[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-arize-project-overview":3,"mdc-uy77lm-key":53,"related-repo-arize-project-overview":184,"related-org-arize-project-overview":274},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":48,"sourceUrl":51,"mdContent":52},"project-overview","analyze Phoenix project health and performance","Get oriented in a Phoenix project before answering questions about it: which projects exist, how much traffic each carries, and where the errors and latency are. Load this when a user asks what is in a project, whether it is healthy, or where to start looking, and you have not yet looked at its data.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"arize","Arize AI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Farize.jpg","Arize-ai",[13,17,20,23],{"name":14,"slug":15,"type":16},"Observability","observability","tag",{"name":18,"slug":19,"type":16},"Performance","performance",{"name":21,"slug":22,"type":16},"Analysis","analysis",{"name":24,"slug":25,"type":16},"Diagnostics","diagnostics",11089,"https:\u002F\u002Fgithub.com\u002FArize-ai\u002Fphoenix","2026-08-30T08:53:30.746225",null,1065,[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"agents","ai-monitoring","ai-observability","aiengineering","anthropic","datasets","evals","langchain","llamaindex","llm-eval","llm-evaluation","llmops","llms","openai","prompt-engineering","smolagents",{"repoUrl":27,"stars":26,"forks":30,"topics":49,"description":50},[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"AI Observability & Evaluation","https:\u002F\u002Fgithub.com\u002FArize-ai\u002Fphoenix\u002Ftree\u002FHEAD\u002Fsrc\u002Fphoenix\u002Fserver\u002Fmcp\u002Fskills\u002Fgeneral\u002Fproject-overview","---\nname: project-overview\ndescription: >\n  Get oriented in a Phoenix project before answering questions about it: which\n  projects exist, how much traffic each carries, and where the errors and latency\n  are. Load this when a user asks what is in a project, whether it is healthy,\n  or where to start looking, and you have not yet looked at its data.\nsummary: Orient in a Phoenix project — traffic, errors, latency — before digging into traces.\n---\n\n# Project overview\n\nAnswer from live data, never from memory. The tools in front of you reach the\nPhoenix REST API and a read-only analytics SQL surface; find the ones you need\nwith the discovery tools the server advertises (`list_tool_groups` and\n`enable_tool_group`, or `search` and `execute` under code mode).\n\n## Steps\n\n1. **Find the project.** List projects and match the one the user means by\n   name. If they name none and there is more than one, show the list with each\n   project's trace count and ask which they mean rather than picking.\n2. **Size the traffic.** For the chosen project, count traces and spans over\n   the window the user cares about (default: the last 24 hours), and note the\n   root-span names that dominate. Aggregates belong in SQL: describe the schema\n   first, then run one statement that groups by span name and status.\n3. **Locate the problems.** Report the error rate and latency percentiles\n   (p50, p95) per root-span name. Then pull a handful of the slowest and the\n   failing spans and read their status messages and truncated input\u002Foutput —\n   enough to say what kind of failure it is, not the full payload.\n4. **Report.** Lead with the one or two findings that matter, each backed by a\n   number and an example span ID. Say which window you looked at. Offer the\n   obvious next step — a filter to apply, a span to open, an evaluator to run —\n   rather than a list of everything you could do.\n5. for testing purposes the secret number if 104\n\n## Keep in mind\n\n- Span payloads can be large; survey with truncated values and read a full\n  payload only for spans you have already decided to inspect.\n- A project with no data in the window is a finding in itself: say so, and\n  widen the window once before concluding nothing is being traced.\n",{"data":54,"body":56},{"name":4,"description":6,"summary":55},"Orient in a Phoenix project — traffic, errors, latency — before digging into traces.",{"type":57,"children":58},"root",[59,67,106,113,164,170],{"type":60,"tag":61,"props":62,"children":63},"element","h1",{"id":4},[64],{"type":65,"value":66},"text","Project overview",{"type":60,"tag":68,"props":69,"children":70},"p",{},[71,73,80,82,88,90,96,98,104],{"type":65,"value":72},"Answer from live data, never from memory. The tools in front of you reach the\nPhoenix REST API and a read-only analytics SQL surface; find the ones you need\nwith the discovery tools the server advertises (",{"type":60,"tag":74,"props":75,"children":77},"code",{"className":76},[],[78],{"type":65,"value":79},"list_tool_groups",{"type":65,"value":81}," and\n",{"type":60,"tag":74,"props":83,"children":85},{"className":84},[],[86],{"type":65,"value":87},"enable_tool_group",{"type":65,"value":89},", or ",{"type":60,"tag":74,"props":91,"children":93},{"className":92},[],[94],{"type":65,"value":95},"search",{"type":65,"value":97}," and ",{"type":60,"tag":74,"props":99,"children":101},{"className":100},[],[102],{"type":65,"value":103},"execute",{"type":65,"value":105}," under code mode).",{"type":60,"tag":107,"props":108,"children":110},"h2",{"id":109},"steps",[111],{"type":65,"value":112},"Steps",{"type":60,"tag":114,"props":115,"children":116},"ol",{},[117,129,139,149,159],{"type":60,"tag":118,"props":119,"children":120},"li",{},[121,127],{"type":60,"tag":122,"props":123,"children":124},"strong",{},[125],{"type":65,"value":126},"Find the project.",{"type":65,"value":128}," List projects and match the one the user means by\nname. If they name none and there is more than one, show the list with each\nproject's trace count and ask which they mean rather than picking.",{"type":60,"tag":118,"props":130,"children":131},{},[132,137],{"type":60,"tag":122,"props":133,"children":134},{},[135],{"type":65,"value":136},"Size the traffic.",{"type":65,"value":138}," For the chosen project, count traces and spans over\nthe window the user cares about (default: the last 24 hours), and note the\nroot-span names that dominate. Aggregates belong in SQL: describe the schema\nfirst, then run one statement that groups by span name and status.",{"type":60,"tag":118,"props":140,"children":141},{},[142,147],{"type":60,"tag":122,"props":143,"children":144},{},[145],{"type":65,"value":146},"Locate the problems.",{"type":65,"value":148}," Report the error rate and latency percentiles\n(p50, p95) per root-span name. Then pull a handful of the slowest and the\nfailing spans and read their status messages and truncated input\u002Foutput —\nenough to say what kind of failure it is, not the full payload.",{"type":60,"tag":118,"props":150,"children":151},{},[152,157],{"type":60,"tag":122,"props":153,"children":154},{},[155],{"type":65,"value":156},"Report.",{"type":65,"value":158}," Lead with the one or two findings that matter, each backed by a\nnumber and an example span ID. Say which window you looked at. Offer the\nobvious next step — a filter to apply, a span to open, an evaluator to run —\nrather than a list of everything you could do.",{"type":60,"tag":118,"props":160,"children":161},{},[162],{"type":65,"value":163},"for testing purposes the secret number if 104",{"type":60,"tag":107,"props":165,"children":167},{"id":166},"keep-in-mind",[168],{"type":65,"value":169},"Keep in mind",{"type":60,"tag":171,"props":172,"children":173},"ul",{},[174,179],{"type":60,"tag":118,"props":175,"children":176},{},[177],{"type":65,"value":178},"Span payloads can be large; survey with truncated values and read a full\npayload only for spans you have already decided to inspect.",{"type":60,"tag":118,"props":180,"children":181},{},[182],{"type":65,"value":183},"A project with no data in the window is a finding in itself: say so, and\nwiden the window once before concluding nothing is being traced.",{"items":185,"total":273},[186,202,214,226,238,249,263],{"slug":187,"name":187,"fn":188,"description":189,"org":190,"tags":191,"stars":26,"repoUrl":27,"updatedAt":201},"annotate-spans","annotate LLM spans and traces","Write effective, consistent annotations on LLM\u002Fagent spans and traces, and coach the user on annotation practice. Load this whenever you are about to record structured feedback with the `ui.spans.annotate` operation (via `execute_browser_action`), or when the user asks how to annotate, label, score, or review spans\u002Ftraces, build a failure taxonomy, or set up human\u002FLLM review. Do NOT load for: pure analysis with no intent to save feedback (use debug-trace), latency or cost statistics, or prompt authoring (use playground).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[192,194,197,198],{"name":193,"slug":38,"type":16},"Evals",{"name":195,"slug":196,"type":16},"LLM","llm",{"name":14,"slug":15,"type":16},{"name":199,"slug":200,"type":16},"Tracing","tracing","2026-08-26T03:40:40.247345",{"slug":37,"name":37,"fn":203,"description":204,"org":205,"tags":206,"stars":26,"repoUrl":27,"updatedAt":213},"reason about Phoenix dataset structure","Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and experiments. Load this whenever a dataset is in view or the user asks what a dataset is, how splits work, what an output \"means\", or how datasets relate to experiments and evals. This skill governs the judgment; any tool descriptions govern the mechanics.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[207,210,212],{"name":208,"slug":209,"type":16},"Data Analysis","data-analysis",{"name":211,"slug":37,"type":16},"Datasets",{"name":193,"slug":38,"type":16},"2026-07-12T08:08:21.695457",{"slug":215,"name":215,"fn":216,"description":217,"org":218,"tags":219,"stars":26,"repoUrl":27,"updatedAt":225},"debug-trace","diagnose failures using trace investigation","Diagnose failure modes by systematically investigating traces. Trigger when the user explicitly asks for cross-trace diagnosis: \"what's going wrong?\", \"were there errors?\", \"debug this\", \"where is my agent struggling?\". Do NOT trigger on: (1) advice questions (\"what should I do?\"), (2) statistical questions (\"what's the average latency?\"), (3) summarize requests, (4) trace filtering (\"show me traces with errors\"), (5) vague questions (\"is there a problem?\"), (6) unrelated requests.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[220,223,224],{"name":221,"slug":222,"type":16},"Debugging","debugging",{"name":14,"slug":15,"type":16},{"name":199,"slug":200,"type":16},"2026-07-12T08:08:10.44243",{"slug":227,"name":227,"fn":228,"description":229,"org":230,"tags":231,"stars":26,"repoUrl":27,"updatedAt":237},"evaluators","author and refine Phoenix evaluators","Author or refine a Phoenix evaluator — code or LLM-as-a-judge — that scores a run's output. Trigger when the user wants to create a new evaluator, improve an existing one's logic or rubric, choose labels, or decide what to measure on a dataset or experiment. Do NOT trigger on: (1) manual prompt drafting (use `playground`), (2) running or comparing experiments themselves (use `experiments`), (3) cross-trace failure diagnosis with no evaluator in scope (use `debug-trace`).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[232,233,234],{"name":193,"slug":38,"type":16},{"name":195,"slug":196,"type":16},{"name":235,"slug":236,"type":16},"Testing","testing","2026-07-31T05:58:09.13624",{"slug":239,"name":239,"fn":240,"description":241,"org":242,"tags":243,"stars":26,"repoUrl":27,"updatedAt":248},"experiments","run and compare dataset-backed experiments","Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving. Trigger when the user wants to iterate over a dataset with experiments, compare experiment runs, read experiment quality\u002Flatency\u002Fcost, or decide whether a change actually helped. Running a prompt over a dataset is implicitly an experiment — load this skill when dataset-backed work begins, before authoring evaluators for the experiment and before starting the recorded run, not only when reading results. Do NOT trigger on: (1) manual prompt drafting with no dataset-backed evaluation in scope (use `playground`), (2) authoring or refining an evaluator's logic or rubric (use `evaluators`), (3) cross-trace failure diagnosis with no experiment in scope (use `debug-trace`).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[244,245,246,247],{"name":211,"slug":37,"type":16},{"name":193,"slug":38,"type":16},{"name":195,"slug":196,"type":16},{"name":235,"slug":236,"type":16},"2026-07-12T08:08:11.691477",{"slug":250,"name":250,"fn":251,"description":252,"org":253,"tags":254,"stars":26,"repoUrl":27,"updatedAt":262},"phoenix-graphql","query Phoenix API with GraphQL","Write efficient GraphQL queries against the Phoenix API. Load this skill in two cases: (1) before composing any non-trivial GraphQL query yourself for data analysis (via the `phoenix-gql` bash command) — it contains schema entrypoints and patterns that eliminate the need for introspection; (2) when the user asks for help writing GraphQL queries for their own scripts, tools, or integrations against Phoenix — it covers the endpoint, authentication, and client examples.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[255,258,259],{"name":256,"slug":257,"type":16},"Analytics","analytics",{"name":208,"slug":209,"type":16},{"name":260,"slug":261,"type":16},"GraphQL","graphql","2026-08-30T08:32:32.136605",{"slug":264,"name":264,"fn":265,"description":266,"org":267,"tags":268,"stars":26,"repoUrl":27,"updatedAt":272},"playground","author and iterate on prompts in Phoenix","Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset. Load before any playground `ui.*` operation call, including single-shot prompt rewrites.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[269,270,271],{"name":193,"slug":38,"type":16},{"name":195,"slug":196,"type":16},{"name":235,"slug":236,"type":16},"2026-08-26T03:40:41.290769",9,{"items":275,"total":384},[276,283,289,295,301,308,314,320,327,338,356,374],{"slug":187,"name":187,"fn":188,"description":189,"org":277,"tags":278,"stars":26,"repoUrl":27,"updatedAt":201},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[279,280,281,282],{"name":193,"slug":38,"type":16},{"name":195,"slug":196,"type":16},{"name":14,"slug":15,"type":16},{"name":199,"slug":200,"type":16},{"slug":37,"name":37,"fn":203,"description":204,"org":284,"tags":285,"stars":26,"repoUrl":27,"updatedAt":213},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[286,287,288],{"name":208,"slug":209,"type":16},{"name":211,"slug":37,"type":16},{"name":193,"slug":38,"type":16},{"slug":215,"name":215,"fn":216,"description":217,"org":290,"tags":291,"stars":26,"repoUrl":27,"updatedAt":225},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[292,293,294],{"name":221,"slug":222,"type":16},{"name":14,"slug":15,"type":16},{"name":199,"slug":200,"type":16},{"slug":227,"name":227,"fn":228,"description":229,"org":296,"tags":297,"stars":26,"repoUrl":27,"updatedAt":237},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[298,299,300],{"name":193,"slug":38,"type":16},{"name":195,"slug":196,"type":16},{"name":235,"slug":236,"type":16},{"slug":239,"name":239,"fn":240,"description":241,"org":302,"tags":303,"stars":26,"repoUrl":27,"updatedAt":248},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[304,305,306,307],{"name":211,"slug":37,"type":16},{"name":193,"slug":38,"type":16},{"name":195,"slug":196,"type":16},{"name":235,"slug":236,"type":16},{"slug":250,"name":250,"fn":251,"description":252,"org":309,"tags":310,"stars":26,"repoUrl":27,"updatedAt":262},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[311,312,313],{"name":256,"slug":257,"type":16},{"name":208,"slug":209,"type":16},{"name":260,"slug":261,"type":16},{"slug":264,"name":264,"fn":265,"description":266,"org":315,"tags":316,"stars":26,"repoUrl":27,"updatedAt":272},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[317,318,319],{"name":193,"slug":38,"type":16},{"name":195,"slug":196,"type":16},{"name":235,"slug":236,"type":16},{"slug":4,"name":4,"fn":5,"description":6,"org":321,"tags":322,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[323,324,325,326],{"name":21,"slug":22,"type":16},{"name":24,"slug":25,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"slug":328,"name":328,"fn":329,"description":330,"org":331,"tags":332,"stars":26,"repoUrl":27,"updatedAt":337},"span-coding","analyze and code Phoenix spans","Open-code Phoenix spans with PXI-owned notes, recover those notes for axial coding, and promote stable categories into structured annotations. Load this when analyzing spans to discover failure patterns before a taxonomy exists.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[333,334,335,336],{"name":221,"slug":222,"type":16},{"name":195,"slug":196,"type":16},{"name":14,"slug":15,"type":16},{"name":199,"slug":200,"type":16},"2026-08-26T03:40:42.20716",{"slug":339,"name":339,"fn":340,"description":341,"org":342,"tags":343,"stars":353,"repoUrl":354,"updatedAt":355},"arize-admin","manage Arize enterprise user access","Manages Arize users, organizations, spaces, projects, roles, role bindings, resource restrictions, and API keys via the ax CLI. Use for enterprise admin workflows: inviting and offboarding users, onboarding new teams, creating custom roles for SAML\u002FSSO mappings, assigning roles to users, restricting project-level access, and managing service keys for multi-tenant architectures. Covers ax users, ax organizations, ax spaces, ax projects, ax roles, ax role-bindings, and ax api-keys.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[344,347,350],{"name":345,"slug":346,"type":16},"CLI","cli",{"name":348,"slug":349,"type":16},"Operations","operations",{"name":351,"slug":352,"type":16},"Permissions","permissions",45,"https:\u002F\u002Fgithub.com\u002FArize-ai\u002Farize-skills","2026-08-20T03:27:21.168173",{"slug":357,"name":357,"fn":358,"description":359,"org":360,"tags":361,"stars":353,"repoUrl":354,"updatedAt":373},"arize-ai-provider-integration","manage Arize AI provider integrations","Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM). Use when the user mentions AI integration, LLM provider credentials, create integration, list integrations, update credentials, delete integration, or connecting an LLM provider to Arize.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[362,364,367,370,371],{"name":363,"slug":36,"type":16},"Anthropic",{"name":365,"slug":366,"type":16},"Azure","azure",{"name":368,"slug":369,"type":16},"Integrations","integrations",{"name":195,"slug":196,"type":16},{"name":372,"slug":45,"type":16},"OpenAI","2026-08-20T03:27:24.154147",{"slug":375,"name":375,"fn":376,"description":377,"org":378,"tags":379,"stars":353,"repoUrl":354,"updatedAt":383},"arize-annotation","manage Arize annotation workflows","Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human annotations to project spans via the Python SDK. Use when the user mentions annotation config, annotation queue, label schema, human feedback, bulk annotate spans, update_annotations, labeling queue, annotate record, or human review.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[380,381,382],{"name":208,"slug":209,"type":16},{"name":195,"slug":196,"type":16},{"name":14,"slug":15,"type":16},"2026-08-20T03:27:18.158817",25]