Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/langfuse-coding-trace
为编码工作流提供 Langfuse 链路追踪能力。当执行 logic-layer-method-impl 等编码 skill 时，自动上报每个大步骤（识别模式、代码生成、编译、启动、单元测试、代码修复）的开始/结束事件到自部署 Langfuse，实现全流程可观测。凡用户涉及编码流程监控、追踪、可观测性、Langfuse 上报时均应触发此 skill，配合其他编码类 skill 联合使用。
Passed 19 of 22 test cases with the skill, and 4 of 22 without it.
and 23 more in the full report
15 fixed4 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
What trace name should be passed to trace-start when beginning an automated coding session for implementing a backend logic method?
| Checked | Without skill | With skill |
|---|---|---|
| Uses logic-layer-method-impl as the trace name | Missed | Passed |
| Passes trace name via --name argument | Missed | Passed |
The instructions your model reads when the skill loads.
为编码工作流每个关键步骤异步上报 Trace/Span 到 Langfuse，不阻塞主流程。
需设置以下环境变量（未设置时静默跳过追踪）：
LANGFUSE_PUBLIC_KEY # Langfuse 公钥
LANGFUSE_SECRET_KEY # Langfuse 私钥
LANGFUSE_HOST # 自部署地址，如 http://192.168.1.100:3000
<skills_dir>/langfuse-coding-trace/scripts/trace.py
调用前先确认
LANGFUSE_PUBLIC_KEY是否存在，不存在则跳过所有追踪调用。
TRACE_ID=$(python "<skills_dir>/langfuse-coding-trace/scripts/trace.py" trace-start \
--name "logic-layer-method-impl" \
--input '{"method": "目标方法名", "mode": "首次编码/需求变更"}')
echo "Trace started: $TRACE_ID"
# 开始 Span（同步获取 span_id，耗时极短）
SPAN_ID=$(python "<skills_dir>/langfuse-coding-trace/scripts/trace.py" span-start \
test cases passed, vs 4 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.