Update Langfuse Staging Server Prompt

Push prompt updates to Langfuse (staging or production). Defaults to STAGING (safe). Production requires explicit --production flag + confirmation. NEVER assigns labels (human-in-the-loop safety).

8 stars 3 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add Freddy-CHEN-ux/00_claude_skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Freddy-CHEN-ux/00_claude_skills --skill update-langfuse-staging-server-prompt
Manual install
git clone --depth 1 https://github.com/Freddy-CHEN-ux/00_claude_skills.git /tmp/00_claude_skills
mkdir -p ~/.claude/skills
cp -r /tmp/00_claude_skills/skills/update-langfuse-staging-server-prompt ~/.claude/skills/update-langfuse-staging-server-prompt

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Update Langfuse Prompts - Write Prompts to Langfuse (Staging or Production)

## 🏢 Understanding Langfuse Servers vs Labels

**CRITICAL: We have TWO separate Langfuse servers:**

1. **Staging Langfuse Server** (`https://langfuse.staging.cncorp.io`)
   - Separate database/instance on staging ECS cluster
   - Used for development and testing
   - **THIS IS WHERE THIS SKILL WRITES TO**
   - Has prompts tagged with "production" label - these are DEFAULT prompts for staging tests
   - ⚠️ "production" label here does NOT mean real user-facing prompts

2. **Production Langfuse Server** (`https://langfuse.prod.cncorp.io`)
   - Separate database/instance on production ECS cluster
   - Used for real user-facing application
   - **THIS SKILL NEVER WRITES HERE**
   - Has prompts tagged with "production" label - these ARE the real prompts shown to users
   - ✅ "production" label here means actual live prompts

**Key Points:**
- The two servers are **completely independent** - no automatic sync between them
- Both servers use the same label system (`production`, `development`, `staging`, etc.)
- **🚨 CRITICAL SAFETY: This skill pushes prompts WITHOUT ANY LABELS**
  - Prompts created by this skill will have **NO LABEL**
  - Without a label, the system will NOT select or use the prompt
  - This is a **human-in-the-loop safety control**
  - A human must manually add a label in the Langfuse UI to activate the prompt
Read the full skill on GitHub

Details

Skill name
update-langfuse-staging-server-prompt
Path
skills/update-langfuse-staging-server-prompt/SKILL.md
Repo updated
10 January 2026

FAQ

What does the Update Langfuse Staging Server Prompt skill do?

Push prompt updates to Langfuse (staging or production). Defaults to STAGING (safe). Production requires explicit --production flag + confirmation. NEVER assigns labels (human-in-the-loop safety).

How do I install the Update Langfuse Staging Server Prompt skill?

Claude Code plugin: /plugin marketplace add Freddy-CHEN-ux/00_claude_skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Update Langfuse Staging Server Prompt popular?

It lives in Freddy-CHEN-ux/00_claude_skills, which has 8 GitHub stars and 3 forks.

Related skills

Add Integration

8

Freddy-CHEN-ux/00_claude_skills

Build a new API integration for Nexus. Load when user mentions "add integration", "new integration", "integrate with", "connect to [service]", or "build [service] integration". Interactive workflow that discovers API endpoints, plans the integration, and creates a project for implementation.

Software Development

AI Agents

8

Freddy-CHEN-ux/00_claude_skills

Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, and observability (modern best practices)

AI, LLMs & Agents

AI LLM

8

Freddy-CHEN-ux/00_claude_skills

Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference serving, and lifecycle operations with cost/safety controls.

AI, LLMs & Agents

Acting

5

GAGAA-HUE/ASHUO-claude-skills

角色表演系统——专为 AI 视频生成(Seedance 2.0)设计的角色行为/表演指导系统。 核心理念:表演是压力下的行为,而非情绪展示。将角色的目标、障碍、策略、 节拍变化、潜台词分解为可观察的身体语言和微表情。擅长:角色动机设计、 情绪节奏控制、非语言行为描述、反应时序、身体状态锚定。触发词:角色表演、 演技设计、角色行为、表演指导、acting、character performance、emotional beats。

AI, LLMs & Agents

Understanding Mistakes

8

Freddy-CHEN-ux/00_claude_skills

Use when user says something went wrong, AI did Y instead of X, or wants to understand why a deviation happened. Manually invoked post-mortem analysis.

AI, LLMs & Agents

Art Asset Designer

5

GAGAA-HUE/ASHUO-claude-skills

美术资产设计师——专为剧本/故事内容拆解人物与场景美术资产,并为每个资产生成可直接用于 AI 图像生成工具的提示词。当用户提到剧本、故事、脚本、分镜、需要美术资产、出图提示词、角色设计、场景设计等内容时,立即触发此技能。即使用户只是说"帮我拆一下剧本里的角色"或"我需要生成场景图",也应立即以美术资产设计师身份介入。覆盖从剧本解析 → 资产清单整理 → 风格确认(必须向用户询问,禁止自行推断)→ 分类提示词生成的完整流程。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.