\n- Test connector credentials with `harness_execute` (resource_type: \"connector\", action: \"test_connection\")\n\n### Missing Inputs\n- Use `harness_get` on the pipeline to see all `<+input>` fields\n- Check input sets for pre-configured values\n\n### Execution Stuck\n- Check for pending approvals with `harness_list` (resource_type: \"approval_instance\")\n- Check delegate status with `harness_status`\n- Abort stuck executions with `harness_execute` (resource_type: \"execution\", action: \"interrupt\", params: {interrupt_type: \"AbortAll\"})","tags":["run","pipeline","harness","skills","agent-skills","agents"],"capabilities":["skill","source-harness","skill-run-pipeline","topic-agent-skills","topic-agents"],"categories":["harness-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/harness/harness-skills/run-pipeline","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add harness/harness-skills","source_repo":"https://github.com/harness/harness-skills","install_from":"skills.sh"}},"qualityScore":"0.457","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 15 github stars · SKILL.md body (5,402 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:06:31.122Z","embedding":null,"createdAt":"2026-05-09T01:05:29.761Z","updatedAt":"2026-05-18T19:06:31.122Z","lastSeenAt":"2026-05-18T19:06:31.122Z","tsv":"'1':16,235 '2':61,242 '2.0.0':435 '3':100,251 '4':133,258 '5':155 '6':183 'abc123':481 'abort':178,351,391,405,465,522,621 'abortal':376,390,416,478,490,635 'action':146,220,307,337,365,578,630 'alway':493 'approv':185,191,200,207,218,221,256,607,613 'approval/input':180 'assum':528 'avail':102,275,559 'call':20,45,65,105,137,158,192,210,328,356,409 'caus':551 'check':101,252,557,594,604,615 'ci':425 'ci-pipelin':424 'compact':36 'complet':295 'configur':124,600 'confirm':236,281,494 'connect':580 'connector':570,577 'context':540 'credenti':571 'critic':229 'default':93,432 'deleg':558,616 'deploy':97,228,247,433,439,459 'detail':64,454 'due':507 'durat':299 'effect':389 'entir':353,393 'environ':250,266 'error':539 'exampl':421 'execut':6,134,141,157,166,173,187,214,231,270,280,287,294,303,311,322,326,332,341,349,355,360,364,395,399,408,411,419,430,444,450,453,463,468,471,480,485,503,506,515,535,574,602,623,626,629 'expir':181 'explicit':241 'extract':80 'fail':177,302,321,401,458,462,505,521,536 'field':87,380,593 'final':532 'find':17,438 'fix':545 'format':268 'full':538 'gate':257 'gather':537 'get':62,69,162,452,585 'guess':548 'handl':184 'har':9,23,48,68,108,140,161,195,213,293,331,359,410,561,573,584,609,619,625 'id':55,57,75,77,79,116,118,149,151,153,168,170,172,203,205,225,288,315,318,324,327,340,342,344,346,368,370,372,420 'identifi':497 'input':85,86,103,113,119,274,276,443,500,510,566,582,592,595 'insid':381 'instanc':201,219,614 'instruct':14 'intent':237 'intermedi':529 'interrupt':347,366,374,378,387,414,472,476,482,488,631,633 'keyword':32 'last':457 'list':39,49,109,196,460,469,610 'log':542 'lower':265 'mark':397 'mcp':13,21,46,66,106,138,159,193,211,329,357 'miss':509,581 'monitor':8,156,514 'multipl':406 'name':30 'note':492 'org':54,76,115,150,169,202,343,369 'overridden':131 'param':373,382,413,475,487,632 'paramet':25,50,70,110,142,163,197,215,333,361 'pass':312 'pend':606 'perform':491 'pipelin':3,5,10,19,29,35,41,53,63,73,88,136,145,232,254,271,286,296,309,314,336,354,394,426,429,440,496,553,588 'pre':123,599 'pre-configur':122,598 'proceed':283 'product':227,234 'project':44,56,78,117,152,171,204,272,345,371 'provid':121,441 'queri':26 'readi':278 'recent':461 'reject':209,223 'report':524 'requir':83,273,384,499,565 'resourc':33,51,71,74,111,143,148,164,167,198,216,224,317,334,339,362,367,575,611,627 'respons':82,267 'result':525 'retri':301,304,338,455,464 'root':550 'run':2,4,11,147,175,290,348,422 'run-pipelin':1 'running/waiting':470 'runtim':84 'safeti':226 'search':24,58,427 'see':590 'servic':249 'set':104,114,120,277,596 'show':243 'skill' 'skill-run-pipeline' 'source-harness' 'specif':484 'stage':94,300,437 'start':556 'state':530 'status':174,289,297,448,519,562,617,620 'step':15,60,99,132,154,182 'stop':479 'structur':95 'stuck':407,467,603,622 'success':176,520 'success/failed':298 'suggest':544 'target':98,233 'term':59 'termin':518 'test':263,569,579 'time':512 'tool':22,47,67,107,139,160,194,212,330,358 'topic-agent-skills' 'topic-agents' 'trigger':285,502 'troubleshoot':552 'true':37 'type':34,52,72,91,112,144,165,199,217,335,363,375,379,388,415,477,489,576,612,628,634 'use':129,583 'user':27,240,403 'usermarkedfailur':396 'valid':385,563 'valu':125,386,568,601 'variabl':89 'verifi':259 'version':248,261,434,442 'via':12 'view':291 'wait':179,189,516 'wast':511 'won':554 'xyz123':451","prices":[{"id":"2394aca4-13fe-4570-8dbc-17c7cd217fb4","listingId":"44c74119-2764-4c7f-8085-0dd5ed130643","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"harness","category":"harness-skills","install_from":"skills.sh"},"createdAt":"2026-05-09T01:05:29.761Z"}],"sources":[{"listingId":"44c74119-2764-4c7f-8085-0dd5ed130643","source":"github","sourceId":"harness/harness-skills/run-pipeline","sourceUrl":"https://github.com/harness/harness-skills/tree/main/skills/run-pipeline","isPrimary":false,"firstSeenAt":"2026-05-09T01:05:29.761Z","lastSeenAt":"2026-05-18T19:06:31.122Z"}],"details":{"listingId":"44c74119-2764-4c7f-8085-0dd5ed130643","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"harness","slug":"run-pipeline","github":{"repo":"harness/harness-skills","stars":15,"topics":["agent-skills","agents"],"license":"apache-2.0","html_url":"https://github.com/harness/harness-skills","pushed_at":"2026-05-13T01:28:28Z","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.","skill_md_sha":"71311b26b6203a57c136de721928fcc2629df5e4","skill_md_path":"skills/run-pipeline/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/harness/harness-skills/tree/main/skills/run-pipeline"},"layout":"multi","source":"github","category":"harness-skills","frontmatter":{"name":"run-pipeline","license":"Apache-2.0","description":">-","compatibility":"Requires Harness MCP v2 server (harness-mcp-v2)"},"skills_sh_url":"https://skills.sh/harness/harness-skills/run-pipeline"},"updatedAt":"2026-05-18T19:06:31.122Z"}}