Arize Link
Generate copy-paste Arize console deep links for LLM traces, spans, sessions, datasets, and labeling queues when debugging or sharing observability context with your team.
Overview
arize-link is an agent skill most often used in Operate (also Build integrations, Ship testing) that builds shareable app.arize.com deep links for LLM traces, spans, sessions, datasets, and labeling queues.
Install
npx skills add https://github.com/arize-ai/arize-skills --skill arize-linkWhat is this skill?
- Documents six deep-link patterns: trace, span-highlighted trace, session, dataset examples, dataset experiments, and lab
- Uses standard Arize query params: selectedTraceId, selectedSpanId, selectedSessionId, selectedTab, envA=tracing, modelTy
- Defines placeholder contract for base64 org_id, space_id, project_id, dataset_id, and epoch-ms startA/endA windows
- Includes timezone encoding example (America/Los_Angeles) so shared links land on the intended trace time range
- No API calls—agent fills IDs from logs or OpenTelemetry exports and returns a shareable app.arize.com URL
- Six documented deep-link patterns: trace, span, session, dataset (two tabs), labeling queue list
Adoption & trust: 838 installs on skills.sh; 31 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have trace, span, or session IDs from logs but waste time clicking through Arize UI or guessing which query parameters open the right llmTracing or dataset tab.
Who is it for?
Solo builders and small teams already on Arize who need fast, accurate share links while debugging agents or reviewing dataset experiments.
Skip if: Teams not using Arize, or workflows that need automated trace export/API analysis instead of hand-built console URLs.
When should I use this skill?
User needs a shareable Arize console URL for a trace, span, session, dataset tab, or labeling queue and has the relevant base64-encoded IDs.
What do I get? / Deliverables
You get a correctly encoded Arize URL with the right selectedTab, time window, and entity IDs so anyone can open the exact observability view in one click.
- Fully formatted app.arize.com URL for the requested entity (trace, span, session, dataset, or queue list)
- Documented placeholder map so IDs and time bounds can be swapped for other incidents
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Operate because the skill’s payoff is inspecting live or recent LLM telemetry in Arize—not authoring product code. Monitoring is the best fit: the URLs open llmTracing, datasets, and labeling views used to watch agent behavior and drill into failures.
Where it fits
After wiring OpenTelemetry export to Arize, you ask the agent for a trace URL template to drop in runbooks for your staging project.
A CI repro fails; you paste trace_id and span_id so the agent returns a span-highlighted llmTracing link for QA.
Production traffic spikes errors and you share a session deep link with millisecond startA/endA so a cofounder sees the same conversation thread.
You compare dataset experiments tabs and need two dataset URLs (examples vs experiments) for a postmortem doc.
How it compares
Use this procedural URL template skill instead of guessing Arize query strings in chat or bookmarking generic project homepages.
Common Questions / FAQ
Who is arize-link for?
It is for solo and indie builders (and small teams) who run LLM apps on Arize and want their agent to emit correct deep links during debug and incident threads.
When should I use arize-link?
Use it in Operate monitoring when sharing a failing trace, in Ship testing when validating a span, and in Build integrations when documenting how to open sessions, dataset examples, or labeling queues from your IDs.
Is arize-link safe to install?
It is documentation-style procedural knowledge with no bundled executables; review the Security Audits panel on this Prism page before installing any skill from the registry.
SKILL.md
READMESKILL.md - Arize Link
# Arize Link Examples Placeholders used throughout: - `{org_id}` — base64-encoded org ID - `{space_id}` — base64-encoded space ID - `{project_id}` — base64-encoded project ID - `{start_ms}` / `{end_ms}` — epoch milliseconds (e.g. 1741305600000 / 1741392000000) --- ## Trace ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedTraceId={trace_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_ms}&endA={end_ms}&envA=tracing&modelType=generative_llm ``` ## Span (trace + span highlighted) ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedTraceId={trace_id}&selectedSpanId={span_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_ms}&endA={end_ms}&envA=tracing&modelType=generative_llm ``` ## Session ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedSessionId={session_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start_ms}&endA={end_ms}&envA=tracing&modelType=generative_llm ``` ## Dataset (examples tab) ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/datasets/{dataset_id}?selectedTab=examples ``` ## Dataset (experiments tab) ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/datasets/{dataset_id}?selectedTab=experiments ``` ## Labeling Queue list ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/queues ``` ## Labeling Queue (specific) ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/queues/{queue_id} ``` ## Evaluator (latest version) ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/evaluators/{evaluator_id} ``` ## Evaluator (specific version) ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/evaluators/{evaluator_id}?version={version_url_encoded} ``` ## Annotation Configs ``` https://app.arize.com/organizations/{org_id}/spaces/{space_id}/annotation-configs ``` --- name: arize-link description: Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Produces clickable URLs for sharing Arize resources with team members. Use when the user wants to link to or open a trace, span, session, dataset, evaluator, or annotation config in the Arize UI. metadata: author: arize version: "1.0" --- # Arize Link Generate deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. ## When to Use - User wants a link to a trace, span, session, dataset, labeling queue, evaluator, or annotation config - You have IDs from exported data or logs and need to link back to the UI - User asks to "open" or "view" any of the above in Arize ## Required Inputs Collect from the user or context (exported trace data, parsed URLs): | Always required | Resource-specific | |---|---| | `org_id` (base64) | `project_id` + `trace_id` [+ `span_id`] — trace/span | | `space_id` (base64) | `project_id` + `session_id` — session | | | `dataset_id` — dataset | | | `queue_id` — specific queue (omit for list) | | | `evaluator_id` [+ `version`] — evaluator | **All path IDs must be base64-encoded** (characters: `A-Za-z0-9+/=`). A raw numeric ID produces a valid-looking URL that 404s. If the user provides a number, ask them to copy the ID directly from their Arize browser URL (`https://app.arize.com/organizations/{org_id}/spaces/{space_id}/…`). If you have a raw internal ID (e.g. `Organization:1:abC1`), base64-encode it before inserting into the URL. ## URL Templates Base URL: `https://app.arize.com` (override for on-prem) **Trace** (add `&selectedSpanId={span_id}` to highlight a specific span): ``` {base_url}/organizations/{org_id}/spaces/{space_id}/projects/{project_id}?selectedTraceId={trace_id}&queryFilterA=&selectedTab=llmTracing&timeZoneA=America%2FLos_Angeles&startA={start