skills
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.zipInstalls 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.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
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
- Set up tracing (instrument your app to capture LLM calls — install + decorators, propagation, processors) → read references/tracing.md
- Set up gateway (route LLM calls through the Respan proxy — wiring + model switching, fallbacks, caching) → read references/gateway.md
- Prompt management (create, version, deploy) → read references/prompts.md
- Evals (datasets, evaluators, experiments) → read references/evals.md
- Monitors & automation (alerts, online evals, webhooks) → read references/monitors.md
Tracing and gateway are separate setups — configure one at a time, never both in the same pass.
Core Principles
- Read the reference first. Each reference file has the exact setup steps, API patterns, MCP tools, and CLI commands.
- Use MCP tools for platform operations (prompts, datasets, evaluators, experiments, traces, logs).
- Use CLI when MCP is not available:
respan traces list,respan prompts list, etc. - Fetch docs for integration-specific details not covered in references.
Quick Reference
| Task | Reference / Command |
|---|---|
| Set up tracing (steps + decorators, propagation) | references/tracing.md |
| Set up gateway (steps + features) | references/gateway.md |
| Prompt management | references/prompts.md |
| Evals & experiments | references/evals.md |
| Monitors & automation | references/monitors.md |
| List traces | respan traces list --limit 10 |
| View a trace | respan traces get <id> |
| Check auth | respan 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.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| skills (this skill) | 0 | 27d | No flags | Intermediate |
| langfuse | 7 | 6mo | No flags | Intermediate |
| mlops-engineer | 3 | 3mo | No flags | Advanced |
| langsmith-observability | 4 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
langfuse
davila7
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
mlops-engineer
sickn33
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.
langsmith-observability
davila7
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
mlflow
davila7
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
trulens-evaluation-workflow
truera
Systematically evaluate your LLM application with TruLens
mlops-observability
fmind
Guide to implement full stack observability including reproducibility, lineage, monitoring, alerting, and explainability.