[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-datadog-labs-unblock-pr":3,"mdc--dk4v2n-key":39,"related-repo-datadog-labs-unblock-pr":1660,"related-org-datadog-labs-unblock-pr":1765},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":28,"repoUrl":29,"updatedAt":30,"license":31,"forks":32,"topics":33,"repo":34,"sourceUrl":37,"mdContent":38},"unblock-pr","investigate and unblock PR CI pipelines","Load when investigating a failing PR CI pipeline or checking PR health. Attributes each CI failure as flaky, infra, or regression, proposes a targeted action, and reports code coverage and quality\u002Fsecurity status.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"datadog-labs","Datadog Labs","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fdatadog-labs.png",[12,16,19,22,25],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"Datadog","datadog",{"name":20,"slug":21,"type":15},"CI\u002FCD","ci-cd",{"name":23,"slug":24,"type":15},"Debugging","debugging",{"name":26,"slug":27,"type":15},"Pull Requests","pull-requests",145,"https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Fagent-skills","2026-05-28T06:54:40.027376",null,19,[],{"repoUrl":29,"stars":28,"forks":32,"topics":35,"description":36},[],"Public repository for Datadog Agent Skills","https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Fagent-skills\u002Ftree\u002FHEAD\u002Fdd-software-delivery\u002Funblock-pr","---\nname: unblock-pr\ndescription: Load when investigating a failing PR CI pipeline or checking PR health. Attributes each CI failure as flaky, infra, or regression, proposes a targeted action, and reports code coverage and quality\u002Fsecurity status.\nmetadata:\n  version: \"1.0.0\"\n  author: datadog-labs\n  repository: https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Fagent-skills\n  tags: datadog,ci,cicd,flaky,flaky-tests,pipeline\n  alwaysApply: \"false\"\n---\n\n# Unblock PR\n\nOne-line summary: Investigate a failing PR CI pipeline — attribute each failure as flaky, infra, or regression and propose a targeted action.\n\nRequires: `dd-pup` skill (pup CLI installed and authenticated), `triage-flaky-test` skill (for flaky failure deep investigation).\n\n---\n\n## Backend\n\n**Detection** — At the start of every invocation, before taking any action, determine which backend to use:\n\n1. If the user passed `--backend pup` anywhere → use **pup mode** immediately. Skip steps 2–4.\n2. Check whether `search_datadog_ci_pipeline_events` appears in your available tools.\n3. If present → use **MCP mode** throughout. Call tools exactly as named in this skill's workflow sections.\n4. If absent → check whether `pup` is executable: run `pup --version` via Bash. If the command exits successfully (exit code 0), pup is available.\n5. If pup responds → use **pup mode** throughout. Translate every tool call using the Tool Reference appendix at the bottom of this file.\n6. If neither is available → stop and tell the user:\n   > \"Neither the Datadog MCP server nor the pup CLI is available. Connect the MCP server or install pup (`brew install datadog-labs\u002Fpack\u002Fpup`).\"\n\n**pup invocation rules:**\n- Invoke via Bash. pup always outputs JSON — parse directly.\n- Repository IDs passed to pup must be fully lowercase (the API rejects mixed-case): `github.com\u002Fdatadog\u002Fmy-repo`, not `github.com\u002FDataDog\u002Fmy-repo`.\n- If pup returns a 401\u002F403, tell the user to run `pup auth refresh` or `pup auth login`.\n\n---\n\n## Input\n\n| Parameter | Description |\n|---|---|\n| PR branch | The branch under investigation (e.g. `my-feature-branch`) |\n| Repository | Lowercase, no-schema URL (e.g. `github.com\u002Forg\u002Frepo`). Derive from `git remote get-url origin` if not provided. |\n\n---\n\n## Workflow\n\n### STEP 0 — Parse Input\n\nDerive repository ID and default branch from git if not provided:\n\n```bash\n# Repository ID: fully lowercase, no-schema URL (the API rejects mixed-case)\ngit remote get-url origin\n# Strip protocol and trailing .git, then lowercase the result\n# e.g. https:\u002F\u002Fgithub.com\u002FDataDog\u002Fmy-repo.git → github.com\u002Fdatadog\u002Fmy-repo\n\n# Default branch\ngit symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD\n# Strip refs\u002Fremotes\u002Forigin\u002F prefix — fall back to main if unset\n```\n\n### STEP 1 — Get PR CI Summary (run in parallel)\n\n**Pipeline failures:**\n```\nTool: search_datadog_ci_pipeline_events\nquery: @ci.status:error @git.branch:\u003Cbranch> @git.repository.id_v2:\"\u003Crepo>\"\nci_level: job\nfrom: now-24h\n```\n\n**Test failures** (only if pipeline results include test-runner jobs):\n```\nTool: search_datadog_test_events\nquery: @test.status:fail @git.branch:\u003Cbranch> @git.repository.id_v2:\"\u003Crepo>\"\nfrom: now-24h\ntest_level: test\n```\n\nRun both in parallel. Collect all distinct `@test.service` values from test event results. If more than one distinct service is found, note each separately in the triage brief — do not collapse them into a single service filter. If pipeline results contain only infrastructure job types (build, lint, deploy) with no test-runner output, discard test results and skip to STEP 3.\n\n### STEP 1.5 — Fetch PR Health (run in parallel with STEP 1)\n\nThis step runs unconditionally — PR health context is valuable whether CI is red or green.\n\n**Code coverage** (both modes):\n```\nTool: get_datadog_code_coverage_branch_summary\nrepository_id: \u003Crepo>\nbranch: \u003Cbranch>\n```\n\n**PR number resolution** (MCP mode only — skip if PR number already provided as input):\n```\nTool: get_prs_by_head_branch\nrepo_url: https:\u002F\u002F\u003Crepo>\nhead_branch: \u003Cbranch>\n```\nUse the first open PR returned. If no open PR is found, skip the quality\u002Fsecurity fetch and report \"No data available\" for Quality and Security.\n\n**Code quality and security** (MCP mode only — only if PR number is available):\n```\nTool: search_pr_insights\nrepo_url: https:\u002F\u002F\u003Crepo>\npr_number: \u003Cpr_number>\n```\nExtract only `code_quality` and `code_security` from `products_status`. Ignore `failed_tests`, `flaky_tests`, and `failed_jobs` — CI data comes from STEP 1–3.\n\n> **pup mode note:** PR number resolution and `search_pr_insights` are not available in pup. Quality and Security always show \"No data available\" in pup mode.\n\n### STEP 2 — Blame Guard per Failing Job\n\nFirst check whether `@error_classification.domain` \u002F `@error_classification.type` are present on job events from STEP 1 — if populated, use them as primary classification signals.\n\nFor each failing job where classification is still needed, run both checks in parallel:\n\n**Default branch check** — was this job already failing before this PR?\n```\nTool: aggregate_datadog_ci_pipeline_events\nquery: @ci.status:error @ci.job.name:\"\u003Cjob>\" @git.branch:\u003Cdefault-branch> @git.repository.id_v2:\"\u003Crepo>\"\nci_level: job\naggregation: count\nfrom: now-24h\n```\n\n**Blast radius check** — is this job failing on other branches too?\n```\nTool: aggregate_datadog_ci_pipeline_events\nquery: @ci.status:error @ci.job.name:\"\u003Cjob>\" @git.repository.id_v2:\"\u003Crepo>\"\nci_level: job\naggregation: count\ngroup_by: [\"@git.branch\"]\nfrom: now-24h\n```\n\nPerformance fallback: if the blast radius query is slow or times out, skip it and rely on the default branch check alone.\n\n### STEP 3 — Classify Each Failure\n\n**Priority order:**\n1. If `@error_classification.domain` \u002F `@error_classification.type` present → use as primary signal\n2. If test failure AND test in `get_datadog_flaky_tests` with `flaky_test_state:active` → **flaky**\n3. Use blame guard results:\n\n| Failing on default branch? | Failing on ≥3 other branches? | Classification |\n|---|---|---|\n| Yes | Yes | **infra** (pre-existing, widespread) |\n| Yes | No | **infra** (pre-existing on default branch) |\n| No | No | **regression** (introduced by this PR) |\n| No | Yes | **flaky** (intermittent, cross-branch) |\n| Insufficient data | — | **unknown** |\n\n### STEP 4 — Produce Triage Brief\n\nOne entry per failing job:\n\n```\nPR CI Triage Brief\n==================\nBranch:   \u003Cbranch>\nRepo:     \u003Crepo>\n\nJob: \u003Cjob-name>\n  Classification:  \u003Cflaky | infra | regression | unknown>\n  Evidence:        \u003C1 key data point — error message, pipeline count, or test result>\n  Confidence:      \u003Chigh | medium | low>\n  Recommended:     \u003Caction>\n\n[repeat for each failing job]\n\nOverall: \u003CN> failures — \u003Ce.g. \"1 regression, 1 flaky, 1 infra\">\n\nPR Health\n=========\nCoverage:   \u003CX>% on \u003Cbranch> | No data available\nQuality:    \u003CN violations (X high, Y medium)> | No violations | No data available\nSecurity:   \u003CN violations> | No violations | No data available\n```\n\nAll three lines always appear. Use \"No data available\" when a tool returned no data or is unavailable (pup mode for Quality\u002FSecurity).\n\n### STEP 5 — Propose Actions\n\n**regression** → Prompt user to investigate their code changes. No write action available.\n\n**flaky** → Load `triage-flaky-test` skill for deep investigation. Invoke it once per distinct failing test name classified as flaky, passing the test name (from `@test.name` in STEP 1 results) and the derived repository as inputs. That skill will:\n- Attempt an agent-native fix using `flaky_category` + stack trace\n- Propose quarantine via `update_datadog_flaky_test_states` if a quick fix isn't possible\n\n**infra** → Before proposing a retry, assess whether the failure is transient:\n- Check `@error_classification.type` and error message for signals like `timeout`, `runner unavailable`, `network error`, `quota exceeded` — transient failures where a retry is likely to help\n- If the error is deterministic (build misconfiguration, missing secret, explicit test assertion failure), a retry is unlikely to help — suggest investigating the root cause\n- If the failure is pre-existing on the default branch, inform the user — a retry will likely fail again; await the upstream fix instead\n\nIf transient:\n\n**MCP mode — GitHub Actions:** use `retry_datadog_ci_job`. From the failing job event, collect:\n- `@ci.provider.name` → ci_provider (\"github\")\n- `@git.repository.id_v2` → repository_id\n- `@ci.job.id` → job_id\n- event `id` field → event_uuid (optional)\n\nFor `pipeline_id`: use `@ci.pipeline.id` directly if it matches `^\\d+-[1-9]\\d*$` (e.g. `26027867390-1`). If it is a bare numeric run ID, combine it with `@github.run_attempt` from the same event: `\"{@ci.pipeline.id}-{@github.run_attempt}\"`. Fallback: parse `@ci.pipeline.url` — extract `{run_id}` and `{attempt}` from `runs\u002F{run_id}\u002Fattempts\u002F{attempt}`.\n\nAfter retry returns, confirm via `search_datadog_ci_pipeline_events` (`query: @ci.job.name:\"\u003Cjob>\" @git.branch:\u003Cbranch>`, from: now-5m) that a new run appears.\n\n**Fallback \u002F pup mode — GitHub Actions:** extract the run ID from `@ci.pipeline.url`:\n```bash\ngh run rerun \u003Crun_id> --failed\n```\n\n**GitLab \u002F other providers** (both modes): share `@ci.pipeline.url` and direct to the provider UI.\n\n**unknown** → Suggest checking raw job logs via the CI provider UI or `@ci.pipeline.url` from the pipeline event.\n\n---\n\n## Tool Reference\n\nThis appendix applies only in **pup mode**. In MCP mode, use the tool names in the workflow sections directly.\n\n| MCP Tool | pup Command |\n|---|---|\n| `search_datadog_ci_pipeline_events` (ci_level: job) | `pup cicd events search --query \"...\" --level job --from 24h --limit 50` |\n| `aggregate_datadog_ci_pipeline_events` (count, group_by branch) | `pup cicd events aggregate --query \"...\" --compute count --group-by \"@git.branch\" --from 24h` |\n| `aggregate_datadog_ci_pipeline_events` (count, no group_by) | `pup cicd events aggregate --query \"...\" --compute count --from 24h` |\n| `search_datadog_test_events` | `pup cicd tests search --query \"...\" --from 24h --limit 50` |\n| `get_datadog_flaky_tests` | `pup cicd flaky-tests search --query \"flaky_test_state:active ...\"` |\n| `update_datadog_flaky_test_states` | Write body to `\u002Ftmp\u002Fflaky-update.json`, then `pup test-optimization flaky-tests update --file \u002Ftmp\u002Fflaky-update.json` |\n| `get_datadog_code_coverage_branch_summary` | `repo_lower=$(echo \"\u003Crepo>\" \\| tr '[:upper:]' '[:lower:]') && pup code-coverage branch-summary --repo \"$repo_lower\" --branch \"\u003Cbranch>\"` |\n| `get_prs_by_head_branch` | Not available in pup — skip; report \"No data available\" for Quality\u002FSecurity |\n| `search_pr_insights` | Not available in pup — skip; report \"No data available\" for Quality\u002FSecurity |\n| `retry_datadog_ci_job` | Not available in pup — use `gh run rerun \u003Crun_id> --failed` instead |\n",{"data":40,"body":45},{"name":4,"description":6,"metadata":41},{"version":42,"author":8,"repository":29,"tags":43,"alwaysApply":44},"1.0.0","datadog,ci,cicd,flaky,flaky-tests,pipeline","false",{"type":46,"children":47},"root",[48,56,62,84,88,95,106,210,218,268,271,277,355,358,364,371,376,489,495,503,513,523,532,545,551,556,566,575,585,594,599,609,618,671,692,698,719,724,734,743,753,762,767,773,781,833,965,971,976,985,990,996,1005,1029,1058,1067,1121,1126,1144,1193,1275,1295,1312,1364,1381,1397,1400,1406,1417,1654],{"type":49,"tag":50,"props":51,"children":52},"element","h1",{"id":4},[53],{"type":54,"value":55},"text","Unblock PR",{"type":49,"tag":57,"props":58,"children":59},"p",{},[60],{"type":54,"value":61},"One-line summary: Investigate a failing PR CI pipeline — attribute each failure as flaky, infra, or regression and propose a targeted action.",{"type":49,"tag":57,"props":63,"children":64},{},[65,67,74,76,82],{"type":54,"value":66},"Requires: ",{"type":49,"tag":68,"props":69,"children":71},"code",{"className":70},[],[72],{"type":54,"value":73},"dd-pup",{"type":54,"value":75}," skill (pup CLI installed and authenticated), ",{"type":49,"tag":68,"props":77,"children":79},{"className":78},[],[80],{"type":54,"value":81},"triage-flaky-test",{"type":54,"value":83}," skill (for flaky failure deep investigation).",{"type":49,"tag":85,"props":86,"children":87},"hr",{},[],{"type":49,"tag":89,"props":90,"children":92},"h2",{"id":91},"backend",[93],{"type":54,"value":94},"Backend",{"type":49,"tag":57,"props":96,"children":97},{},[98,104],{"type":49,"tag":99,"props":100,"children":101},"strong",{},[102],{"type":54,"value":103},"Detection",{"type":54,"value":105}," — At the start of every invocation, before taking any action, determine which backend to use:",{"type":49,"tag":107,"props":108,"children":109},"ol",{},[110,131,144,156,177,188],{"type":49,"tag":111,"props":112,"children":113},"li",{},[114,116,122,124,129],{"type":54,"value":115},"If the user passed ",{"type":49,"tag":68,"props":117,"children":119},{"className":118},[],[120],{"type":54,"value":121},"--backend pup",{"type":54,"value":123}," anywhere → use ",{"type":49,"tag":99,"props":125,"children":126},{},[127],{"type":54,"value":128},"pup mode",{"type":54,"value":130}," immediately. Skip steps 2–4.",{"type":49,"tag":111,"props":132,"children":133},{},[134,136,142],{"type":54,"value":135},"Check whether ",{"type":49,"tag":68,"props":137,"children":139},{"className":138},[],[140],{"type":54,"value":141},"search_datadog_ci_pipeline_events",{"type":54,"value":143}," appears in your available tools.",{"type":49,"tag":111,"props":145,"children":146},{},[147,149,154],{"type":54,"value":148},"If present → use ",{"type":49,"tag":99,"props":150,"children":151},{},[152],{"type":54,"value":153},"MCP mode",{"type":54,"value":155}," throughout. Call tools exactly as named in this skill's workflow sections.",{"type":49,"tag":111,"props":157,"children":158},{},[159,161,167,169,175],{"type":54,"value":160},"If absent → check whether ",{"type":49,"tag":68,"props":162,"children":164},{"className":163},[],[165],{"type":54,"value":166},"pup",{"type":54,"value":168}," is executable: run ",{"type":49,"tag":68,"props":170,"children":172},{"className":171},[],[173],{"type":54,"value":174},"pup --version",{"type":54,"value":176}," via Bash. If the command exits successfully (exit code 0), pup is available.",{"type":49,"tag":111,"props":178,"children":179},{},[180,182,186],{"type":54,"value":181},"If pup responds → use ",{"type":49,"tag":99,"props":183,"children":184},{},[185],{"type":54,"value":128},{"type":54,"value":187}," throughout. Translate every tool call using the Tool Reference appendix at the bottom of this file.",{"type":49,"tag":111,"props":189,"children":190},{},[191,193],{"type":54,"value":192},"If neither is available → stop and tell the user:\n",{"type":49,"tag":194,"props":195,"children":196},"blockquote",{},[197],{"type":49,"tag":57,"props":198,"children":199},{},[200,202,208],{"type":54,"value":201},"\"Neither the Datadog MCP server nor the pup CLI is available. Connect the MCP server or install pup (",{"type":49,"tag":68,"props":203,"children":205},{"className":204},[],[206],{"type":54,"value":207},"brew install datadog-labs\u002Fpack\u002Fpup",{"type":54,"value":209},").\"",{"type":49,"tag":57,"props":211,"children":212},{},[213],{"type":49,"tag":99,"props":214,"children":215},{},[216],{"type":54,"value":217},"pup invocation rules:",{"type":49,"tag":219,"props":220,"children":221},"ul",{},[222,227,248],{"type":49,"tag":111,"props":223,"children":224},{},[225],{"type":54,"value":226},"Invoke via Bash. pup always outputs JSON — parse directly.",{"type":49,"tag":111,"props":228,"children":229},{},[230,232,238,240,246],{"type":54,"value":231},"Repository IDs passed to pup must be fully lowercase (the API rejects mixed-case): ",{"type":49,"tag":68,"props":233,"children":235},{"className":234},[],[236],{"type":54,"value":237},"github.com\u002Fdatadog\u002Fmy-repo",{"type":54,"value":239},", not ",{"type":49,"tag":68,"props":241,"children":243},{"className":242},[],[244],{"type":54,"value":245},"github.com\u002FDataDog\u002Fmy-repo",{"type":54,"value":247},".",{"type":49,"tag":111,"props":249,"children":250},{},[251,253,259,261,267],{"type":54,"value":252},"If pup returns a 401\u002F403, tell the user to run ",{"type":49,"tag":68,"props":254,"children":256},{"className":255},[],[257],{"type":54,"value":258},"pup auth refresh",{"type":54,"value":260}," or ",{"type":49,"tag":68,"props":262,"children":264},{"className":263},[],[265],{"type":54,"value":266},"pup auth login",{"type":54,"value":247},{"type":49,"tag":85,"props":269,"children":270},{},[],{"type":49,"tag":89,"props":272,"children":274},{"id":273},"input",[275],{"type":54,"value":276},"Input",{"type":49,"tag":278,"props":279,"children":280},"table",{},[281,300],{"type":49,"tag":282,"props":283,"children":284},"thead",{},[285],{"type":49,"tag":286,"props":287,"children":288},"tr",{},[289,295],{"type":49,"tag":290,"props":291,"children":292},"th",{},[293],{"type":54,"value":294},"Parameter",{"type":49,"tag":290,"props":296,"children":297},{},[298],{"type":54,"value":299},"Description",{"type":49,"tag":301,"props":302,"children":303},"tbody",{},[304,326],{"type":49,"tag":286,"props":305,"children":306},{},[307,313],{"type":49,"tag":308,"props":309,"children":310},"td",{},[311],{"type":54,"value":312},"PR branch",{"type":49,"tag":308,"props":314,"children":315},{},[316,318,324],{"type":54,"value":317},"The branch under investigation (e.g. ",{"type":49,"tag":68,"props":319,"children":321},{"className":320},[],[322],{"type":54,"value":323},"my-feature-branch",{"type":54,"value":325},")",{"type":49,"tag":286,"props":327,"children":328},{},[329,334],{"type":49,"tag":308,"props":330,"children":331},{},[332],{"type":54,"value":333},"Repository",{"type":49,"tag":308,"props":335,"children":336},{},[337,339,345,347,353],{"type":54,"value":338},"Lowercase, no-schema URL (e.g. ",{"type":49,"tag":68,"props":340,"children":342},{"className":341},[],[343],{"type":54,"value":344},"github.com\u002Forg\u002Frepo",{"type":54,"value":346},"). Derive from ",{"type":49,"tag":68,"props":348,"children":350},{"className":349},[],[351],{"type":54,"value":352},"git remote get-url origin",{"type":54,"value":354}," if not provided.",{"type":49,"tag":85,"props":356,"children":357},{},[],{"type":49,"tag":89,"props":359,"children":361},{"id":360},"workflow",[362],{"type":54,"value":363},"Workflow",{"type":49,"tag":365,"props":366,"children":368},"h3",{"id":367},"step-0-parse-input",[369],{"type":54,"value":370},"STEP 0 — Parse Input",{"type":49,"tag":57,"props":372,"children":373},{},[374],{"type":54,"value":375},"Derive repository ID and default branch from git if not provided:",{"type":49,"tag":377,"props":378,"children":383},"pre",{"className":379,"code":380,"language":381,"meta":382,"style":382},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Repository ID: fully lowercase, no-schema URL (the API rejects mixed-case)\ngit remote get-url origin\n# Strip protocol and trailing .git, then lowercase the result\n# e.g. https:\u002F\u002Fgithub.com\u002FDataDog\u002Fmy-repo.git → github.com\u002Fdatadog\u002Fmy-repo\n\n# Default branch\ngit symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD\n# Strip refs\u002Fremotes\u002Forigin\u002F prefix — fall back to main if unset\n","bash","",[384],{"type":49,"tag":68,"props":385,"children":386},{"__ignoreMap":382},[387,399,425,434,443,453,462,480],{"type":49,"tag":388,"props":389,"children":392},"span",{"class":390,"line":391},"line",1,[393],{"type":49,"tag":388,"props":394,"children":396},{"style":395},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[397],{"type":54,"value":398},"# Repository ID: fully lowercase, no-schema URL (the API rejects mixed-case)\n",{"type":49,"tag":388,"props":400,"children":402},{"class":390,"line":401},2,[403,409,415,420],{"type":49,"tag":388,"props":404,"children":406},{"style":405},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[407],{"type":54,"value":408},"git",{"type":49,"tag":388,"props":410,"children":412},{"style":411},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[413],{"type":54,"value":414}," remote",{"type":49,"tag":388,"props":416,"children":417},{"style":411},[418],{"type":54,"value":419}," get-url",{"type":49,"tag":388,"props":421,"children":422},{"style":411},[423],{"type":54,"value":424}," origin\n",{"type":49,"tag":388,"props":426,"children":428},{"class":390,"line":427},3,[429],{"type":49,"tag":388,"props":430,"children":431},{"style":395},[432],{"type":54,"value":433},"# Strip protocol and trailing .git, then lowercase the result\n",{"type":49,"tag":388,"props":435,"children":437},{"class":390,"line":436},4,[438],{"type":49,"tag":388,"props":439,"children":440},{"style":395},[441],{"type":54,"value":442},"# e.g. https:\u002F\u002Fgithub.com\u002FDataDog\u002Fmy-repo.git → github.com\u002Fdatadog\u002Fmy-repo\n",{"type":49,"tag":388,"props":444,"children":446},{"class":390,"line":445},5,[447],{"type":49,"tag":388,"props":448,"children":450},{"emptyLinePlaceholder":449},true,[451],{"type":54,"value":452},"\n",{"type":49,"tag":388,"props":454,"children":456},{"class":390,"line":455},6,[457],{"type":49,"tag":388,"props":458,"children":459},{"style":395},[460],{"type":54,"value":461},"# Default branch\n",{"type":49,"tag":388,"props":463,"children":465},{"class":390,"line":464},7,[466,470,475],{"type":49,"tag":388,"props":467,"children":468},{"style":405},[469],{"type":54,"value":408},{"type":49,"tag":388,"props":471,"children":472},{"style":411},[473],{"type":54,"value":474}," symbolic-ref",{"type":49,"tag":388,"props":476,"children":477},{"style":411},[478],{"type":54,"value":479}," refs\u002Fremotes\u002Forigin\u002FHEAD\n",{"type":49,"tag":388,"props":481,"children":483},{"class":390,"line":482},8,[484],{"type":49,"tag":388,"props":485,"children":486},{"style":395},[487],{"type":54,"value":488},"# Strip refs\u002Fremotes\u002Forigin\u002F prefix — fall back to main if unset\n",{"type":49,"tag":365,"props":490,"children":492},{"id":491},"step-1-get-pr-ci-summary-run-in-parallel",[493],{"type":54,"value":494},"STEP 1 — Get PR CI Summary (run in parallel)",{"type":49,"tag":57,"props":496,"children":497},{},[498],{"type":49,"tag":99,"props":499,"children":500},{},[501],{"type":54,"value":502},"Pipeline failures:",{"type":49,"tag":377,"props":504,"children":508},{"className":505,"code":507,"language":54},[506],"language-text","Tool: search_datadog_ci_pipeline_events\nquery: @ci.status:error @git.branch:\u003Cbranch> @git.repository.id_v2:\"\u003Crepo>\"\nci_level: job\nfrom: now-24h\n",[509],{"type":49,"tag":68,"props":510,"children":511},{"__ignoreMap":382},[512],{"type":54,"value":507},{"type":49,"tag":57,"props":514,"children":515},{},[516,521],{"type":49,"tag":99,"props":517,"children":518},{},[519],{"type":54,"value":520},"Test failures",{"type":54,"value":522}," (only if pipeline results include test-runner jobs):",{"type":49,"tag":377,"props":524,"children":527},{"className":525,"code":526,"language":54},[506],"Tool: search_datadog_test_events\nquery: @test.status:fail @git.branch:\u003Cbranch> @git.repository.id_v2:\"\u003Crepo>\"\nfrom: now-24h\ntest_level: test\n",[528],{"type":49,"tag":68,"props":529,"children":530},{"__ignoreMap":382},[531],{"type":54,"value":526},{"type":49,"tag":57,"props":533,"children":534},{},[535,537,543],{"type":54,"value":536},"Run both in parallel. Collect all distinct ",{"type":49,"tag":68,"props":538,"children":540},{"className":539},[],[541],{"type":54,"value":542},"@test.service",{"type":54,"value":544}," values from test event results. If more than one distinct service is found, note each separately in the triage brief — do not collapse them into a single service filter. If pipeline results contain only infrastructure job types (build, lint, deploy) with no test-runner output, discard test results and skip to STEP 3.",{"type":49,"tag":365,"props":546,"children":548},{"id":547},"step-15-fetch-pr-health-run-in-parallel-with-step-1",[549],{"type":54,"value":550},"STEP 1.5 — Fetch PR Health (run in parallel with STEP 1)",{"type":49,"tag":57,"props":552,"children":553},{},[554],{"type":54,"value":555},"This step runs unconditionally — PR health context is valuable whether CI is red or green.",{"type":49,"tag":57,"props":557,"children":558},{},[559,564],{"type":49,"tag":99,"props":560,"children":561},{},[562],{"type":54,"value":563},"Code coverage",{"type":54,"value":565}," (both modes):",{"type":49,"tag":377,"props":567,"children":570},{"className":568,"code":569,"language":54},[506],"Tool: get_datadog_code_coverage_branch_summary\nrepository_id: \u003Crepo>\nbranch: \u003Cbranch>\n",[571],{"type":49,"tag":68,"props":572,"children":573},{"__ignoreMap":382},[574],{"type":54,"value":569},{"type":49,"tag":57,"props":576,"children":577},{},[578,583],{"type":49,"tag":99,"props":579,"children":580},{},[581],{"type":54,"value":582},"PR number resolution",{"type":54,"value":584}," (MCP mode only — skip if PR number already provided as input):",{"type":49,"tag":377,"props":586,"children":589},{"className":587,"code":588,"language":54},[506],"Tool: get_prs_by_head_branch\nrepo_url: https:\u002F\u002F\u003Crepo>\nhead_branch: \u003Cbranch>\n",[590],{"type":49,"tag":68,"props":591,"children":592},{"__ignoreMap":382},[593],{"type":54,"value":588},{"type":49,"tag":57,"props":595,"children":596},{},[597],{"type":54,"value":598},"Use the first open PR returned. If no open PR is found, skip the quality\u002Fsecurity fetch and report \"No data available\" for Quality and Security.",{"type":49,"tag":57,"props":600,"children":601},{},[602,607],{"type":49,"tag":99,"props":603,"children":604},{},[605],{"type":54,"value":606},"Code quality and security",{"type":54,"value":608}," (MCP mode only — only if PR number is available):",{"type":49,"tag":377,"props":610,"children":613},{"className":611,"code":612,"language":54},[506],"Tool: search_pr_insights\nrepo_url: https:\u002F\u002F\u003Crepo>\npr_number: \u003Cpr_number>\n",[614],{"type":49,"tag":68,"props":615,"children":616},{"__ignoreMap":382},[617],{"type":54,"value":612},{"type":49,"tag":57,"props":619,"children":620},{},[621,623,629,631,637,639,645,647,653,655,661,663,669],{"type":54,"value":622},"Extract only ",{"type":49,"tag":68,"props":624,"children":626},{"className":625},[],[627],{"type":54,"value":628},"code_quality",{"type":54,"value":630}," and ",{"type":49,"tag":68,"props":632,"children":634},{"className":633},[],[635],{"type":54,"value":636},"code_security",{"type":54,"value":638}," from ",{"type":49,"tag":68,"props":640,"children":642},{"className":641},[],[643],{"type":54,"value":644},"products_status",{"type":54,"value":646},". Ignore ",{"type":49,"tag":68,"props":648,"children":650},{"className":649},[],[651],{"type":54,"value":652},"failed_tests",{"type":54,"value":654},", ",{"type":49,"tag":68,"props":656,"children":658},{"className":657},[],[659],{"type":54,"value":660},"flaky_tests",{"type":54,"value":662},", and ",{"type":49,"tag":68,"props":664,"children":666},{"className":665},[],[667],{"type":54,"value":668},"failed_jobs",{"type":54,"value":670}," — CI data comes from STEP 1–3.",{"type":49,"tag":194,"props":672,"children":673},{},[674],{"type":49,"tag":57,"props":675,"children":676},{},[677,682,684,690],{"type":49,"tag":99,"props":678,"children":679},{},[680],{"type":54,"value":681},"pup mode note:",{"type":54,"value":683}," PR number resolution and ",{"type":49,"tag":68,"props":685,"children":687},{"className":686},[],[688],{"type":54,"value":689},"search_pr_insights",{"type":54,"value":691}," are not available in pup. Quality and Security always show \"No data available\" in pup mode.",{"type":49,"tag":365,"props":693,"children":695},{"id":694},"step-2-blame-guard-per-failing-job",[696],{"type":54,"value":697},"STEP 2 — Blame Guard per Failing Job",{"type":49,"tag":57,"props":699,"children":700},{},[701,703,709,711,717],{"type":54,"value":702},"First check whether ",{"type":49,"tag":68,"props":704,"children":706},{"className":705},[],[707],{"type":54,"value":708},"@error_classification.domain",{"type":54,"value":710}," \u002F ",{"type":49,"tag":68,"props":712,"children":714},{"className":713},[],[715],{"type":54,"value":716},"@error_classification.type",{"type":54,"value":718}," are present on job events from STEP 1 — if populated, use them as primary classification signals.",{"type":49,"tag":57,"props":720,"children":721},{},[722],{"type":54,"value":723},"For each failing job where classification is still needed, run both checks in parallel:",{"type":49,"tag":57,"props":725,"children":726},{},[727,732],{"type":49,"tag":99,"props":728,"children":729},{},[730],{"type":54,"value":731},"Default branch check",{"type":54,"value":733}," — was this job already failing before this PR?",{"type":49,"tag":377,"props":735,"children":738},{"className":736,"code":737,"language":54},[506],"Tool: aggregate_datadog_ci_pipeline_events\nquery: @ci.status:error @ci.job.name:\"\u003Cjob>\" @git.branch:\u003Cdefault-branch> @git.repository.id_v2:\"\u003Crepo>\"\nci_level: job\naggregation: count\nfrom: now-24h\n",[739],{"type":49,"tag":68,"props":740,"children":741},{"__ignoreMap":382},[742],{"type":54,"value":737},{"type":49,"tag":57,"props":744,"children":745},{},[746,751],{"type":49,"tag":99,"props":747,"children":748},{},[749],{"type":54,"value":750},"Blast radius check",{"type":54,"value":752}," — is this job failing on other branches too?",{"type":49,"tag":377,"props":754,"children":757},{"className":755,"code":756,"language":54},[506],"Tool: aggregate_datadog_ci_pipeline_events\nquery: @ci.status:error @ci.job.name:\"\u003Cjob>\" @git.repository.id_v2:\"\u003Crepo>\"\nci_level: job\naggregation: count\ngroup_by: [\"@git.branch\"]\nfrom: now-24h\n",[758],{"type":49,"tag":68,"props":759,"children":760},{"__ignoreMap":382},[761],{"type":54,"value":756},{"type":49,"tag":57,"props":763,"children":764},{},[765],{"type":54,"value":766},"Performance fallback: if the blast radius query is slow or times out, skip it and rely on the default branch check alone.",{"type":49,"tag":365,"props":768,"children":770},{"id":769},"step-3-classify-each-failure",[771],{"type":54,"value":772},"STEP 3 — Classify Each Failure",{"type":49,"tag":57,"props":774,"children":775},{},[776],{"type":49,"tag":99,"props":777,"children":778},{},[779],{"type":54,"value":780},"Priority order:",{"type":49,"tag":107,"props":782,"children":783},{},[784,802,828],{"type":49,"tag":111,"props":785,"children":786},{},[787,789,794,795,800],{"type":54,"value":788},"If ",{"type":49,"tag":68,"props":790,"children":792},{"className":791},[],[793],{"type":54,"value":708},{"type":54,"value":710},{"type":49,"tag":68,"props":796,"children":798},{"className":797},[],[799],{"type":54,"value":716},{"type":54,"value":801}," present → use as primary signal",{"type":49,"tag":111,"props":803,"children":804},{},[805,807,813,815,821,823],{"type":54,"value":806},"If test failure AND test in ",{"type":49,"tag":68,"props":808,"children":810},{"className":809},[],[811],{"type":54,"value":812},"get_datadog_flaky_tests",{"type":54,"value":814}," with ",{"type":49,"tag":68,"props":816,"children":818},{"className":817},[],[819],{"type":54,"value":820},"flaky_test_state:active",{"type":54,"value":822}," → ",{"type":49,"tag":99,"props":824,"children":825},{},[826],{"type":54,"value":827},"flaky",{"type":49,"tag":111,"props":829,"children":830},{},[831],{"type":54,"value":832},"Use blame guard results:",{"type":49,"tag":278,"props":834,"children":835},{},[836,857],{"type":49,"tag":282,"props":837,"children":838},{},[839],{"type":49,"tag":286,"props":840,"children":841},{},[842,847,852],{"type":49,"tag":290,"props":843,"children":844},{},[845],{"type":54,"value":846},"Failing on default branch?",{"type":49,"tag":290,"props":848,"children":849},{},[850],{"type":54,"value":851},"Failing on ≥3 other branches?",{"type":49,"tag":290,"props":853,"children":854},{},[855],{"type":54,"value":856},"Classification",{"type":49,"tag":301,"props":858,"children":859},{},[860,882,903,924,944],{"type":49,"tag":286,"props":861,"children":862},{},[863,868,872],{"type":49,"tag":308,"props":864,"children":865},{},[866],{"type":54,"value":867},"Yes",{"type":49,"tag":308,"props":869,"children":870},{},[871],{"type":54,"value":867},{"type":49,"tag":308,"props":873,"children":874},{},[875,880],{"type":49,"tag":99,"props":876,"children":877},{},[878],{"type":54,"value":879},"infra",{"type":54,"value":881}," (pre-existing, widespread)",{"type":49,"tag":286,"props":883,"children":884},{},[885,889,894],{"type":49,"tag":308,"props":886,"children":887},{},[888],{"type":54,"value":867},{"type":49,"tag":308,"props":890,"children":891},{},[892],{"type":54,"value":893},"No",{"type":49,"tag":308,"props":895,"children":896},{},[897,901],{"type":49,"tag":99,"props":898,"children":899},{},[900],{"type":54,"value":879},{"type":54,"value":902}," (pre-existing on default branch)",{"type":49,"tag":286,"props":904,"children":905},{},[906,910,914],{"type":49,"tag":308,"props":907,"children":908},{},[909],{"type":54,"value":893},{"type":49,"tag":308,"props":911,"children":912},{},[913],{"type":54,"value":893},{"type":49,"tag":308,"props":915,"children":916},{},[917,922],{"type":49,"tag":99,"props":918,"children":919},{},[920],{"type":54,"value":921},"regression",{"type":54,"value":923}," (introduced by this PR)",{"type":49,"tag":286,"props":925,"children":926},{},[927,931,935],{"type":49,"tag":308,"props":928,"children":929},{},[930],{"type":54,"value":893},{"type":49,"tag":308,"props":932,"children":933},{},[934],{"type":54,"value":867},{"type":49,"tag":308,"props":936,"children":937},{},[938,942],{"type":49,"tag":99,"props":939,"children":940},{},[941],{"type":54,"value":827},{"type":54,"value":943}," (intermittent, cross-branch)",{"type":49,"tag":286,"props":945,"children":946},{},[947,952,957],{"type":49,"tag":308,"props":948,"children":949},{},[950],{"type":54,"value":951},"Insufficient data",{"type":49,"tag":308,"props":953,"children":954},{},[955],{"type":54,"value":956},"—",{"type":49,"tag":308,"props":958,"children":959},{},[960],{"type":49,"tag":99,"props":961,"children":962},{},[963],{"type":54,"value":964},"unknown",{"type":49,"tag":365,"props":966,"children":968},{"id":967},"step-4-produce-triage-brief",[969],{"type":54,"value":970},"STEP 4 — Produce Triage Brief",{"type":49,"tag":57,"props":972,"children":973},{},[974],{"type":54,"value":975},"One entry per failing job:",{"type":49,"tag":377,"props":977,"children":980},{"className":978,"code":979,"language":54},[506],"PR CI Triage Brief\n==================\nBranch:   \u003Cbranch>\nRepo:     \u003Crepo>\n\nJob: \u003Cjob-name>\n  Classification:  \u003Cflaky | infra | regression | unknown>\n  Evidence:        \u003C1 key data point — error message, pipeline count, or test result>\n  Confidence:      \u003Chigh | medium | low>\n  Recommended:     \u003Caction>\n\n[repeat for each failing job]\n\nOverall: \u003CN> failures — \u003Ce.g. \"1 regression, 1 flaky, 1 infra\">\n\nPR Health\n=========\nCoverage:   \u003CX>% on \u003Cbranch> | No data available\nQuality:    \u003CN violations (X high, Y medium)> | No violations | No data available\nSecurity:   \u003CN violations> | No violations | No data available\n",[981],{"type":49,"tag":68,"props":982,"children":983},{"__ignoreMap":382},[984],{"type":54,"value":979},{"type":49,"tag":57,"props":986,"children":987},{},[988],{"type":54,"value":989},"All three lines always appear. Use \"No data available\" when a tool returned no data or is unavailable (pup mode for Quality\u002FSecurity).",{"type":49,"tag":365,"props":991,"children":993},{"id":992},"step-5-propose-actions",[994],{"type":54,"value":995},"STEP 5 — Propose Actions",{"type":49,"tag":57,"props":997,"children":998},{},[999,1003],{"type":49,"tag":99,"props":1000,"children":1001},{},[1002],{"type":54,"value":921},{"type":54,"value":1004}," → Prompt user to investigate their code changes. No write action available.",{"type":49,"tag":57,"props":1006,"children":1007},{},[1008,1012,1014,1019,1021,1027],{"type":49,"tag":99,"props":1009,"children":1010},{},[1011],{"type":54,"value":827},{"type":54,"value":1013}," → Load ",{"type":49,"tag":68,"props":1015,"children":1017},{"className":1016},[],[1018],{"type":54,"value":81},{"type":54,"value":1020}," skill for deep investigation. Invoke it once per distinct failing test name classified as flaky, passing the test name (from ",{"type":49,"tag":68,"props":1022,"children":1024},{"className":1023},[],[1025],{"type":54,"value":1026},"@test.name",{"type":54,"value":1028}," in STEP 1 results) and the derived repository as inputs. That skill will:",{"type":49,"tag":219,"props":1030,"children":1031},{},[1032,1045],{"type":49,"tag":111,"props":1033,"children":1034},{},[1035,1037,1043],{"type":54,"value":1036},"Attempt an agent-native fix using ",{"type":49,"tag":68,"props":1038,"children":1040},{"className":1039},[],[1041],{"type":54,"value":1042},"flaky_category",{"type":54,"value":1044}," + stack trace",{"type":49,"tag":111,"props":1046,"children":1047},{},[1048,1050,1056],{"type":54,"value":1049},"Propose quarantine via ",{"type":49,"tag":68,"props":1051,"children":1053},{"className":1052},[],[1054],{"type":54,"value":1055},"update_datadog_flaky_test_states",{"type":54,"value":1057}," if a quick fix isn't possible",{"type":49,"tag":57,"props":1059,"children":1060},{},[1061,1065],{"type":49,"tag":99,"props":1062,"children":1063},{},[1064],{"type":54,"value":879},{"type":54,"value":1066}," → Before proposing a retry, assess whether the failure is transient:",{"type":49,"tag":219,"props":1068,"children":1069},{},[1070,1111,1116],{"type":49,"tag":111,"props":1071,"children":1072},{},[1073,1075,1080,1082,1088,1089,1095,1096,1102,1103,1109],{"type":54,"value":1074},"Check ",{"type":49,"tag":68,"props":1076,"children":1078},{"className":1077},[],[1079],{"type":54,"value":716},{"type":54,"value":1081}," and error message for signals like ",{"type":49,"tag":68,"props":1083,"children":1085},{"className":1084},[],[1086],{"type":54,"value":1087},"timeout",{"type":54,"value":654},{"type":49,"tag":68,"props":1090,"children":1092},{"className":1091},[],[1093],{"type":54,"value":1094},"runner unavailable",{"type":54,"value":654},{"type":49,"tag":68,"props":1097,"children":1099},{"className":1098},[],[1100],{"type":54,"value":1101},"network error",{"type":54,"value":654},{"type":49,"tag":68,"props":1104,"children":1106},{"className":1105},[],[1107],{"type":54,"value":1108},"quota exceeded",{"type":54,"value":1110}," — transient failures where a retry is likely to help",{"type":49,"tag":111,"props":1112,"children":1113},{},[1114],{"type":54,"value":1115},"If the error is deterministic (build misconfiguration, missing secret, explicit test assertion failure), a retry is unlikely to help — suggest investigating the root cause",{"type":49,"tag":111,"props":1117,"children":1118},{},[1119],{"type":54,"value":1120},"If the failure is pre-existing on the default branch, inform the user — a retry will likely fail again; await the upstream fix instead",{"type":49,"tag":57,"props":1122,"children":1123},{},[1124],{"type":54,"value":1125},"If transient:",{"type":49,"tag":57,"props":1127,"children":1128},{},[1129,1134,1136,1142],{"type":49,"tag":99,"props":1130,"children":1131},{},[1132],{"type":54,"value":1133},"MCP mode — GitHub Actions:",{"type":54,"value":1135}," use ",{"type":49,"tag":68,"props":1137,"children":1139},{"className":1138},[],[1140],{"type":54,"value":1141},"retry_datadog_ci_job",{"type":54,"value":1143},". From the failing job event, collect:",{"type":49,"tag":219,"props":1145,"children":1146},{},[1147,1158,1169,1180],{"type":49,"tag":111,"props":1148,"children":1149},{},[1150,1156],{"type":49,"tag":68,"props":1151,"children":1153},{"className":1152},[],[1154],{"type":54,"value":1155},"@ci.provider.name",{"type":54,"value":1157}," → ci_provider (\"github\")",{"type":49,"tag":111,"props":1159,"children":1160},{},[1161,1167],{"type":49,"tag":68,"props":1162,"children":1164},{"className":1163},[],[1165],{"type":54,"value":1166},"@git.repository.id_v2",{"type":54,"value":1168}," → repository_id",{"type":49,"tag":111,"props":1170,"children":1171},{},[1172,1178],{"type":49,"tag":68,"props":1173,"children":1175},{"className":1174},[],[1176],{"type":54,"value":1177},"@ci.job.id",{"type":54,"value":1179}," → job_id",{"type":49,"tag":111,"props":1181,"children":1182},{},[1183,1185,1191],{"type":54,"value":1184},"event ",{"type":49,"tag":68,"props":1186,"children":1188},{"className":1187},[],[1189],{"type":54,"value":1190},"id",{"type":54,"value":1192}," field → event_uuid (optional)",{"type":49,"tag":57,"props":1194,"children":1195},{},[1196,1198,1204,1206,1212,1214,1220,1222,1228,1230,1236,1238,1244,1246,1252,1254,1260,1261,1267,1268,1274],{"type":54,"value":1197},"For ",{"type":49,"tag":68,"props":1199,"children":1201},{"className":1200},[],[1202],{"type":54,"value":1203},"pipeline_id",{"type":54,"value":1205},": use ",{"type":49,"tag":68,"props":1207,"children":1209},{"className":1208},[],[1210],{"type":54,"value":1211},"@ci.pipeline.id",{"type":54,"value":1213}," directly if it matches ",{"type":49,"tag":68,"props":1215,"children":1217},{"className":1216},[],[1218],{"type":54,"value":1219},"^\\d+-[1-9]\\d*$",{"type":54,"value":1221}," (e.g. ",{"type":49,"tag":68,"props":1223,"children":1225},{"className":1224},[],[1226],{"type":54,"value":1227},"26027867390-1",{"type":54,"value":1229},"). If it is a bare numeric run ID, combine it with ",{"type":49,"tag":68,"props":1231,"children":1233},{"className":1232},[],[1234],{"type":54,"value":1235},"@github.run_attempt",{"type":54,"value":1237}," from the same event: ",{"type":49,"tag":68,"props":1239,"children":1241},{"className":1240},[],[1242],{"type":54,"value":1243},"\"{@ci.pipeline.id}-{@github.run_attempt}\"",{"type":54,"value":1245},". Fallback: parse ",{"type":49,"tag":68,"props":1247,"children":1249},{"className":1248},[],[1250],{"type":54,"value":1251},"@ci.pipeline.url",{"type":54,"value":1253}," — extract ",{"type":49,"tag":68,"props":1255,"children":1257},{"className":1256},[],[1258],{"type":54,"value":1259},"{run_id}",{"type":54,"value":630},{"type":49,"tag":68,"props":1262,"children":1264},{"className":1263},[],[1265],{"type":54,"value":1266},"{attempt}",{"type":54,"value":638},{"type":49,"tag":68,"props":1269,"children":1271},{"className":1270},[],[1272],{"type":54,"value":1273},"runs\u002F{run_id}\u002Fattempts\u002F{attempt}",{"type":54,"value":247},{"type":49,"tag":57,"props":1276,"children":1277},{},[1278,1280,1285,1287,1293],{"type":54,"value":1279},"After retry returns, confirm via ",{"type":49,"tag":68,"props":1281,"children":1283},{"className":1282},[],[1284],{"type":54,"value":141},{"type":54,"value":1286}," (",{"type":49,"tag":68,"props":1288,"children":1290},{"className":1289},[],[1291],{"type":54,"value":1292},"query: @ci.job.name:\"\u003Cjob>\" @git.branch:\u003Cbranch>",{"type":54,"value":1294},", from: now-5m) that a new run appears.",{"type":49,"tag":57,"props":1296,"children":1297},{},[1298,1303,1305,1310],{"type":49,"tag":99,"props":1299,"children":1300},{},[1301],{"type":54,"value":1302},"Fallback \u002F pup mode — GitHub Actions:",{"type":54,"value":1304}," extract the run ID from ",{"type":49,"tag":68,"props":1306,"children":1308},{"className":1307},[],[1309],{"type":54,"value":1251},{"type":54,"value":1311},":",{"type":49,"tag":377,"props":1313,"children":1315},{"className":379,"code":1314,"language":381,"meta":382,"style":382},"gh run rerun \u003Crun_id> --failed\n",[1316],{"type":49,"tag":68,"props":1317,"children":1318},{"__ignoreMap":382},[1319],{"type":49,"tag":388,"props":1320,"children":1321},{"class":390,"line":391},[1322,1327,1332,1337,1343,1348,1354,1359],{"type":49,"tag":388,"props":1323,"children":1324},{"style":405},[1325],{"type":54,"value":1326},"gh",{"type":49,"tag":388,"props":1328,"children":1329},{"style":411},[1330],{"type":54,"value":1331}," run",{"type":49,"tag":388,"props":1333,"children":1334},{"style":411},[1335],{"type":54,"value":1336}," rerun",{"type":49,"tag":388,"props":1338,"children":1340},{"style":1339},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[1341],{"type":54,"value":1342}," \u003C",{"type":49,"tag":388,"props":1344,"children":1345},{"style":411},[1346],{"type":54,"value":1347},"run_i",{"type":49,"tag":388,"props":1349,"children":1351},{"style":1350},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[1352],{"type":54,"value":1353},"d",{"type":49,"tag":388,"props":1355,"children":1356},{"style":1339},[1357],{"type":54,"value":1358},">",{"type":49,"tag":388,"props":1360,"children":1361},{"style":411},[1362],{"type":54,"value":1363}," --failed\n",{"type":49,"tag":57,"props":1365,"children":1366},{},[1367,1372,1374,1379],{"type":49,"tag":99,"props":1368,"children":1369},{},[1370],{"type":54,"value":1371},"GitLab \u002F other providers",{"type":54,"value":1373}," (both modes): share ",{"type":49,"tag":68,"props":1375,"children":1377},{"className":1376},[],[1378],{"type":54,"value":1251},{"type":54,"value":1380}," and direct to the provider UI.",{"type":49,"tag":57,"props":1382,"children":1383},{},[1384,1388,1390,1395],{"type":49,"tag":99,"props":1385,"children":1386},{},[1387],{"type":54,"value":964},{"type":54,"value":1389}," → Suggest checking raw job logs via the CI provider UI or ",{"type":49,"tag":68,"props":1391,"children":1393},{"className":1392},[],[1394],{"type":54,"value":1251},{"type":54,"value":1396}," from the pipeline event.",{"type":49,"tag":85,"props":1398,"children":1399},{},[],{"type":49,"tag":89,"props":1401,"children":1403},{"id":1402},"tool-reference",[1404],{"type":54,"value":1405},"Tool Reference",{"type":49,"tag":57,"props":1407,"children":1408},{},[1409,1411,1415],{"type":54,"value":1410},"This appendix applies only in ",{"type":49,"tag":99,"props":1412,"children":1413},{},[1414],{"type":54,"value":128},{"type":54,"value":1416},". In MCP mode, use the tool names in the workflow sections directly.",{"type":49,"tag":278,"props":1418,"children":1419},{},[1420,1436],{"type":49,"tag":282,"props":1421,"children":1422},{},[1423],{"type":49,"tag":286,"props":1424,"children":1425},{},[1426,1431],{"type":49,"tag":290,"props":1427,"children":1428},{},[1429],{"type":54,"value":1430},"MCP Tool",{"type":49,"tag":290,"props":1432,"children":1433},{},[1434],{"type":54,"value":1435},"pup Command",{"type":49,"tag":301,"props":1437,"children":1438},{},[1439,1461,1484,1506,1527,1547,1577,1598,1615,1630],{"type":49,"tag":286,"props":1440,"children":1441},{},[1442,1452],{"type":49,"tag":308,"props":1443,"children":1444},{},[1445,1450],{"type":49,"tag":68,"props":1446,"children":1448},{"className":1447},[],[1449],{"type":54,"value":141},{"type":54,"value":1451}," (ci_level: job)",{"type":49,"tag":308,"props":1453,"children":1454},{},[1455],{"type":49,"tag":68,"props":1456,"children":1458},{"className":1457},[],[1459],{"type":54,"value":1460},"pup cicd events search --query \"...\" --level job --from 24h --limit 50",{"type":49,"tag":286,"props":1462,"children":1463},{},[1464,1475],{"type":49,"tag":308,"props":1465,"children":1466},{},[1467,1473],{"type":49,"tag":68,"props":1468,"children":1470},{"className":1469},[],[1471],{"type":54,"value":1472},"aggregate_datadog_ci_pipeline_events",{"type":54,"value":1474}," (count, group_by branch)",{"type":49,"tag":308,"props":1476,"children":1477},{},[1478],{"type":49,"tag":68,"props":1479,"children":1481},{"className":1480},[],[1482],{"type":54,"value":1483},"pup cicd events aggregate --query \"...\" --compute count --group-by \"@git.branch\" --from 24h",{"type":49,"tag":286,"props":1485,"children":1486},{},[1487,1497],{"type":49,"tag":308,"props":1488,"children":1489},{},[1490,1495],{"type":49,"tag":68,"props":1491,"children":1493},{"className":1492},[],[1494],{"type":54,"value":1472},{"type":54,"value":1496}," (count, no group_by)",{"type":49,"tag":308,"props":1498,"children":1499},{},[1500],{"type":49,"tag":68,"props":1501,"children":1503},{"className":1502},[],[1504],{"type":54,"value":1505},"pup cicd events aggregate --query \"...\" --compute count --from 24h",{"type":49,"tag":286,"props":1507,"children":1508},{},[1509,1518],{"type":49,"tag":308,"props":1510,"children":1511},{},[1512],{"type":49,"tag":68,"props":1513,"children":1515},{"className":1514},[],[1516],{"type":54,"value":1517},"search_datadog_test_events",{"type":49,"tag":308,"props":1519,"children":1520},{},[1521],{"type":49,"tag":68,"props":1522,"children":1524},{"className":1523},[],[1525],{"type":54,"value":1526},"pup cicd tests search --query \"...\" --from 24h --limit 50",{"type":49,"tag":286,"props":1528,"children":1529},{},[1530,1538],{"type":49,"tag":308,"props":1531,"children":1532},{},[1533],{"type":49,"tag":68,"props":1534,"children":1536},{"className":1535},[],[1537],{"type":54,"value":812},{"type":49,"tag":308,"props":1539,"children":1540},{},[1541],{"type":49,"tag":68,"props":1542,"children":1544},{"className":1543},[],[1545],{"type":54,"value":1546},"pup cicd flaky-tests search --query \"flaky_test_state:active ...\"",{"type":49,"tag":286,"props":1548,"children":1549},{},[1550,1558],{"type":49,"tag":308,"props":1551,"children":1552},{},[1553],{"type":49,"tag":68,"props":1554,"children":1556},{"className":1555},[],[1557],{"type":54,"value":1055},{"type":49,"tag":308,"props":1559,"children":1560},{},[1561,1563,1569,1571],{"type":54,"value":1562},"Write body to ",{"type":49,"tag":68,"props":1564,"children":1566},{"className":1565},[],[1567],{"type":54,"value":1568},"\u002Ftmp\u002Fflaky-update.json",{"type":54,"value":1570},", then ",{"type":49,"tag":68,"props":1572,"children":1574},{"className":1573},[],[1575],{"type":54,"value":1576},"pup test-optimization flaky-tests update --file \u002Ftmp\u002Fflaky-update.json",{"type":49,"tag":286,"props":1578,"children":1579},{},[1580,1589],{"type":49,"tag":308,"props":1581,"children":1582},{},[1583],{"type":49,"tag":68,"props":1584,"children":1586},{"className":1585},[],[1587],{"type":54,"value":1588},"get_datadog_code_coverage_branch_summary",{"type":49,"tag":308,"props":1590,"children":1591},{},[1592],{"type":49,"tag":68,"props":1593,"children":1595},{"className":1594},[],[1596],{"type":54,"value":1597},"repo_lower=$(echo \"\u003Crepo>\" | tr '[:upper:]' '[:lower:]') && pup code-coverage branch-summary --repo \"$repo_lower\" --branch \"\u003Cbranch>\"",{"type":49,"tag":286,"props":1599,"children":1600},{},[1601,1610],{"type":49,"tag":308,"props":1602,"children":1603},{},[1604],{"type":49,"tag":68,"props":1605,"children":1607},{"className":1606},[],[1608],{"type":54,"value":1609},"get_prs_by_head_branch",{"type":49,"tag":308,"props":1611,"children":1612},{},[1613],{"type":54,"value":1614},"Not available in pup — skip; report \"No data available\" for Quality\u002FSecurity",{"type":49,"tag":286,"props":1616,"children":1617},{},[1618,1626],{"type":49,"tag":308,"props":1619,"children":1620},{},[1621],{"type":49,"tag":68,"props":1622,"children":1624},{"className":1623},[],[1625],{"type":54,"value":689},{"type":49,"tag":308,"props":1627,"children":1628},{},[1629],{"type":54,"value":1614},{"type":49,"tag":286,"props":1631,"children":1632},{},[1633,1641],{"type":49,"tag":308,"props":1634,"children":1635},{},[1636],{"type":49,"tag":68,"props":1637,"children":1639},{"className":1638},[],[1640],{"type":54,"value":1141},{"type":49,"tag":308,"props":1642,"children":1643},{},[1644,1646,1652],{"type":54,"value":1645},"Not available in pup — use ",{"type":49,"tag":68,"props":1647,"children":1649},{"className":1648},[],[1650],{"type":54,"value":1651},"gh run rerun \u003Crun_id> --failed",{"type":54,"value":1653}," instead",{"type":49,"tag":1655,"props":1656,"children":1657},"style",{},[1658],{"type":54,"value":1659},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1661,"total":1764},[1662,1677,1693,1704,1720,1734,1750],{"slug":1663,"name":1663,"fn":1664,"description":1665,"org":1666,"tags":1667,"stars":28,"repoUrl":29,"updatedAt":1676},"agent-install","install Datadog Agent on Kubernetes","Install the Datadog Agent on Kubernetes using the Datadog Operator — required before enabling Single Step Instrumentation (SSI), which automatically instruments applications for APM without code changes. Only use if no Datadog Agent is deployed on the cluster yet.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1668,1669,1672,1675],{"name":17,"slug":18,"type":15},{"name":1670,"slug":1671,"type":15},"Deployment","deployment",{"name":1673,"slug":1674,"type":15},"Kubernetes","kubernetes",{"name":13,"slug":14,"type":15},"2026-04-15T04:57:27.489805",{"slug":1678,"name":1678,"fn":1679,"description":1680,"org":1681,"tags":1682,"stars":28,"repoUrl":29,"updatedAt":1692},"agent-observability-auto-experiment","run iterative code improvements using Datadog data","Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and repeats. Use when the user says \"run an auto experiment\", \"hill-climb this code\", \"iteratively improve X and measure the delta\", \"optimize this prompt\u002Ffile against my traces\", \"auto-optimize against LLM-Obs\", or wants the local equivalent of the auto_experiments worker. Works from a local dataset file, an ml_app, a dataset_id, or a list of trace_ids.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1683,1684,1685,1688,1691],{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":1686,"slug":1687,"type":15},"Evals","evals",{"name":1689,"slug":1690,"type":15},"LLM","llm",{"name":13,"slug":14,"type":15},"2026-07-31T05:52:13.711906",{"slug":1694,"name":1694,"fn":1695,"description":1696,"org":1697,"tags":1698,"stars":28,"repoUrl":29,"updatedAt":1703},"agent-observability-eval-bootstrap","bootstrap evaluators from production traces","Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says \"bootstrap evaluators\", \"generate evaluators\", \"create evals from traces\", \"eval bootstrap\", \"write evaluators\", \"build eval suite\", \"publish evaluators\", or wants to generate BaseEvaluator\u002FLLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1699,1700,1701,1702],{"name":17,"slug":18,"type":15},{"name":1686,"slug":1687,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:19.259734",{"slug":1705,"name":1705,"fn":1706,"description":1707,"org":1708,"tags":1709,"stars":28,"repoUrl":29,"updatedAt":1719},"agent-observability-eval-pipeline","run agent observability and evaluation pipelines","End-to-end Agent Observability pipeline for an instrumented ml_app — classify production traces, root-cause failures, bootstrap evaluators, then (optionally) sample + publish a dataset, generate + run an experiment, and analyze results. Six narrated phases with a standardized banner and a \"continue\" checkpoint between each. Pure orchestration over the agent-observability sub-skills (`agent-observability-session-classify`, `agent-observability-trace-rca`, `agent-observability-eval-bootstrap`, `agent-observability-experiment-py-bootstrap`, `agent-observability-experiment-analyzer`). Use when user says \"run the eval pipeline\", \"go from traces to evals\", \"bootstrap evals end to end\", \"classify then RCA then bootstrap\", \"build an eval set from scratch\", \"onboard me to datasets and experiments\", \"walk me through experiments\", \"I have an ml_app, now what\", \"Agent Observability onboarding\", \"guided experiment setup\", \"from traces to experiments\", or wants a deterministic, narrated tour from production data through evaluators, datasets, and experiments. Stop early with `--stop-after \u003Cphase>` to short-circuit at evaluators or dataset, or resume mid-flow with `--start-at \u003Cphase>`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1710,1713,1716,1717,1718],{"name":1711,"slug":1712,"type":15},"Agents","agents",{"name":1714,"slug":1715,"type":15},"Data Pipeline","data-pipeline",{"name":17,"slug":18,"type":15},{"name":1686,"slug":1687,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:17.231423",{"slug":1721,"name":1721,"fn":1722,"description":1723,"org":1724,"tags":1725,"stars":28,"repoUrl":29,"updatedAt":1733},"agent-observability-experiment-analyzer","analyze LLM experiment results","Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says \"analyze experiment\", \"compare experiments\", \"analyze against baseline\", or provides one or two experiment IDs for analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1726,1729,1730,1731,1732],{"name":1727,"slug":1728,"type":15},"Analytics","analytics",{"name":17,"slug":18,"type":15},{"name":1686,"slug":1687,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:21.212498",{"slug":1735,"name":1735,"fn":1736,"description":1737,"org":1738,"tags":1739,"stars":28,"repoUrl":29,"updatedAt":1749},"agent-observability-experiment-py-bootstrap","generate Python experiment clients for LLM observability","Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says \"generate Python experiment\", \"write an SDK experiment\", \"create a ddtrace experiment\", \"Python notebook experiment\", \"use the Agent Observability SDK\", or has `ddtrace` installed and wants idiomatic SDK code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1740,1741,1744,1745,1746],{"name":17,"slug":18,"type":15},{"name":1742,"slug":1743,"type":15},"Jupyter","jupyter",{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},{"name":1747,"slug":1748,"type":15},"Python","python","2026-06-19T09:04:22.640384",{"slug":1751,"name":1751,"fn":1752,"description":1753,"org":1754,"tags":1755,"stars":28,"repoUrl":29,"updatedAt":1763},"agent-observability-replay-trace","iterate on LLM traces with local code","Use when a developer wants to iterate on ONE specific Agent Observability \u002F LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as \u002Fagent-observability-replay-trace \u003Ctrace-id> [changes to test]. Signals: \"replay this trace\"; \"iterate on a trace\"; \"this trace's output is wrong, fix it and re-run\"; \"re-run trace \u003Cid> with \u003Cchange>\"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace \u002F LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser \"Replay\" button (that's agent-observability-replay-experiment), building an experiment from a dataset\u002FCSV, writing evaluators, root-causing failed traces, or RUM\u002FHTTP session replay.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1756,1757,1758,1759,1760],{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},{"name":1761,"slug":1762,"type":15},"Tracing","tracing","2026-07-31T05:52:08.594182",34,{"items":1766,"total":1892},[1767,1774,1782,1789,1797,1805,1813,1821,1833,1845,1857,1877],{"slug":1663,"name":1663,"fn":1664,"description":1665,"org":1768,"tags":1769,"stars":28,"repoUrl":29,"updatedAt":1676},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1770,1771,1772,1773],{"name":17,"slug":18,"type":15},{"name":1670,"slug":1671,"type":15},{"name":1673,"slug":1674,"type":15},{"name":13,"slug":14,"type":15},{"slug":1678,"name":1678,"fn":1679,"description":1680,"org":1775,"tags":1776,"stars":28,"repoUrl":29,"updatedAt":1692},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1777,1778,1779,1780,1781],{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":1686,"slug":1687,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},{"slug":1694,"name":1694,"fn":1695,"description":1696,"org":1783,"tags":1784,"stars":28,"repoUrl":29,"updatedAt":1703},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1785,1786,1787,1788],{"name":17,"slug":18,"type":15},{"name":1686,"slug":1687,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},{"slug":1705,"name":1705,"fn":1706,"description":1707,"org":1790,"tags":1791,"stars":28,"repoUrl":29,"updatedAt":1719},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1792,1793,1794,1795,1796],{"name":1711,"slug":1712,"type":15},{"name":1714,"slug":1715,"type":15},{"name":17,"slug":18,"type":15},{"name":1686,"slug":1687,"type":15},{"name":13,"slug":14,"type":15},{"slug":1721,"name":1721,"fn":1722,"description":1723,"org":1798,"tags":1799,"stars":28,"repoUrl":29,"updatedAt":1733},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1800,1801,1802,1803,1804],{"name":1727,"slug":1728,"type":15},{"name":17,"slug":18,"type":15},{"name":1686,"slug":1687,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},{"slug":1735,"name":1735,"fn":1736,"description":1737,"org":1806,"tags":1807,"stars":28,"repoUrl":29,"updatedAt":1749},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1808,1809,1810,1811,1812],{"name":17,"slug":18,"type":15},{"name":1742,"slug":1743,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},{"name":1747,"slug":1748,"type":15},{"slug":1751,"name":1751,"fn":1752,"description":1753,"org":1814,"tags":1815,"stars":28,"repoUrl":29,"updatedAt":1763},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1816,1817,1818,1819,1820],{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},{"name":1761,"slug":1762,"type":15},{"slug":1822,"name":1822,"fn":1823,"description":1824,"org":1825,"tags":1826,"stars":28,"repoUrl":29,"updatedAt":1832},"agent-observability-session-classify","evaluate user intent satisfaction in sessions","Classify whether user intent was satisfied in a Datadog Agent Observability trace or session. Three modes: (1) session_id — classify a single CMD+I assistant session with RUM; (2) trace_id — classify a single Agent Observability trace without RUM; (3) ml_app — sample and classify multiple sessions or traces from a given LLM app. Output is compact by default (verdict + one-sentence reason). Use when evaluating satisfaction, classifying sessions\u002Ftraces, labeling data, or generating signal for agent-observability-eval-pipeline or agent-observability-trace-rca.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1827,1828,1829,1830,1831],{"name":1727,"slug":1728,"type":15},{"name":17,"slug":18,"type":15},{"name":1686,"slug":1687,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:26.341497",{"slug":1834,"name":1834,"fn":1835,"description":1836,"org":1837,"tags":1838,"stars":28,"repoUrl":29,"updatedAt":1844},"agent-observability-trace-rca","diagnose LLM application failures from traces","Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural anomalies depending on what signals are present. Walks the span tree from symptom to root cause. Use when user says \"what's wrong with my app\", \"why is my eval failing\", \"analyze errors\", \"root cause analysis\", \"diagnose failures\", or wants to understand production failure patterns.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1839,1840,1841,1842,1843],{"name":17,"slug":18,"type":15},{"name":23,"slug":24,"type":15},{"name":1686,"slug":1687,"type":15},{"name":1689,"slug":1690,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:24.316244",{"slug":1846,"name":1846,"fn":1847,"description":1848,"org":1849,"tags":1850,"stars":28,"repoUrl":29,"updatedAt":1856},"agent-skills","use Datadog observability skills","Datadog skills for AI agents. Essential monitoring, logging, tracing and observability.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1851,1852,1855],{"name":17,"slug":18,"type":15},{"name":1853,"slug":1854,"type":15},"Monitoring","monitoring",{"name":13,"slug":14,"type":15},"2026-04-06T18:08:33.337476",{"slug":1858,"name":1858,"fn":1859,"description":1860,"org":1861,"tags":1862,"stars":28,"repoUrl":29,"updatedAt":1876},"datadog-app","build and manage Datadog applications","Guides developers building Datadog Apps with TypeScript, React, the @datadog\u002Fapps scaffolder, and @datadog\u002Fvite-plugin. Use when a user wants to scaffold, run, debug, upgrade, build, upload, publish, upload without publishing (draft upload), add an upload-no-publish script, set up CI\u002FCD, use OAuth or API\u002Fapplication key auth, trigger\u002Fpoll Workflow Automation, choose DDSQL or Action Catalog for backend data access, or query app datastores with DDSQL, including backend function troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1863,1864,1867,1870,1873],{"name":17,"slug":18,"type":15},{"name":1865,"slug":1866,"type":15},"Frontend","frontend",{"name":1868,"slug":1869,"type":15},"React","react",{"name":1871,"slug":1872,"type":15},"TypeScript","typescript",{"name":1874,"slug":1875,"type":15},"Vite","vite","2026-06-18T08:01:32.562331",{"slug":1878,"name":1878,"fn":1879,"description":1880,"org":1881,"tags":1882,"stars":28,"repoUrl":29,"updatedAt":1891},"dd-apm","query Datadog APM traces","APM - install, onboard, instrument, enable, set up, configure, traces, services, dependencies, performance analysis. Use for any request involving Datadog APM setup, instrumentation (SSI, ddtrace, agent install), or analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1883,1884,1887,1888],{"name":17,"slug":18,"type":15},{"name":1885,"slug":1886,"type":15},"Distributed Tracing","distributed-tracing",{"name":13,"slug":14,"type":15},{"name":1889,"slug":1890,"type":15},"Performance","performance","2026-04-06T18:08:34.575282",35]