[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-datadog-labs-incognito":3,"mdc--4unkwn-key":32,"related-repo-datadog-labs-incognito":338,"related-org-datadog-labs-incognito":347},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":30,"mdContent":31},"incognito","toggle incognito mode for sessions","Toggle Trajectory incognito mode for the current OpenCode session. Use when the user says \"\u002Fincognito\", \"go incognito\", \"pause capture\", \"stop recording\", \"private mode\", or asks to temporarily suppress Datadog publish for sensitive work.",{"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],{"name":13,"slug":14,"type":15},"Observability","observability","tag",{"name":17,"slug":18,"type":15},"Datadog","datadog",{"name":20,"slug":21,"type":15},"Privacy","privacy",8,"https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Ftrajectory","2026-07-21T05:38:44.913737",null,0,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":25},[],"https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Ftrajectory\u002Ftree\u002FHEAD\u002Fplugin\u002Ftrajectory-opencode\u002Fskills\u002Fincognito","---\nname: incognito\nmanaged-by: trajectory\ndescription: Toggle Trajectory incognito mode for the current OpenCode session. Use when the user says \"\u002Fincognito\", \"go incognito\", \"pause capture\", \"stop recording\", \"private mode\", or asks to temporarily suppress Datadog publish for sensitive work.\n---\n\n# Incognito Mode\n\nToggle incognito mode for the current OpenCode session. When enabled:\n- Local JSONL capture continues\n- Publish to non-exempt Datadog destinations is suppressed\n- Mode resets automatically when the session ends\n\nOrg-managed security destinations configured with `incognito_exempt: true` may still receive events. Do not describe incognito as a security or compliance bypass.\n\n## Toggle\n\n1. Decide the requested state.\n   - For `\u002Fincognito`, \"go incognito\", \"pause capture\", \"stop recording\", or \"private mode\", enable incognito.\n   - For \"turn off incognito\", \"resume capture\", or \"resume publish\", disable incognito.\n   - If the user explicitly asks to toggle, call the `trajectory_incognito` MCP tool with `enable: true` unless you have already confirmed the active session is incognito, then call it with `enable: false`.\n2. If the `trajectory_incognito` MCP tool is available, call it with `enable`, `client: opencode`, and `project_dir` set to the current workspace; omit `session_id` so the tool resolves the active session from Trajectory's active-session registry.\n3. If the tool reports multiple matching active sessions, call `list_active_sessions`, choose the active OpenCode session matching the current workspace, and retry with that `session_id`.\n4. Worst-case fast lookup: check `TRAJECTORY_SESSION_ID`, `CODEX_SESSION_ID`, `GEMINI_SESSION_ID`, `CLAUDE_SESSION_ID`, `OPENCODE_SESSION_ID`, `PI_SESSION_ID`, `DROID_SESSION_ID`, or `COPILOT_SESSION_ID`; otherwise call `list_active_sessions` or run `trajectory mcp sessions --active --json` from the workspace, select the row matching the current client\u002Fworkspace with the newest `last_event`, and retry with `session_id`.\n5. If MCP is not available, resolve the current session ID with `TRAJECTORY_SESSION_ID` or `trajectory mcp sessions --active --json`, then call the HTTP endpoint directly:\n   `curl -fsS -X POST \"http:\u002F\u002Flocalhost:19222\u002Fsession\u002Fincognito?session_id=${session_id}&enable=${enable}\"`\n6. Tell the user whether incognito is now enabled or disabled.\n",{"data":33,"body":35},{"name":4,"managed-by":34,"description":6},"trajectory",{"type":36,"children":37},"root",[38,47,53,73,87,94],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"incognito-mode",[44],{"type":45,"value":46},"text","Incognito Mode",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51],{"type":45,"value":52},"Toggle incognito mode for the current OpenCode session. When enabled:",{"type":39,"tag":54,"props":55,"children":56},"ul",{},[57,63,68],{"type":39,"tag":58,"props":59,"children":60},"li",{},[61],{"type":45,"value":62},"Local JSONL capture continues",{"type":39,"tag":58,"props":64,"children":65},{},[66],{"type":45,"value":67},"Publish to non-exempt Datadog destinations is suppressed",{"type":39,"tag":58,"props":69,"children":70},{},[71],{"type":45,"value":72},"Mode resets automatically when the session ends",{"type":39,"tag":48,"props":74,"children":75},{},[76,78,85],{"type":45,"value":77},"Org-managed security destinations configured with ",{"type":39,"tag":79,"props":80,"children":82},"code",{"className":81},[],[83],{"type":45,"value":84},"incognito_exempt: true",{"type":45,"value":86}," may still receive events. Do not describe incognito as a security or compliance bypass.",{"type":39,"tag":88,"props":89,"children":91},"h2",{"id":90},"toggle",[92],{"type":45,"value":93},"Toggle",{"type":39,"tag":95,"props":96,"children":97},"ol",{},[98,153,197,216,308,333],{"type":39,"tag":58,"props":99,"children":100},{},[101,103],{"type":45,"value":102},"Decide the requested state.\n",{"type":39,"tag":54,"props":104,"children":105},{},[106,119,124],{"type":39,"tag":58,"props":107,"children":108},{},[109,111,117],{"type":45,"value":110},"For ",{"type":39,"tag":79,"props":112,"children":114},{"className":113},[],[115],{"type":45,"value":116},"\u002Fincognito",{"type":45,"value":118},", \"go incognito\", \"pause capture\", \"stop recording\", or \"private mode\", enable incognito.",{"type":39,"tag":58,"props":120,"children":121},{},[122],{"type":45,"value":123},"For \"turn off incognito\", \"resume capture\", or \"resume publish\", disable incognito.",{"type":39,"tag":58,"props":125,"children":126},{},[127,129,135,137,143,145,151],{"type":45,"value":128},"If the user explicitly asks to toggle, call the ",{"type":39,"tag":79,"props":130,"children":132},{"className":131},[],[133],{"type":45,"value":134},"trajectory_incognito",{"type":45,"value":136}," MCP tool with ",{"type":39,"tag":79,"props":138,"children":140},{"className":139},[],[141],{"type":45,"value":142},"enable: true",{"type":45,"value":144}," unless you have already confirmed the active session is incognito, then call it with ",{"type":39,"tag":79,"props":146,"children":148},{"className":147},[],[149],{"type":45,"value":150},"enable: false",{"type":45,"value":152},".",{"type":39,"tag":58,"props":154,"children":155},{},[156,158,163,165,171,173,179,181,187,189,195],{"type":45,"value":157},"If the ",{"type":39,"tag":79,"props":159,"children":161},{"className":160},[],[162],{"type":45,"value":134},{"type":45,"value":164}," MCP tool is available, call it with ",{"type":39,"tag":79,"props":166,"children":168},{"className":167},[],[169],{"type":45,"value":170},"enable",{"type":45,"value":172},", ",{"type":39,"tag":79,"props":174,"children":176},{"className":175},[],[177],{"type":45,"value":178},"client: opencode",{"type":45,"value":180},", and ",{"type":39,"tag":79,"props":182,"children":184},{"className":183},[],[185],{"type":45,"value":186},"project_dir",{"type":45,"value":188}," set to the current workspace; omit ",{"type":39,"tag":79,"props":190,"children":192},{"className":191},[],[193],{"type":45,"value":194},"session_id",{"type":45,"value":196}," so the tool resolves the active session from Trajectory's active-session registry.",{"type":39,"tag":58,"props":198,"children":199},{},[200,202,208,210,215],{"type":45,"value":201},"If the tool reports multiple matching active sessions, call ",{"type":39,"tag":79,"props":203,"children":205},{"className":204},[],[206],{"type":45,"value":207},"list_active_sessions",{"type":45,"value":209},", choose the active OpenCode session matching the current workspace, and retry with that ",{"type":39,"tag":79,"props":211,"children":213},{"className":212},[],[214],{"type":45,"value":194},{"type":45,"value":152},{"type":39,"tag":58,"props":217,"children":218},{},[219,221,227,228,234,235,241,242,248,249,255,256,262,263,269,271,277,279,284,286,292,294,300,302,307],{"type":45,"value":220},"Worst-case fast lookup: check ",{"type":39,"tag":79,"props":222,"children":224},{"className":223},[],[225],{"type":45,"value":226},"TRAJECTORY_SESSION_ID",{"type":45,"value":172},{"type":39,"tag":79,"props":229,"children":231},{"className":230},[],[232],{"type":45,"value":233},"CODEX_SESSION_ID",{"type":45,"value":172},{"type":39,"tag":79,"props":236,"children":238},{"className":237},[],[239],{"type":45,"value":240},"GEMINI_SESSION_ID",{"type":45,"value":172},{"type":39,"tag":79,"props":243,"children":245},{"className":244},[],[246],{"type":45,"value":247},"CLAUDE_SESSION_ID",{"type":45,"value":172},{"type":39,"tag":79,"props":250,"children":252},{"className":251},[],[253],{"type":45,"value":254},"OPENCODE_SESSION_ID",{"type":45,"value":172},{"type":39,"tag":79,"props":257,"children":259},{"className":258},[],[260],{"type":45,"value":261},"PI_SESSION_ID",{"type":45,"value":172},{"type":39,"tag":79,"props":264,"children":266},{"className":265},[],[267],{"type":45,"value":268},"DROID_SESSION_ID",{"type":45,"value":270},", or ",{"type":39,"tag":79,"props":272,"children":274},{"className":273},[],[275],{"type":45,"value":276},"COPILOT_SESSION_ID",{"type":45,"value":278},"; otherwise call ",{"type":39,"tag":79,"props":280,"children":282},{"className":281},[],[283],{"type":45,"value":207},{"type":45,"value":285}," or run ",{"type":39,"tag":79,"props":287,"children":289},{"className":288},[],[290],{"type":45,"value":291},"trajectory mcp sessions --active --json",{"type":45,"value":293}," from the workspace, select the row matching the current client\u002Fworkspace with the newest ",{"type":39,"tag":79,"props":295,"children":297},{"className":296},[],[298],{"type":45,"value":299},"last_event",{"type":45,"value":301},", and retry with ",{"type":39,"tag":79,"props":303,"children":305},{"className":304},[],[306],{"type":45,"value":194},{"type":45,"value":152},{"type":39,"tag":58,"props":309,"children":310},{},[311,313,318,320,325,327],{"type":45,"value":312},"If MCP is not available, resolve the current session ID with ",{"type":39,"tag":79,"props":314,"children":316},{"className":315},[],[317],{"type":45,"value":226},{"type":45,"value":319}," or ",{"type":39,"tag":79,"props":321,"children":323},{"className":322},[],[324],{"type":45,"value":291},{"type":45,"value":326},", then call the HTTP endpoint directly:\n",{"type":39,"tag":79,"props":328,"children":330},{"className":329},[],[331],{"type":45,"value":332},"curl -fsS -X POST \"http:\u002F\u002Flocalhost:19222\u002Fsession\u002Fincognito?session_id=${session_id}&enable=${enable}\"",{"type":39,"tag":58,"props":334,"children":335},{},[336],{"type":45,"value":337},"Tell the user whether incognito is now enabled or disabled.",{"items":339,"total":346},[340],{"slug":4,"name":4,"fn":5,"description":6,"org":341,"tags":342,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[343,344,345],{"name":17,"slug":18,"type":15},{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},1,{"items":348,"total":526},[349,366,384,395,411,425,441,455,467,479,491,511],{"slug":350,"name":350,"fn":351,"description":352,"org":353,"tags":354,"stars":363,"repoUrl":364,"updatedAt":365},"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},[355,356,359,362],{"name":17,"slug":18,"type":15},{"name":357,"slug":358,"type":15},"Deployment","deployment",{"name":360,"slug":361,"type":15},"Kubernetes","kubernetes",{"name":13,"slug":14,"type":15},145,"https:\u002F\u002Fgithub.com\u002Fdatadog-labs\u002Fagent-skills","2026-04-15T04:57:27.489805",{"slug":367,"name":367,"fn":368,"description":369,"org":370,"tags":371,"stars":363,"repoUrl":364,"updatedAt":383},"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},[372,373,376,379,382],{"name":17,"slug":18,"type":15},{"name":374,"slug":375,"type":15},"Debugging","debugging",{"name":377,"slug":378,"type":15},"Evals","evals",{"name":380,"slug":381,"type":15},"LLM","llm",{"name":13,"slug":14,"type":15},"2026-07-31T05:52:13.711906",{"slug":385,"name":385,"fn":386,"description":387,"org":388,"tags":389,"stars":363,"repoUrl":364,"updatedAt":394},"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},[390,391,392,393],{"name":17,"slug":18,"type":15},{"name":377,"slug":378,"type":15},{"name":380,"slug":381,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:19.259734",{"slug":396,"name":396,"fn":397,"description":398,"org":399,"tags":400,"stars":363,"repoUrl":364,"updatedAt":410},"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},[401,404,407,408,409],{"name":402,"slug":403,"type":15},"Agents","agents",{"name":405,"slug":406,"type":15},"Data Pipeline","data-pipeline",{"name":17,"slug":18,"type":15},{"name":377,"slug":378,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:17.231423",{"slug":412,"name":412,"fn":413,"description":414,"org":415,"tags":416,"stars":363,"repoUrl":364,"updatedAt":424},"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},[417,420,421,422,423],{"name":418,"slug":419,"type":15},"Analytics","analytics",{"name":17,"slug":18,"type":15},{"name":377,"slug":378,"type":15},{"name":380,"slug":381,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:21.212498",{"slug":426,"name":426,"fn":427,"description":428,"org":429,"tags":430,"stars":363,"repoUrl":364,"updatedAt":440},"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},[431,432,435,436,437],{"name":17,"slug":18,"type":15},{"name":433,"slug":434,"type":15},"Jupyter","jupyter",{"name":380,"slug":381,"type":15},{"name":13,"slug":14,"type":15},{"name":438,"slug":439,"type":15},"Python","python","2026-06-19T09:04:22.640384",{"slug":442,"name":442,"fn":443,"description":444,"org":445,"tags":446,"stars":363,"repoUrl":364,"updatedAt":454},"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},[447,448,449,450,451],{"name":17,"slug":18,"type":15},{"name":374,"slug":375,"type":15},{"name":380,"slug":381,"type":15},{"name":13,"slug":14,"type":15},{"name":452,"slug":453,"type":15},"Tracing","tracing","2026-07-31T05:52:08.594182",{"slug":456,"name":456,"fn":457,"description":458,"org":459,"tags":460,"stars":363,"repoUrl":364,"updatedAt":466},"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},[461,462,463,464,465],{"name":418,"slug":419,"type":15},{"name":17,"slug":18,"type":15},{"name":377,"slug":378,"type":15},{"name":380,"slug":381,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:26.341497",{"slug":468,"name":468,"fn":469,"description":470,"org":471,"tags":472,"stars":363,"repoUrl":364,"updatedAt":478},"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},[473,474,475,476,477],{"name":17,"slug":18,"type":15},{"name":374,"slug":375,"type":15},{"name":377,"slug":378,"type":15},{"name":380,"slug":381,"type":15},{"name":13,"slug":14,"type":15},"2026-06-19T09:04:24.316244",{"slug":480,"name":480,"fn":481,"description":482,"org":483,"tags":484,"stars":363,"repoUrl":364,"updatedAt":490},"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},[485,486,489],{"name":17,"slug":18,"type":15},{"name":487,"slug":488,"type":15},"Monitoring","monitoring",{"name":13,"slug":14,"type":15},"2026-04-06T18:08:33.337476",{"slug":492,"name":492,"fn":493,"description":494,"org":495,"tags":496,"stars":363,"repoUrl":364,"updatedAt":510},"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},[497,498,501,504,507],{"name":17,"slug":18,"type":15},{"name":499,"slug":500,"type":15},"Frontend","frontend",{"name":502,"slug":503,"type":15},"React","react",{"name":505,"slug":506,"type":15},"TypeScript","typescript",{"name":508,"slug":509,"type":15},"Vite","vite","2026-06-18T08:01:32.562331",{"slug":512,"name":512,"fn":513,"description":514,"org":515,"tags":516,"stars":363,"repoUrl":364,"updatedAt":525},"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},[517,518,521,522],{"name":17,"slug":18,"type":15},{"name":519,"slug":520,"type":15},"Distributed Tracing","distributed-tracing",{"name":13,"slug":14,"type":15},{"name":523,"slug":524,"type":15},"Performance","performance","2026-04-06T18:08:34.575282",35]