[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"org-arize":3,"repo-skills-v-0-3-0":124},{"org":4,"repos":54},{"slug":5,"name":6,"logoUrl":7,"githubOrg":8,"website":9,"skillCount":10,"repoCount":11,"topRepos":12,"topTags":22,"lastUpdatedAt":53},"arize","Arize AI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Farize.jpg","Arize-ai","https:\u002F\u002Farize.com",23,3,[13,16,19],{"name":14,"skillCount":15},"Arize-ai\u002Farize-skills",13,{"name":17,"skillCount":18},"Arize-ai\u002Fphoenix",8,{"name":20,"skillCount":21},"Arize-ai\u002Farize-claude-code-plugin",2,[23,26,29,32,35,38,41,44,47,50],{"slug":24,"name":25},"llm","LLM",{"slug":27,"name":28},"observability","Observability",{"slug":30,"name":31},"evals","Evals",{"slug":33,"name":34},"datasets","Datasets",{"slug":36,"name":37},"tracing","Tracing",{"slug":39,"name":40},"analytics","Analytics",{"slug":42,"name":43},"cli","CLI",{"slug":45,"name":46},"data-analysis","Data Analysis",{"slug":48,"name":49},"debugging","Debugging",{"slug":51,"name":52},"testing","Testing","2026-07-31T05:58:09.13624",[55,83,109],{"name":56,"fullName":14,"repoUrl":57,"skillCount":15,"stars":58,"forks":59,"description":60,"topics":61,"topTags":70,"topTagCount":81,"lastUpdatedAt":82},"arize-skills","https:\u002F\u002Fgithub.com\u002FArize-ai\u002Farize-skills",38,5,"Agent skills for Arize — datasets, experiments, and traces via the ax CLI",[62,63,64,5,65,66,67,33,68,69,36],"agent-skills","ai-agents","ai-observability","claude-code","codex","cursor","experiments","llmops",[71,72,73,74,75,78],{"slug":24,"name":25},{"slug":27,"name":28},{"slug":30,"name":31},{"slug":39,"name":40},{"slug":76,"name":77},"anthropic","Anthropic",{"slug":79,"name":80},"audit","Audit",25,"2026-07-31T05:53:45.56562",{"name":84,"fullName":17,"repoUrl":85,"skillCount":18,"stars":86,"forks":87,"description":88,"topics":89,"topTags":101,"topTagCount":108,"lastUpdatedAt":53},"phoenix","https:\u002F\u002Fgithub.com\u002FArize-ai\u002Fphoenix",10513,977,"AI Observability & Evaluation",[90,91,64,92,76,33,30,93,94,95,96,69,97,98,99,100],"agents","ai-monitoring","aiengineering","langchain","llamaindex","llm-eval","llm-evaluation","llms","openai","prompt-engineering","smolagents",[102,103,104,105,106,107],{"slug":30,"name":31},{"slug":24,"name":25},{"slug":27,"name":28},{"slug":51,"name":52},{"slug":36,"name":37},{"slug":45,"name":46},10,{"name":110,"fullName":20,"repoUrl":111,"skillCount":21,"stars":112,"forks":113,"description":114,"topics":115,"topTags":116,"topTagCount":113,"lastUpdatedAt":123},"arize-claude-code-plugin","https:\u002F\u002Fgithub.com\u002FArize-ai\u002Farize-claude-code-plugin",20,4,"Arize Claude Code Plugin",[],[117,118,121,122],{"slug":42,"name":43},{"slug":119,"name":120},"data-engineering","Data Engineering",{"slug":33,"name":34},{"slug":27,"name":28},"2026-07-12T08:08:07.341667",{"items":125,"total":18},[126,138,147,157,166,176,188,198],{"slug":127,"name":127,"fn":128,"description":129,"org":130,"tags":131,"stars":86,"repoUrl":85,"updatedAt":137},"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 `batch_span_annotate` tool, 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":5,"name":6,"logoUrl":7,"githubOrg":8},[132,134,135,136],{"name":31,"slug":30,"type":133},"tag",{"name":25,"slug":24,"type":133},{"name":28,"slug":27,"type":133},{"name":37,"slug":36,"type":133},"2026-07-12T08:08:14.140984",{"slug":33,"name":33,"fn":139,"description":140,"org":141,"tags":142,"stars":86,"repoUrl":85,"updatedAt":146},"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":5,"name":6,"logoUrl":7,"githubOrg":8},[143,144,145],{"name":46,"slug":45,"type":133},{"name":34,"slug":33,"type":133},{"name":31,"slug":30,"type":133},"2026-07-12T08:08:21.695457",{"slug":148,"name":148,"fn":149,"description":150,"org":151,"tags":152,"stars":86,"repoUrl":85,"updatedAt":156},"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":5,"name":6,"logoUrl":7,"githubOrg":8},[153,154,155],{"name":49,"slug":48,"type":133},{"name":28,"slug":27,"type":133},{"name":37,"slug":36,"type":133},"2026-07-12T08:08:10.44243",{"slug":158,"name":158,"fn":159,"description":160,"org":161,"tags":162,"stars":86,"repoUrl":85,"updatedAt":53},"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":5,"name":6,"logoUrl":7,"githubOrg":8},[163,164,165],{"name":31,"slug":30,"type":133},{"name":25,"slug":24,"type":133},{"name":52,"slug":51,"type":133},{"slug":68,"name":68,"fn":167,"description":168,"org":169,"tags":170,"stars":86,"repoUrl":85,"updatedAt":175},"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":5,"name":6,"logoUrl":7,"githubOrg":8},[171,172,173,174],{"name":34,"slug":33,"type":133},{"name":31,"slug":30,"type":133},{"name":25,"slug":24,"type":133},{"name":52,"slug":51,"type":133},"2026-07-12T08:08:11.691477",{"slug":177,"name":177,"fn":178,"description":179,"org":180,"tags":181,"stars":86,"repoUrl":85,"updatedAt":187},"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":5,"name":6,"logoUrl":7,"githubOrg":8},[182,183,184],{"name":40,"slug":39,"type":133},{"name":46,"slug":45,"type":133},{"name":185,"slug":186,"type":133},"GraphQL","graphql","2026-07-12T08:08:17.163493",{"slug":189,"name":189,"fn":190,"description":191,"org":192,"tags":193,"stars":86,"repoUrl":85,"updatedAt":197},"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 tool call, including single-shot prompt rewrites.",{"slug":5,"name":6,"logoUrl":7,"githubOrg":8},[194,195,196],{"name":31,"slug":30,"type":133},{"name":25,"slug":24,"type":133},{"name":52,"slug":51,"type":133},"2026-07-12T08:08:12.920792",{"slug":199,"name":199,"fn":200,"description":201,"org":202,"tags":203,"stars":86,"repoUrl":85,"updatedAt":208},"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":5,"name":6,"logoUrl":7,"githubOrg":8},[204,205,206,207],{"name":49,"slug":48,"type":133},{"name":25,"slug":24,"type":133},{"name":28,"slug":27,"type":133},{"name":37,"slug":36,"type":133},"2026-07-12T08:08:19.597239"]