Cubepi Trace | Agent Skills Atlas

About this skill

Use when debugging a cubepi/cubebox agent run — a missing final reply, a tool that misbehaved, a 4xx from the model, wrong token/cache numbers, or "why did the agent do that?". Reads the JSONL traces cubepi writes per run via the cubepi trace CLI (ls / view / follow / stats) to inspect the span tree, errors, tool inputs/outputs, and token usage. Triggers on phrases like "查一下这个 run", "trace 一下", "为什么最后一轮没回复", "工具结果不对", "看 trace".

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Unavailable

HTTP 404

About scan coverage and limitations

Original listing metadata

Original name

cubepi-trace

Original description

Use when debugging a cubepi/cubebox agent run — a missing final reply, a tool that misbehaved, a 4xx from the model, wrong token/cache numbers, or "why did the agent do that?". Reads the JSONL traces cubepi writes per run via the `cubepi trace` CLI (ls / view / follow / stats) to inspect the span tree, errors, tool inputs/outputs, and token usage. Triggers on phrases like "查一下这个 run", "trace 一下", "为什么最后一轮没回复", "工具结果不对", "看 trace".

About this listing

Category: Engineering
Reported license: MIT
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.