PluginBench
Skill
Pass
Audit score 90

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
Prerequisites
  • 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
Claude Code
Cursor
Windsurf
Cline

How to use arize-link

  1. 1.Collect the required IDs from the user, exported data, or Arize browser URL
  2. 2.Verify all path IDs are base64-encoded (raw numeric IDs will produce 404s)
  3. 3.Determine the time range (startA/endA) using: user-provided URL, span start_time ±1 day, or last 90 days as fallback
  4. 4.Select the appropriate URL template based on resource type (trace, session, dataset, queue, evaluator, or annotation config)
  5. 5.Substitute IDs and time range into the template
  6. 6.Present the generated URL as a clickable markdown link

Use cases

Good for
  • 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
Who it's for
  • 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

Why does my link show 'no data' or an empty view?

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.

I get a 404 error. What went wrong?

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.

How do I highlight a specific span in a trace link?

Add the query parameter &selectedSpanId={span_id} to the trace URL. Verify the span_id belongs to the same trace.

Can I link to a specific evaluator version?

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).

Where do I find org_id if the ax CLI doesn't expose it?

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 requiredResource-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:

  1. User-provided URL — extract and reuse startA/endA directly.
  2. Span start_time — pad ±1 day (or ±1 hour for a tighter window).
  3. Fallback — last 90 days (now - 90d to now).

Prefer tight windows; 90-day windows load slowly.

Instructions

  1. Gather IDs from user, exported data, or URL context.
  2. Verify all path IDs are base64-encoded.
  3. Determine startA/endA using the priority order above.
  4. Substitute into the appropriate template and present as a clickable markdown link.

Troubleshooting

ProblemSolution
"No data" / empty viewTrace outside time window — widen startA/endA (±1h → ±1d → 90d).
404ID wrong or not base64. Re-check org_id, space_id, project_id from the browser URL.
Span not highlightedspan_id may belong to a different trace. Verify against exported span data.
org_id unknownax 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, and start_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.

ARarize-prompt-optimization logo

arize-prompt-optimization

arize-ai/arize-skills

Optimize LLM prompts using production trace data and performance feedback with Arize.

1.5k installs
ARarize-trace logo

arize-trace

arize-ai/arize-skills

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

1.4k installs
ARarize-admin logo

arize-admin

arize-ai/arize-skills

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.

670 installsAudited
ARarize-ai-provider-integration logo

arize-ai-provider-integration

arize-ai/arize-skills

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.

1.3k installsAudited
SWswiftui-design-principles logo

swiftui-design-principles

arjitj2/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.

819 installsAudited
EXextract-design-system logo

extract-design-system

arvindrk/extract-design-system

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

124k installs