Skill issue: Lessons from skilling up coding agents to use Langfuse - Marc Klingen, Clickhouse
Without a skill, Claude Code adds Langfuse using stale pre-training context, ships broken instrumentation, then catches the failure and fetches current docs to fix it. The resulting trace captures two LLM calls with no visibility into what the agent actually did.
Marc Klingen covers the six learnings from building a skill to close that gap: surfacing a natural language search endpoint so agents stop crawling 478 documentation pages, why pointing to references beats duplicating content, and what happened when they ran an auto-research loop on the skill itself. Three of six suggested improvements shipped, but their target function nearly backfired by optimizing out the documentation-fetching steps that make the skill reliable over time.
Speaker info:
- https://x.com/marcklingen
- https://www.linkedin.com/in/marcklingen/
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
More on: Agent Foundations
View skill →Related AI Lessons
⚡
⚡
⚡
⚡
AI Agents Don't Crash. They Drift. Here's the Framework to See It.
Dev.to · Varsha Das
How Can AI Detect and Analyze Traffic Patterns in Real Time?
Medium · AI
Overland AI: The Autonomous War Machine That Actually Works — For Now
Medium · AI
How to Find Your Own Code Inside ChatGPT (Tiger Team)
Medium · ChatGPT
🎓
Tutor Explanation
DeepCamp AI