Platform for LLM observability including tracing, prompt versioning, and evaluation datasets.

Install

mkdir -p .claude/skills/skills-respanai && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18068" && unzip -o skill.zip -d .claude/skills/skills-respanai && rm skill.zip

Installs to .claude/skills/skills-respanai

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use the Respan CLI and SDK for LLM observability — tracing, evals, prompts, datasets, and gateway routing.
106 chars · catalog descriptionno explicit “when” trigger
Intermediate

Key capabilities

  • Set up tracing for LLM calls in an application
  • Configure a gateway to route LLM calls
  • Manage prompts by creating, versioning, and deploying them
  • Set up evaluations with datasets and evaluators
  • Configure monitors and automation for LLM applications
  • List traces and check authentication status

How it works

The skill provides guidance and commands for using the Respan CLI and SDK to instrument applications for LLM observability.

Inputs & outputs

You give it
User request to set up LLM observability or manage prompts
You get back
Configuration changes, CLI command output, or reference to documentation

When to use skills

  • Set up LLM tracing
  • Manage model prompts
  • Run model evaluation experiments
  • Configure API gateway

About this skill

Respan

Use the Respan CLI and SDK for LLM observability — tracing, evals, prompts, datasets, and gateway routing.

When To Use

Tracing and gateway are separate setups — configure one at a time, never both in the same pass.

Core Principles

  1. Read the reference first. Each reference file has the exact setup steps, API patterns, MCP tools, and CLI commands.
  2. Use MCP tools for platform operations (prompts, datasets, evaluators, experiments, traces, logs).
  3. Use CLI when MCP is not available: respan traces list, respan prompts list, etc.
  4. Fetch docs for integration-specific details not covered in references.

Quick Reference

TaskReference / Command
Set up tracing (steps + decorators, propagation)references/tracing.md
Set up gateway (steps + features)references/gateway.md
Prompt managementreferences/prompts.md
Evals & experimentsreferences/evals.md
Monitors & automationreferences/monitors.md
List tracesrespan traces list --limit 10
View a tracerespan traces get <id>
Check authrespan auth status

Documentation Access

Any doc page can be fetched as markdown: https://respan.ai/docs/integrations/openai-sdk.md https://respan.ai/docs/sdks/typescript-sdk/overview.md

Full docs index: https://www.respan.ai/docs/llms.txt

Platform: https://platform.respan.ai

When not to use it

  • When setting up both tracing and gateway in the same pass
  • When specific integration details are needed without consulting documentation

Limitations

  • Tracing and gateway setups are separate and cannot be configured simultaneously
  • Requires consulting reference documentation for exact setup steps and API patterns
  • Requires MCP tools for platform operations when CLI is not available

How it compares

This skill centralizes LLM observability tasks like tracing, gateway setup, and prompt management, offering a structured approach compared to disparate tools.

Compared to similar skills

skills side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
skills (this skill)027dNo flagsIntermediate
langfuse76moNo flagsIntermediate
mlops-engineer33moNo flagsAdvanced
langsmith-observability46moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry