Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs.
- GitHub stars
- 41,038
- Files
- 2
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the arize-link skill do?
arize-link generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs.
Summary generated from the skill's SKILL.md.
About the arize-link skill
Creating clickable links to specific observability resources in the Arize UI is what this skill enables. Developers and AI agents use it to transform raw IDs from logs or exported data into direct URLs for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. This is particularly useful when an agent needs to help a user navigate directly to a specific piece of telemetry or a dataset without manual searching.
To function correctly, the skill requires base64-encoded identifiers for the organization and space, along with resource-specific IDs like project_id or dataset_id. For trace and session links, the tool also relies on epoch millisecond timestamps for start and end times to ensure the data appears within the correct time window. It produces markdown links that allow team members to jump straight to the relevant context in the Arize interface.
What an agent can do with it
- 1Navigate to datasetsCreate a link that takes a user directly to a specific dataset for review.
- 2Access labeling queuesProvide a link to a specific labeling queue or the general queue list.
- 3View evaluator versionsDirect a user to a specific version of an evaluator within the platform.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the arize-link skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the arize-link skill in Claude Code
~/.claude/skills/arize-link/SKILL.md
$ npx degit github/awesome-copilot/skills/arize-link ~/.claude/skills/arize-linkInstall the arize-link skill in Claude Code (project)
.claude/skills/arize-link/SKILL.md
$ npx degit github/awesome-copilot/skills/arize-link .claude/skills/arize-linkInstall the arize-link skill in Codex
~/.agents/skills/arize-link/SKILL.md
$ npx degit github/awesome-copilot/skills/arize-link ~/.agents/skills/arize-linkInstall the arize-link skill in Gemini CLI
~/.gemini/skills/arize-link/SKILL.md
$ npx degit github/awesome-copilot/skills/arize-link ~/.gemini/skills/arize-linkInstall the arize-link skill in Claude.ai
npx degit github/awesome-copilot/skills/arize-link arize-link && zip -r arize-link.zip arize-link # claude.ai → Customize → Skills → + → Create skill → Upload a skill → arize-link.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablegithub/awesome-copilot/skills/arize-link is public and reachablegithub.com/github/awesome-copilot/tree/HEAD/skills/arize-lin ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/github/awesome-copilot/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/github/awesome-copilot/blob/HEAD/skills/arize-lin ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/github/awesome-copilot/blob/HEAD/skills/arize-lin ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 104 linesgithub.com/github/awesome-copilot/blob/HEAD/skills/arize-lin ↗Pass
SKILL.md
View on GitHubArize 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.
Files in this skill
2arize-link skill questions
How do I install the arize-link skill in Claude Code?
Run npx degit github/awesome-copilot/skills/arize-link ~/.claude/skills/arize-link. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the arize-link skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What happens if I use a raw numeric ID instead of a base64-encoded ID?
Using a raw numeric ID will produce a URL that appears valid but will result in a 404 error.
Why am I seeing 'no recent data' when I open a trace link?
The trace might fall outside the specified time window. You should widen the startA and endA parameters.
Are start and end times required for trace links?
Yes, startA and endA (epoch milliseconds) are required for trace, span, and session links to prevent defaulting to a window that might not contain the data.