Arize Link
Copy correct Arize console deep links for traces, spans, sessions, and datasets when debugging or sharing LLM agent runs.
Overview
Arize-link is an agent skill most often used in Operate (also Ship and Build) that documents canonical Arize app URL templates for generative LLM tracing—traces, spans, sessions, datasets, and labeling queues—with base64
Install
npx skills add https://github.com/github/awesome-copilot --skill arize-linkWhat is this skill?
- Six URL patterns: trace, span (trace + span), session, dataset examples tab, dataset experiments tab, and labeling queue
- Documents placeholders for base64 org, space, project, and dataset IDs plus epoch millisecond start/end windows
- Pre-selects generative LLM tracing with timezone, env=tracing, and modelType=generative_llm query params
- Span template adds selectedSpanId on top of the trace URL for pinpoint navigation
- No runtime dependencies—pure reference templates for paste-and-substitute workflows
- Six documented link types: trace, span, session, dataset examples, dataset experiments, labeling queue list
Adoption & trust: 864 installs on skills.sh; 34.6k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have trace or span IDs in Arize but assembling the long, error-prone console URL with the right tabs, filters, and time window slows down debugging and sharing.
Who is it for?
Solo builders shipping LLM agents on Arize who routinely share trace, span, or session links during reviews and on-call debugging.
Skip if: Teams not on Arize observability or anyone who only needs OpenTelemetry export pipelines without linking into the Arize web UI.
When should I use this skill?
You need a shareable or bookmarkable Arize console URL for a trace, span, session, dataset tab, or labeling queue and have the underlying IDs and time range.
What do I get? / Deliverables
You get copy-ready URL patterns with named placeholders so you can open or share the correct Arize LLM Tracing or dataset view without guessing query parameters.
- Filled Arize app URLs for trace, span, or session views with LLM Tracing tab selected
- Dataset deep links for examples or experiments tabs
- Labeling queue list URL for the org and space
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
The skill’s value peaks when you are inspecting production or staging LLM traffic in Arize, which maps to running and observing shipped agents. Monitoring is the canonical shelf because these URLs open the LLM Tracing tab for investigation, handoffs, and incident review—not for initial instrumentation setup alone.
Where it fits
Paste a span deep link into an incident thread so you and a cofounder land on the same failed tool-call span with the time window already set.
Attach a trace URL to a pre-release checklist item when validating a prompt change against production-like traffic in Arize.
Encode the documented query params when adding a ‘open in Arize’ button to an internal agent dashboard.
How it compares
A static URL cookbook for the Arize console—not an MCP server, SDK, or automated trace retrieval tool.
Common Questions / FAQ
Who is arize-link for?
Indie and solo builders who instrument generative LLM apps in Arize and need fast, accurate deep links for traces, spans, sessions, and datasets during collaboration.
When should I use arize-link?
Use it in Operate when monitoring failed agent runs and sharing span links; in Ship when attaching trace URLs to reviews; and in Build when wiring internal debug helpers that must open the right Arize project view.
Is arize-link safe to install?
The skill is documentation-only with no shell or network hooks in the skill itself; review the Security Audits panel on this Prism page before adding any skill from the catalog to your agent.
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