arize-link
arize-ai/arize-skills
Generate shareable deep links to Arize UI resources—traces, spans, sessions, datasets, queues, evaluators, and annotation configs.
What is arize-link?
Creates clickable URLs that link directly to specific Arize resources for sharing with team members. Use this when you have resource IDs and need to generate a browser-ready link to traces, spans, sessions, datasets, labeling queues, evaluators, or annotation configs in the Arize UI.
- Generate trace and span links with optional span highlighting
- Create session links with automatic time-range detection
- Build dataset links with configurable tab selection (examples or experiments)
- Generate labeling queue list and specific queue links
- Produce evaluator links with optional version pinning
- Create annotation config links
How to install arize-link
npx skills add https://github.com/arize-ai/arize-skills --skill arize-link- Valid org_id and space_id (base64-encoded, from Arize browser URL)
- Resource-specific IDs: trace_id, span_id, session_id, dataset_id, queue_id, evaluator_id, or annotation config reference
- Time range (startA/endA in epoch milliseconds) for trace/span/session links; auto-derived from span start_time or defaults to last 90 days
How to use arize-link
- 1.Collect the required IDs from the user, exported data, or Arize browser URL
- 2.Verify all path IDs are base64-encoded (raw numeric IDs will produce 404s)
- 3.Determine the time range (startA/endA) using: user-provided URL, span start_time ±1 day, or last 90 days as fallback
- 4.Select the appropriate URL template based on resource type (trace, session, dataset, queue, evaluator, or annotation config)
- 5.Substitute IDs and time range into the template
- 6.Present the generated URL as a clickable markdown link
Use cases
- Share a specific trace with a team member for debugging
- Link to a session from a report or documentation
- Generate a dataset URL for collaborative review
- Create a queue link for labeling task assignment
- Share an evaluator configuration with specific version history
- ML engineers debugging traces and spans
- Data scientists reviewing datasets and experiments
- Team leads managing labeling queues and evaluators
- DevOps engineers sharing Arize resources across teams
arize-link FAQ
The trace likely falls outside the time window specified by startA/endA. Widen the window (start with ±1 hour, then ±1 day, then 90 days) until data appears.
Either the ID is incorrect or it is not base64-encoded. Verify org_id, space_id, and project_id directly from your Arize browser URL (https://app.arize.com/organizations/{org_id}/spaces/{space_id}/…). If you have a raw internal ID, base64-encode it before inserting.
Add the query parameter &selectedSpanId={span_id} to the trace URL. Verify the span_id belongs to the same trace.
Yes. Use the evaluator template with ?version={version_url_encoded}. Omit the version parameter to link to the latest version. Remember to URL-encode special characters (e.g., trailing = becomes %3D).
Copy it directly from your Arize browser URL: https://app.arize.com/organizations/{org_id}/spaces/{space_id}/…
Full instructions (SKILL.md)
Source of truth, from arize-ai/arize-skills.
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_ms}&endA={end_ms}&envA=tracing&modelType=generative_llm
Session:
{base_url}/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 (selectedTab: examples or experiments):
{base_url}/organizations/{org_id}/spaces/{space_id}/datasets/{dataset_id}?selectedTab=examples
Queue list / specific queue:
{base_url}/organizations/{org_id}/spaces/{space_id}/queues
{base_url}/organizations/{org_id}/spaces/{space_id}/queues/{queue_id}
Evaluator (omit ?version=… for latest):
{base_url}/organizations/{org_id}/spaces/{space_id}/evaluators/{evaluator_id}
{base_url}/organizations/{org_id}/spaces/{space_id}/evaluators/{evaluator_id}?version={version_url_encoded}
The version value must be URL-encoded (e.g., trailing = → %3D).
Annotation configs:
{base_url}/organizations/{org_id}/spaces/{space_id}/annotation-configs
Time Range
CRITICAL: startA and endA (epoch milliseconds) are required for trace/span/session links — omitting them defaults to the last 7 days and will show "no recent data" if the trace falls outside that window.
Priority order:
- User-provided URL — extract and reuse
startA/endAdirectly. - Span
start_time— pad ±1 day (or ±1 hour for a tighter window). - Fallback — last 90 days (
now - 90dtonow).
Prefer tight windows; 90-day windows load slowly.
Instructions
- Gather IDs from user, exported data, or URL context.
- Verify all path IDs are base64-encoded.
- Determine
startA/endAusing the priority order above. - Substitute into the appropriate template and present as a clickable markdown link.
Troubleshooting
| Problem | Solution |
|---|---|
| "No data" / empty view | Trace outside time window — widen startA/endA (±1h → ±1d → 90d). |
| 404 | ID wrong or not base64. Re-check org_id, space_id, project_id from the browser URL. |
| Span not highlighted | span_id may belong to a different trace. Verify against exported span data. |
org_id unknown | ax CLI doesn't expose it. Ask user to copy from https://app.arize.com/organizations/{org_id}/spaces/{space_id}/…. |
Related Skills
- arize-trace: Export spans to get
trace_id,span_id, andstart_time.
Examples
See references/EXAMPLES.md for a complete set of concrete URLs for every link type.
Related skills
More from arize-ai/arize-skills and the wider catalog.

arize-prompt-optimization
Optimize LLM prompts using production trace data and performance feedback with Arize.

arize-trace
Download, export, and inspect Arize traces and spans to debug LLM app behavior and investigate runtime issues.

arize-admin
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/SSO 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.

arize-ai-provider-integration
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.

swiftui-design-principles
Design principles for building polished, native-feeling SwiftUI apps and widgets. Use this skill when creating or modifying SwiftUI views, iOS widgets (WidgetKit), or any native Apple UI. Ensures proper spacing, typography, colors, and widget implementations that look and feel like quality apps rather than AI-generated slop.

extract-design-system
Reverse-engineer design primitives from public websites into starter token files.