abhisheksharma-17/langfuse
skills/langfuse/SKILL.md
Open-source LLM observability and evaluation platform for tracing, prompt management, datasets, and cost analytics. MANDATORY TRIGGERS: langfuse, langfuse tracing, langfuse observability, langfuse evaluation, LLM observability, LLM tracing, LLM monitoring. Also trigger when user wants to trace LLM calls, monitor token usage and costs, manage prompts with versioning, evaluate LLM outputs with datasets, set up LLM-as-a-judge, or instrument AI agents with OpenTelemetry. When in doubt about whether to use this skill for LLM observability tasks, use it.
testing
Updated Mar 30, 2026
$ install --global
skillsauthnpx skillsauth add abhisheksharma-17/skills-graph langfuseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 1, 2026, 4:44 AM57.0s18 files scanned
SKILL.md
- name:
- langfuse
- description:
- Open-source LLM observability and evaluation platform for tracing, prompt management, datasets, and cost analytics. MANDATORY TRIGGERS: langfuse, langfuse tracing, langfuse observability, langfuse evaluation, LLM observability, LLM tracing, LLM monitoring. Also trigger when user wants to trace LLM calls, monitor token usage and costs, manage prompts with versioning, evaluate LLM outputs with datasets, set up LLM-as-a-judge, or instrument AI agents with OpenTelemetry. When in doubt about whether to use this skill for LLM observability tasks, use it.
- license:
- MIT
- version:
- 1.0.0
- author:
- Abhishek Sharma
- tags:
- ["langfuse", "llm-observability", "tracing", "evaluation", "prompt-management", "opentelemetry", "llm-monitoring", "ai-observability", "cost-tracking"]
Langfuse — Skill Router
Open-source LLM engineering platform: observability, evals, prompt management, and analytics.
Source: langfuse.com v3.162.0 | Package: langfuse (Python) / @langfuse/core (JS) | License: MIT
Reference Files
| Reference | File | Read When |
|-----------|------|-----------|
| Overview & Setup | references/00-overview.md | Getting started, installation, what Langfuse is, architecture, quickstart |
| Python SDK — Decorators | references/01-python-decorators.md | @observe decorator, auto-tracing, nesting, async, input/output capture |
| Python SDK — Low-Level | references/02-python-low-level.md | Manual traces, spans, generations, context managers, flush, get_client |
| TypeScript SDK | references/03-typescript-sdk.md | JS/TS tracing, OpenTelemetry setup, observeOpenAI, startActiveObservation |
| Tracing Concepts | references/04-tracing-concepts.md | Traces, spans, generations, sessions, users, tags, metadata, environments |
| OpenTelemetry Integration | references/05-opentelemetry.md | OTLP endpoint, span processors, attribute mapping, collector config |
| Framework Integrations | references/06-integrations.md | LangChain, LlamaIndex, OpenAI SDK, Vercel AI SDK, LiteLLM, CrewAI |
| Prompt Management | references/07-prompt-management.md | Versioning, labels, templates, caching, compile, deployment workflow |
| Evaluation & Datasets | references/08-evaluation-datasets.md | Datasets, experiments, scoring, LLM-as-a-judge, annotation workflows |
| Analytics & Dashboards | references/09-analytics.md | Cost tracking, latency, token usage, custom dashboards, metrics API |
| Self-Hosting | references/10-self-hosting.md | Docker, Kubernetes, Postgres, ClickHouse, Redis, environment variables |
| Security & Data Privacy | references/11-security.md | Data masking, PII redaction, access control, SSO, compliance, encryption |
| Best Practices | references/12-best-practices.md | Production patterns, performance, error handling, migration, scaling |
Installation
# Python
pip install langfuse
# JavaScript/TypeScript (OpenAI wrapper)
npm install @langfuse/openai
# JavaScript/TypeScript (OTEL-native)
npm install @langfuse/tracing @langfuse/otel @opentelemetry/sdk-node
Quick Reference
- Docs: https://langfuse.com/docs
- GitHub: https://github.com/langfuse/langfuse
- PyPI: https://pypi.org/project/langfuse/
- npm: https://www.npmjs.com/package/@langfuse/core
Related Skills
abhisheksharma-17/weaviate
tools
VerifiedTrustedCommunity
Open-source AI-native vector database for semantic search, hybrid search, RAG, and agent-driven workflows with multi-tenancy and model provider integrations. MANDATORY TRIGGERS: weaviate, Weaviate, weaviate-client, near_text, near_vector, hybrid search vector database, WeaviateClient, weaviate.connect, collections.create, query.near_text, query.hybrid, query.bm25. Also trigger when user wants to build semantic search, store vector embeddings, implement RAG pipelines, combine keyword and vector search, set up multi-tenant vector storage, use named vectors, or integrate vector DB with LLM providers. When in doubt about whether to use this skill for vector database or semantic search tasks, use it.
1SKILL.mdUpdated Jun 4, 2026
abhisheksharma-17/playwright
tools
VerifiedTrustedCommunity
End-to-end testing and browser automation framework by Microsoft — locators, assertions, fixtures, network mocking, visual testing, tracing, codegen, API testing, and CI/CD integration. MANDATORY TRIGGERS: playwright, Playwright, @playwright/test, page.goto, page.click, page.locator, getByRole, getByText, getByTestId, expect(page), toHaveScreenshot, playwright.config, npx playwright. Also trigger when user wants to write E2E tests, automate browser interactions, test across Chromium/Firefox/WebKit, mock network requests in tests, do visual regression testing, generate tests with codegen, or set up CI test pipelines. When in doubt about whether to use this skill for browser testing or E2E automation tasks, use it.
1SKILL.mdUpdated Jun 4, 2026
abhisheksharma-17/openai-agents-sdk
tools
VerifiedTrustedCommunity
OpenAI Agents SDK for building multi-agent workflows with tools, handoffs, guardrails, streaming, MCP, sessions, and tracing. MANDATORY TRIGGERS: openai-agents, openai agents sdk, openai-agents-python, openai agents, Runner.run, function_tool, handoff, guardrail, MCPServerStdio, MCPServerStreamableHttp, HostedMCPTool, RunContextWrapper, AgentHooks. Also trigger when user wants to build multi-agent systems with OpenAI models, create agent orchestration with handoffs, add guardrails to LLM applications, integrate MCP servers with agents, implement streaming agent responses, or use OpenAI's official agent framework. When in doubt about whether to use this skill for OpenAI agent tasks, use it.
1SKILL.mdUpdated Jun 4, 2026
abhisheksharma-17/haystack
tools
VerifiedTrustedCommunity
AI orchestration framework for building production-ready RAG applications, autonomous agents, and multimodal search systems. MANDATORY TRIGGERS: haystack, deepset, haystack-ai, haystack pipeline, haystack agent. Also trigger when the user wants to build RAG pipelines with modular components, create tool-calling agents with Haystack, orchestrate retrieval-augmented generation, build semantic search systems, or evaluate LLM pipelines. When in doubt about whether to use this skill for RAG orchestration or AI pipeline tasks, use it.
1SKILL.mdUpdated Jun 4, 2026